# Ozwell — complete site content > Ozwell is an AI medical assistant for healthcare practices, built by BlueHive > Health, LLC. It transcribes patient visits, writes structured SOAP notes, answers > inbound calls, and integrates with the EHR and other systems a practice runs. > HIPAA compliant; the first and only Drummond pDSI-Risk certified AI-powered > Health IT solution. Source: https://ozwell.ai · Contact: info@ozwell.ai · Free trial: https://app.ozwell.ai/?utm_source=ozwell.ai --- # Product overview ## What Ozwell does ### Smart scribing & accurate charting: Reclaim your time, refocus on patient care Ozwell transcribes the encounter as it happens, pulls out the clinical detail, and populates the chart — handling specialised terminology rather than everyday speech. You review a finished note instead of writing one. - Transcribe patient visits - Automate chart population ### Smart call handling: Optimize your lines, elevate your service Configure your own voice prompts and let Ozwell answer. It handles refill requests, appointment reminders, and routine questions, routes what it should not answer, and gives your front desk back the phone. - Automate routine calls - Personalize caller experience ### Works inside your stack: No new system to learn Ozwell connects to WebChart, Enterprise Health, and the EHR, HRIS, and CRM tools you already run, then writes results back where your team expects to find them. Orders, referrals, and follow-ups queue as reviewable actions — nothing files until you approve it. - Write back to the chart - Approve before anything files ## How it works Ozwell listens to the visit, understands the clinical detail, and does the documentation — then gets better at your terminology every time you use it. ### Step 1: Listen Start from phone or chat, on desktop or mobile. Ozwell transcribes the encounter in real time and handles specialized clinical terminology, not just everyday speech. ### Step 2: Understand It reads the full context of the conversation rather than matching keywords — pulling out conditions, medications, allergies, vitals, and referrals as discrete clinical facts. ### Step 3: Act A structured SOAP note is written for you, with orders, referrals, and follow-ups queued as reviewable actions. Nothing is filed until you approve it. ### Step 4: Learn Your corrections feed back in, so accuracy improves against your own vocabulary and documentation style. Results sync to EHR, HRIS, and the rest of your stack. ## Capabilities in detail Ozwell adapts to how your practice already runs, rather than asking your practice to adapt to it. ### Learns your vocabulary Every correction you make feeds back in, so accuracy improves against your own terminology and note style instead of a generic model average. ### Custom instructions per clinician Set your name, title, and standing instructions once. Notes come out in your voice and your format, not a house template. ### Specialty terminology, not just speech Built to interpret complex medical, legal, and technical language — the vocabulary general-purpose dictation reliably mangles. ### A phone line that answers itself Refill requests, appointment reminders, and routine questions handled with your own voice prompts, escalating the rest to a human. ### Works on the phone in your pocket iOS and Android apps on the same account. Start a note between rooms on mobile and finish it at the desktop. ### Nothing files without approval Orders, referrals, and follow-ups arrive as reviewable actions. You stay the last step before anything reaches the record. ## Security and certification The market's first and only Drummond pDSI-Risk certified AI-powered Health IT solution The certification confirms that Ozwell's AI platform meets key benchmarks for intervention risk assessment and mitigation — a critical step in supporting the responsible use of AI in clinical care. Verified attributes: HIPAA compliant, Mobile friendly, Drummond certified. ## The documentation burden Ozwell addresses Clinicians did not train for data entry. The shift to electronic records moved the paperwork onto the screen without reducing any of it — and the cost shows up in hours, in burnout, and in dollars. - **2 hours** — of documentation and desk work for every hour spent with a patient. Source: Sinsky et al., 2016. - **63%** — of physicians report symptoms of burnout, with administrative burden a leading cause. Source: Shanafelt et al., 2022. - **52%** — of the primary-care workday goes to EHR tasks — 5.9 hours out of 11.4. Source: Arndt et al., 2017. - **$286B** — spent every year on administrative complexity instead of on patient care. Source: Shrank et al., 2019. ## Customer testimonials ### Jeffrey Margolis, M.D., President of Michigan Health Professionals > BlueHive AI [Ozwell] has been an absolute game changer for me. I’ve been using it for just two weeks, but it already feels like a major step forward compared to when we transitioned from paper charts to EMRs. With EMRs, I often found myself focusing more on the screen than on the patient, which really took away from the personal interaction. BlueHive [Ozwell] has given me the freedom to go back to being a doctor—looking my patients in the eye and focusing on them, while the AI handles the documentation. It’s liberating. Most of us in the practice have gained back an hour or two each day, and the improvement in patient care is remarkable. (Quotes predate the BlueHive AI → Ozwell rename; the bracketed name marks the current product name.) ### Richard Zekman, D.O., Division of Clinical Hematology & Medical Oncology > One of the biggest challenges in medicine is time. We spend a lot of hours on administrative tasks like charting—up to one to two hours daily. This time is taking away from patient care and even our personal lives. BlueHive AI [Ozwell] has already helped cut down that time. It allows me to focus more on patient care without the stress of additional paperwork at the end of the day. For example, I saw 35 patients today, and all my notes and referrals were completed by the end of the clinic day. (Quotes predate the BlueHive AI → Ozwell rename; the bracketed name marks the current product name.) ## Frequently asked questions ### What is Ozwell? Ozwell is an AI medical assistant for healthcare practices. It transcribes patient visits, writes structured clinical notes, answers inbound calls, and connects to the EHR and other systems you already use, so documentation and routine administration stop consuming clinical time. ### How does the Ozwell phone assistant work when people call in? The Ozwell phone assistant handles incoming calls with advanced natural language processing. When a call comes in, it can understand and respond to a wide range of inquiries — scheduling appointments, providing information, or routing the call to the appropriate department. It interprets complex industry-specific terminology, which makes it particularly useful in fields like healthcare and legal services, so callers receive prompt, accurate, and professional service every time. ### How does Ozwell integrate with my existing systems? Ozwell integrates with a wide range of existing systems, including EHR, HRIS, CRM, and other essential tools — [WebChart](https://webchartnow.com) and [Enterprise Health](https://enterprisehealth.com) included. Results are written back where your team already looks for them, so workflows improve without disrupting your current setup. The Help Center has a full WebChart integration guide. ### Is Ozwell HIPAA compliant, and how is the AI risk assessed? Yes. Ozwell is HIPAA compliant and is the first AI-powered Health IT solution to hold Drummond pDSI-Risk certification, which confirms the platform meets benchmarks for predictive decision support intervention risk assessment and mitigation. Our full source attribute disclosures are published on the certification page. ### What is Drummond pDSI-Risk certification? It is an independent certification, issued by Drummond Group, that a predictive decision support intervention meets the intervention risk management and source attribute disclosure requirements of ASTP/ONC § 170.315(b)(11). Ozwell was the first AI-powered health IT product to achieve it, announced on July 15, 2025. In practice it means an impartial third party has reviewed how the risks of the AI are assessed, mitigated, and disclosed — not merely that the vendor says they are. ### Does Ozwell make clinical decisions on its own? No. Ozwell is designed to inform and augment clinical decision-making, not to replace clinical management — that is the intended decision-making role published in our source attribute disclosure. It drafts documentation and queues actions; a clinician reviews and approves them, and nothing reaches the patient record until they do. ### When should Ozwell not be used? Ozwell is not intended for emergency or critical care settings where real-time clinical decision-making is required, nor as a substitute for professional medical judgment. We also caution against relying on it for highly specialized or nuanced care, such as advanced pain management or rare disease treatment. These limits are published in full in our source attribute disclosure rather than left for you to discover. ### Which clinicians and care settings is Ozwell built for? Ozwell is intended for outpatient clinics, hospitals, and administrative offices, and is built for primary care physicians, specialists, nurses and nurse practitioners, physician assistants, and the administrative staff involved in documentation and care coordination. It supports clinicians working with a broad range of patient populations, including routine, preventive, and chronic condition care. ### Who builds Ozwell? Ozwell is built by BlueHive Health, LLC, part of Medical Informatics Engineering, Inc. — the team behind the [WebChart](https://webchartnow.com) and [Enterprise Health](https://enterprisehealth.com) EHRs, with a long history in health IT rather than a general AI company entering healthcare. BlueHive Health is the named developer on our ONC source attribute disclosure. ### Can Ozwell understand and process industry-specific terminology? Yes. Ozwell is equipped with advanced natural language processing that allows it to understand and process complex industry-specific terminology, including medical, legal, and technical jargon, rather than only everyday speech. ### Can I customize Ozwell to fit my specific workflow? Yes. Ozwell offers customizable workflows, and each user can set their own name, title, and custom instructions so that output matches their documentation style. This ensures alignment with how your organization already works rather than forcing a single house format. ### Does anything get filed to the patient record automatically? No. Ozwell drafts the note and queues orders, referrals, and follow-ups as reviewable actions. A clinician approves them before anything is written to the record, so you remain the final check on everything that reaches the chart. ### How does Ozwell stay up to date with my evolving needs? Ozwell continuously learns from your interactions and corrections, adapting to better match your vocabulary and documentation style over time, so it remains useful as your organization grows and changes. ### What kind of support can I expect? The Help Center covers setup, accounts, integrations, and the API, and our team answers questions directly at info@ozwell.ai. Ozwell also includes integrated communication tools with real-time messaging and notifications to keep your team coordinated, whether they work in the office or remotely. ### Is Ozwell easy to use? Yes. Ozwell is designed around an intuitive interface that minimizes learning curves, and it runs on the web plus iOS and Android, so most people are productive without training. You can start a note on mobile between rooms and finish it at a desktop on the same account. --- # About Ozwell ## Our mission At Ozwell, we believe technology should empower—not burden—healthcare professionals. Our AI-driven solutions automate documentation, optimize workflows, and enhance decision-making, giving providers more time to focus on delivering exceptional care. ### More patients, less burnout The weight of administrative tasks contributes to provider burnout, pulling focus away from the calling that brought you to healthcare in the first place. With Ozwell, you can reclaim your time, your energy, and your passion for patient care. ### Reduce errors, increase confidence Documentation should support, not slow down, patient care. Ozwell helps providers capture critical details efficiently, reducing administrative strain and improving workflow clarity—so you can focus on making informed decisions with confidence. ### Smart integration, effortless workflow Too often, new systems disrupt your workflow instead of supporting it. Ozwell seamlessly integrates into your existing tools, ensuring a smooth experience that enhances—never hinders—your ability to provide care. ## Our values ### Compassion We believe technology should enhance, not replace, human connection in healthcare. Ozwell is built to support providers, reduce burnout, and give them more time to focus on delivering quality patient care. ### Innovation Healthcare is constantly evolving, and so are we. Ozwell leverages cutting-edge AI to simplify workflows, optimize efficiency, and help providers stay ahead in an ever-changing landscape. ### Clarity Documentation should be an asset, not a burden. Ozwell streamlines processes, providing clear, structured, and actionable insights so providers can make informed decisions with confidence. ### Integrity We prioritize responsible technology. Ozwell is designed with healthcare in mind, ensuring AI solutions align with ethical standards, regulatory requirements, and real-world needs. ### Collaboration Great care doesn't happen in isolation. Ozwell seamlessly integrates with existing systems, creating a connected ecosystem that enhances communication and teamwork across healthcare organizations. ### Support From setup to day-to-day operations, our team is here to help. Whether it's a quick question or in-depth troubleshooting, we provide responsive, knowledgeable support so you can get the most out of Ozwell. --- # Help Center ## Topic: Accounts ### Can I access my Ozwell account from another device? URL: https://ozwell.ai/docs/can-i-access-my-ozwell-account-from-another-device/ Yes, you can access your Ozwell account from another device. Simply log in using your credentials on the new device. When you access your Ozwell account from another device, all of your sessions will appear on the new device as well. This allows you to seamlessly continue your work across multiple devices. If you have any questions or need assistance, please visit https://ozwell.ai or email or info@ozwell.ai ### Creating an account URL: https://ozwell.ai/docs/creating-an-account/ Ozwell.ai offers four convenient ways to create an account. You can register using **Google, Facebook, Windows**, or sign up with an **email and password**. This guide will walk you through each method so you can get started quickly. ![](https://ozwell.ai/images/wp/2025-01-Screenshot-2025-02-04-at-1.48.51_PM-1024x536.webp) ### Step 1: Choose a sign-up method #### Option 1: Sign Up with Google 1. Tap **Continue with Google**. 2. Select your Google account (or sign in if prompted). 3. A consent screen will appear—review the details and tap **Allow** to share: • Your name • Email address • Language preference • Profile picture 4. After confirming, you will be redirected back to the **BlueHive AI** app, and your account will be created automatically. 📌 **Note:** Google will authenticate your identity, so you won’t need to set a password. #### Option 2: Sign Up with Facebook 1. Tap **Continue with Facebook**. 2. Log in to your Facebook account (or choose your account if already logged in). 3. Grant permission for **BlueHive AI** to access your profile information. 4. Once confirmed, your account will be created, and you will be logged in automatically. 📌 **Note:** Your Facebook profile name and email will be used to create your account. #### Option 3: Sign Up with Windows 1. Tap **Continue with Windows**. 2. Enter your **Microsoft email** and **password** (used for Outlook, Office 365, etc.). 3. If prompted, approve the sign-in request via **two-factor authentication (2FA)**. 4. Once verified, your account will be created, and you will be redirected to the **BlueHive AI** app. 📌 **Note:** If you’re using a corporate Microsoft account, check with your IT department for permission to integrate external apps. #### Option 4: Sign Up with Email and Password 1. Tap **Sign Up with Email**. 2. Enter your **email address**. 3. Create a **strong password** that meets security requirements: • At least 8 characters long • Includes uppercase and lowercase letters • Contains at least one number • Includes a special character (e.g., @, #, $) 4. Tap **Register**. 5. You will be prompted to **re-enter your password** for confirmation. 6. Tap **Register** again. 7. By clicking **Register**, you agree to **BlueHive AI’s Privacy Policy and Terms of Use**. ### How to Reset Your Password URL: https://ozwell.ai/docs/how-to-reset-your-password/ Forgot your password? No worries! Resetting your **BlueHive AI** password is quick and easy. Just follow these simple steps to regain access to your account. #### Step 1: Go to the Login Screen 1. Open the **BlueHive AI** app or go to [app.ozwell.ai](https://app.ozwell.ai). 2. On the login screen, tap **Forgot Your Password?** #### Step 2: Request a Password Reset Link ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-04-at-2.01.14_PM-911x1024.webp) 1. After selecting **Forgot Your Password?**, you’ll be prompted to enter your **registered email address**. 2. Type in your email and ensure it is correct. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-04-at-2.01.51_PM-1024x892.webp) 3. Tap the **Email Reset Link** button. 4. A pop-up will confirm that the **password reset email has been sent successfully**. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-04-at-2.02.08_PM-969x1024.webp) 📌 **Note:** If you don’t see the pop-up, check your internet connection and try again. #### Step 3: Check Your Email 1. Open your **email inbox** (associated with your BlueHive account). 2. Look for an email from **bluehive.com** with the subject **“How to reset your password on BlueHiveHealth, LLC.”**. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-04-at-2.02.30_PM-1024x322.png) 3. If you don’t see the email within a few minutes, check your **spam/junk** folder. 📌 **Didn’t receive the email?** • Ensure you entered the correct email address. • Try tapping **Resend Email** on the reset screen. #### Step 4: Create a New Password 1. Click on the **password reset link** in the email. 2. You’ll be directed to a **Reset Password** page. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-04-at-2.02.54_PM-1024x668.png) 3. Enter a **new strong password** that meets the security requirements: • At least **8 characters** • Includes **uppercase and lowercase letters** • Contains **at least one number** • Has **at least one special character** (e.g., @, #, $) 4. Confirm your new password by re-entering it. 5. Tap **Submit** to complete the password reset process. 📌 **Tip:** Use a **password manager** to securely store your new password. #### Step 5: Log In with Your New Password 1. Once you receive the confirmation that your password has been **reset successfully**, return to the **login screen**. 2. Enter your **email address** and new **password**. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-04-at-1.48.51_PM-1024x536.webp) 3. Tap **Sign In** to access your account. 🎉 **Success! You’ve now reset your password and can continue using BlueHive AI as usual.** #### Troubleshooting Common Issues **1. Didn’t Receive the Password Reset Email?** • Check your **spam or junk folder**. • Ensure you entered the **correct email address**. • Tap **Resend Email** on the reset screen. **2. Reset Link Expired?** • Password reset links expire after a certain time for security reasons. • Repeat **Step 1** to request a new reset link. **3. Can’t Log In After Resetting?** • Double-check that you are using your **new password** (not the old one). • If you’re still having trouble, try **resetting your password again**. **Conclusion** Resetting your **BlueHive AI** password is a quick and simple process. By following these steps, you can regain access to your account in minutes. ## Topic: API ### Completions API URL: https://ozwell.ai/docs/completions-api/ ## Overview Our Completions API allows you to send text to our AI engine and receives a response based on your input. ## Request To interact with the Completions API, send a POST request to the following URL: ``` POST https://ai.bluehive.com/api/v1/completion ``` The request should include the following JSON payload: ``` { "prompt": "Hello, world!", "systemMessage": "You are a helpful chatbot named Will." } ``` ## Response The API will return a JSON response structured as follows: ``` { "logId": "zucj6bL6cx4FfGXnA", // BlueHive Event Log ID "status": 200, "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Hello, human!", "refusal": null }, "logprobs": null, "finish_reason": "stop" } ] } ``` ## Example Here is an example of how to use the Completions API with `curl`: ``` curl -X POST https://ai.bluehive.com/api/v1/completion \ -H "Authorization: Bearer BHSK-sandbox-SAMPLE" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Hello, world!", "systemMessage": "You are a helpful chatbot named Will." } ``` ## Conclusion The Completions API is a powerful tool for integrating AI-driven responses into your applications. Make sure to format your requests correctly and handle the responses appropriately for the best experience. ## Topic: Experiments ### How to enable Ozwell’s experimental features URL: https://ozwell.ai/docs/how-to-enable-ozwells-experimental-features/ Ozwell frequently rolls out experimental features to provide users with early access to the latest innovations. These features can offer enhanced functionality but may still be under development. Below is a step-by-step guide on how to enable these experimental features within your Ozwell application. ## Step 1: Navigate to experiments - Click on your profile icon located at the top-right corner of the application. - From the dropdown menu, select **"Experiments"**. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.14.17_PM.png) ## Step 2: Enable Experimental Features - A pop-up window will appear, showing various experimental features organized in tabs. - Click on the desired tab to view details of specific experiments. For example: **WebChart Smart Actions**: This tab provides a summary of the feature and includes a button to enable it. - **Encounter Link**: Clicking this tab will give you a summary of this specific experiment and a button to enable it. - To enable a feature, click the **"Enable"** button within each specific tab. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-21-at-12.04.11_PM-1024x948.webp) ## Step 3: Activate Experiments - After enabling your desired features, refresh your page to activate the experiments. By following these steps, you can take advantage of Ozwell's cutting-edge capabilities while contributing to their refinement. ### WebChart Smart Actions URL: https://ozwell.ai/docs/webchart-smart-actions/ WebChart Smart Actions streamline documentation with **one click**, eliminating the need for manual charting. This feature automatically records **vital signs, conditions, allergies, medications, and referrals** using AI-generated insights. With pre-populated recommendations, documentation becomes effortless, allowing providers to focus on **patient care, not clicks**. ## Step 1: Enable experimental feature To use Smart Actions, you must first enable it in the settings. - Click on your **profile icon** in the top-right corner of the application. - Select **“Experiments”** from the dropdown menu. - A pop-up window will display various experimental features. - Navigate to the **WebChart Smart Actions** tab for feature details. - Click the **Enable** button. - **Refresh the page** to apply changes. ## Step 2: Dictate a visit encounter - Tap the **blue “Start” button** to begin recording. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-21-at-12.32.16_PM-1024x561.png) - Dictate the visit encounter as you normally would. - When finished, tap the **blue “Stop” button** to end the recording. ## Step 3: Review actions Once you've dictated the encounter, your transcription will appear with the attached audio recording that can be scrubbed through. Documentation will be produced automatically, including a soap note. Under the soap note is where you will see the AI-generated actions. These actions are generated when the AI hears you refer to a condition, an order, a medication, or an allergy. You can look through these and make sure that the action was transcribed correctly. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-21-at-12.34.39_PM-1-1024x646.webp) ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-21-at-12.34.52_PM-2-1024x579.webp) ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-21-at-12.35.05_PM-1-1024x591.webp) Clicking on the bug icon will show the coded values of each action and exactly what is being captured by Ozwell and will be entered into the patient's chart. Clicking on the bug icon again will close the expanded screen. ![](https://ozwell.ai/images/wp/2025-03-Screenshot-2025-03-10-at-10.20.46_PM-1024x408.png) The blue switch allows you to tell Ozwell whether to send the action to the patients chart or to disregard that action. The switcher is automatically set to send all actions to the patients chart. When the switcher is white with a blue outline, then the action will not be sent to the patients chart. ![](https://ozwell.ai/images/wp/2025-03-Screenshot-2025-03-10-at-10.23.41_PM.png) ## Step 4: Perform Actions When you are ready to send the actions over to the patients chart, you can click the perform actions icon at the bottom of the smart actions drop down. ![](https://ozwell.ai/images/wp/2025-03-Screenshot-2025-03-10-at-10.25.21_PM.png) ## Step 5: Check to see if actions were performed successfully When the actions have been sent to the patient's chart the blue switcher will be replaced by a green check mark to indicate the actions that were transmitted successfully. If the switcher is replaced by the red caution icon, it is because their was an unexpected error that occurred when trying to transmit the action to the patients chart. The reason for the error is not the same for everyone, therefore, if you have any trouble with smart actions, please contact us at info@ozwell.ai ![](https://ozwell.ai/images/wp/2025-03-Screenshot-2025-03-10-at-10.40.06_PM.png) ![](https://ozwell.ai/images/wp/2025-03-Screenshot-2025-03-10-at-10.41.10_PM.png) It is also import to check on your EHR to see if the actions were imported correctly. If they were not imported correctly, make sure to contact your organizations Ozwell rep for more guidance. ## Still need help? If you encounter any issues or need further assistance, please reach out to **info@ozwell.ai** or contact your **Ozwell representative**. ## Topic: Getting Started ### How to Download and Install the BlueHive AI App (Powered by Ozwell) from the App Store URL: https://ozwell.ai/docs/how-to-download-and-install-the-bluehive-ai-app-powered-by-ozwell-from-the-app-store/ The **BlueHive AI** app, powered by **Ozwell**, is an advanced AI-driven tool designed to enhance physician documentation, streamline workflows, and improve overall healthcare efficiency. Whether you’re a clinician looking to reduce administrative burdens or a healthcare professional integrating AI into your practice, this guide will help you quickly download and install the **BlueHive AI** app from the App Store. #### Step 1: Prepare Your Device Before downloading the **BlueHive AI** app, make sure: ✔️ Your device is **connected to Wi-Fi or cellular data**. ✔️ You have **enough storage space** for the app. ✔️ You are **signed in to your Apple ID**, which is required for app downloads. To check your Apple ID: 1. Open the **Settings** app. 2. Tap **[Your Name]** at the top. 3. If you are not signed in, tap **Sign in to your iPhone** and enter your Apple ID credentials. #### Step 2: Open the App Store 1. Locate and open the **App Store** (a blue icon with a white “A”). 2. Tap on the **Search** tab at the bottom right of the screen. #### Step 3: Search for BlueHive AI 1. In the **search bar**, type: 🔍 **BlueHive AI** 2. Tap **Search** on your keyboard. 3. Find the **BlueHive AI** app in the search results. Look for the correct logo and developer name to ensure you are downloading the official app. ![](https://ozwell.ai/images/wp/2025-02-IMG_2599-472x1024.webp) #### Step 4: Download and Install the BlueHive AI App 1. Tap the **Get** button. 2. Authenticate your download with one of the following: • **Face ID** (double-click the side button and look at the screen). • **Touch ID** (place your finger on the Home button). • **Apple ID Password** (enter it manually if prompted). 3. The app will begin downloading. You’ll see a progress indicator on the app icon. #### Step 5: Open and Set Up the BlueHive AI App 1. Once installed, tap **Open** from the App Store or find the app on your home screen. 2. Follow the **on-screen setup instructions**, which may include: • Logging in or signing up. To see more on how to create an account please click [here](https://ozwell.ai/docs/creating-an-account/). ![](https://ozwell.ai/images/wp/2025-02-IMG_2600-1-472x1024.png) • **Granting permissions** for microphone access. ![](https://ozwell.ai/images/wp/2025-02-IMG_2602-472x1024.png) ![](https://ozwell.ai/images/wp/2025-02-IMG_2603-472x1024.png) • **Agreeing to the terms**. ![](https://ozwell.ai/images/wp/2025-02-IMG_2601-472x1024.webp) #### Troubleshooting Common Issues **1. Can’t Find the BlueHive AI App in the App Store?** • Ensure your **App Store region** is set correctly (Settings > Apple ID > Country/Region). • Make sure your device is running **iOS 14 or later** (Settings > General > Software Update). **2. Download Button is Greyed Out?** • Check if **Screen Time or Content Restrictions** are blocking app downloads (Settings > Screen Time > Content & Privacy Restrictions). • Ensure your **Apple ID payment method is valid** (even for free apps). **3. The App Won’t Download or Install?** • **Restart your device** and try again. • **Pause and resume the download** by tapping the app icon. • **Try switching** between Wi-Fi and cellular data. **Conclusion** Downloading and installing the **BlueHive AI (Powered by Ozwell)** app is a seamless process. Once set up, you’ll gain access to AI-powered features that significantly reduce documentation time and enhance patient care. ### Who is Ozwell? URL: https://ozwell.ai/docs/who-is-ozwell/ ![](https://ozwell.ai/images/wp/2025-01-Ozwell-Branding-Whiteboard-4.png) Ozwell (formely known as BlueHive AI) is your all in one AI medical assistant designed to understand and respond to a wide array of medical queries and tasks. Ozwell offers advanced solutions for documentation, interactive voice response (IVR), and workflow optimization. Ozwellaims to support healthcare providers and employers by streamlining processes and enhancing efficiency. ## What is an AI medical assistant? An **AI medical assistant** is an artificial intelligence-powered tool designed to assist healthcare professionals with various tasks, improving efficiency, accuracy, and patient care. These assistants leverage **natural language processing (NLP), machine learning, and automation** to streamline medical workflows. #### Key Functions of an AI Medical Assistant: ##### Medical Documentation & Transcription - Captures and transcribes physician-patient conversations in real-time. - Generates clinical notes automatically, reducing administrative burden. - Uses AI-driven dictation to speed up medical charting. ##### Clinical Decision Support - Analyzes patient records and medical guidelines to offer diagnostic suggestions. - Provides alerts for potential medication interactions and contraindications. - Helps in treatment planning by referencing medical literature. ##### Virtual Patient Assistance - Answers patient questions via chatbots or voice assistants. - Helps with scheduling appointments and medication reminders. - Provides health education and self-care guidance. ##### AI-Powered Medical Scribes - Acts as a **real-time scribe**, reducing the time physicians spend on paperwork. - Integrates seamlessly into Electronic Health Records (EHR) systems. - Uses **speech-to-text and NLP** to structure clinical documentation. ##### Workflow Automation - Automates repetitive administrative tasks (e.g., insurance verification, billing). - Assists with population health management and predictive analytics. - Streamlines hospital and clinic operations. ## Topic: Integrations ### WebChart / Ozwell Integration User Guide URL: https://ozwell.ai/docs/webchart-ozwell-integration-user-guide/ This guide outlines the WebChart/Ozwell integration process. WebChart is fully integrated with Ozwell AI. To turn on Ozwell in your system, contact your administration. #### Getting Started The following items are required to enable the integration: - Login for BlueHive - Login for WebChart #### Connect to WebChart - Log into your Ozwell AI (formerly known as BlueHive AI) account. ([https://www.bluehive.com/login?redirect=https%3A%2F%2Fapp.ozwell.ai%2F&loggedOut=true](https://www.bluehive.com/login?redirect=https%3A%2F%2Fapp.ozwell.ai%2F&loggedOut=true)) - Clicking on your profile picture will display a drop down of menu choices. Click on the "Integrations" menu option. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.14.17_PM-1.png) 4. Locate the WebChart EHR integration and select "Setup" ![](https://ozwell.ai/images/wp/2025-02-Set-up-1024x457.webp) 5. Type in you WebChart handle. For example, if your system is client.webchartnow.com, your handle is "client" ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.25.05_PM.png) 6. Once Ozwell as located you WebChart system, it will display your practices logo and you can select "Next" to continue to log into your WebChart system. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.27.08_PM.png) 7. This screen may look different depending on your provider organization. From here, you should log into you WebChart account using your WebChart credentials. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.29.25_PM.png) 8. Once logged in, you will be asked to agree to allow Ozwell AI to access the following information: - Create and access patient data - Create and view documents - Access your schedule and appointments - View and manage your account information and settings - Your user data (name, email, username, etc.) 9. Click "Connect Ozwell AI" ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.31.06_PM-1024x534.png) 10. Once connected, you will be directed back to Ozwell AI. #### Viewing WebChart dashboard To view the dashboard of your WebChart system from Ozwell AI, read through the following steps: - Click on "Integrations" from the menu dropdown. - Select "Dashboard". ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.38.38_PM.png) - From the dashboard, you can view recent patients and patients with appointments for today. Ozwell will keep track of the last time the page was updated which is displayed in parentheses. You can refresh this list by click the **blue fresh icon.**[1](#781807c8-53cf-4342-872c-00c4c847b656) This section will display the patients name, date of birth, medical record number, appointment time, time last accessed, and the ability to **link out to their chart in WebChart.**[2](#6123911c-e634-4987-9566-2f8fce37d905) The section below shows what WebChart system is connected to your account and the username associated to the WebChart account. [3](#da8b87a4-a471-4846-8d6d-d75cf6afe573) ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-1.04.15_PM-1-1024x497.png) - Pictured above [↩︎](#781807c8-53cf-4342-872c-00c4c847b656-link) - Pictured above [↩︎](#6123911c-e634-4987-9566-2f8fce37d905-link) - Pictured above [↩︎](#da8b87a4-a471-4846-8d6d-d75cf6afe573-link) #### Changing which WebChart system is linked to Ozwell - Clicking on your profile picture will display a drop down of menu choices. Click on the "Integrations" menu option. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.14.17_PM-1.png) - Locate the WebChart EHR integration and select "Change System" ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.20.41_PM.png) - Type in you WebChart handle. For example, if your system is client.webchartnow.com, your handle is "client" ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.25.05_PM.png) - Once Ozwell as located you WebChart system, it will display your practices logo and you can select "Next" to continue to log into your WebChart system. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.27.08_PM.png) - This screen may look different depending on your provider organization. From here, you should log into you WebChart account using your WebChart credentials. ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.29.25_PM.png) - Once logged in, you will be asked to agree to allow Ozwell AI to access the following information: Create and access patient data - Create and view documents - Access your schedule and appointments - View and manage your account information and settings - Your user data (name, email, username, etc.) - Click "Connect Ozwell AI" ![](https://ozwell.ai/images/wp/2025-02-Screenshot-2025-02-11-at-12.31.06_PM-1024x534.png) - Once connected, you will be directed back to Ozwell AI. ## Topic: Setup Process ### How to Customize Ozwell: Set Your Name, Title, and Custom Instructions URL: https://ozwell.ai/docs/how-to-customize-ozwell-set-your-name-title-and-custom-instructions/ ## Overview Ozwell allows you to personalize your experience by setting your preferred name, professional title, and custom instructions for how Ozwell should respond. This ensures that Ozwell addresses you correctly and tailors its responses to your workflow needs. ## 1. Access Your Profile Settings - Click on your profile icon in the top right corner of the Ozwell dashboard. - Select **Settings** from the dropdown menu. ![](https://ozwell.ai/images/wp/2025-05-Screenshot-2025-05-09-at-4.08.56_PM.png) ## 2. Open the “Customize Ozwell” Section - In the settings pop-up, locate the section labeled **Customize Ozwell**. ## 3. Set Your Name and Title - In the field labeled “What should Ozwell call you?”, enter your preferred name and job title. *Example:* `Internist Butler, Physician` - Ozwell will use this name and title when addressing you in responses. ## 4. Add a Custom Instruction - In the custom instruction box, type any specific guidance you want Ozwell to follow in its responses. *Example:* `Always output a separate "HPI" section in narrative format so I can copy and paste it into my EMR.` - This ensures Ozwell consistently includes a narrative HPI section in its documentation outputs. ![](https://ozwell.ai/images/wp/2025-05-Screenshot-2025-05-09-at-4.09.43_PM-886x1024.webp) ## 5. Save Your Changes - Click **Save Changes** to apply your customizations. ## 6. See Your Customization in Action - After saving, Ozwell will immediately begin responding according to your preferences. - For example, when you request a SOAP note, Ozwell will include a separate HPI section in narrative format, as specified. **Need More Help?** For additional tips and support, visit [ozwell.ai](https://ozwell.ai/?utm_source=bluehive&utm_medium=chat&utm_campaign=bluehive-ai) or contact our team at [info@ozwell.ai](mailto:info@ozwell.ai). --- # Blog ## Ozwell pDSI Source Attributes URL: https://ozwell.ai/blog/ozwell-pdsi-source-attributes/ Published: May 27, 2025 Author: Nicole Welsh Source attributes are the technical and quality information used to create and understand Predictive Decision Support Interventions (pDSI). The Office of the National Coordinator for Health IT (ONC) defines a pDSI, generically understood as Artificial Intelligence (AI), using a three prong test. A pDSI must (1) support decision making based on models, (2) derive relationships from training data, and (3) result in prediction, classification, recommendation, evaluation or analysis. Ozwell uses third party models to inform and augment the clinical decision-making workflow by performing tasks, such as creating SOAP notes and clinical summaries or recommending clinical documentation actions. The following information will help you, as an Ozwell end user, understand the scope and purpose of Ozwell, its intended uses and limitations, and make an informed decision to trust the validity and fairness of Ozwell's output. ## Details and Output of the Intervention 1. **Name and contact information for the intervention developer**: - Developer: BlueHive Health, LLC. - Contact: Visit [bluehive.com](https://bluehive.com/ai/?utm_source=ozwell&utm_medium=blog&utm_campaign=healthcareaiethics) for more information. 2. **Funding source of the technical implementation for the intervention(s) development**: - Funded by BlueHive Health, LLC. 3. **Description of value that the intervention produces as an output**: - The value output of Ozwell includes: Suggested documentation for SOAP notes (e.g., subjective, objective, assessment, plan). - Assistance with generating medical record entries (e.g., suggested diagnoses, treatment plans). - General recommendations or guidance based on user-provided healthcare-related queries. 4. **Whether the intervention output is a prediction, classification, recommendation, evaluation, analysis, or other type of output**: - Outputs include recommendations, evaluations, and analyses based on user input. ## Purpose of the Intervention 5. **Intended use of the intervention**: - The intended use of Ozwell is to assist healthcare professionals, administrators, and other users in healthcare-related workflows. **Clinical Setting:** Ozwell is designed to be used in various healthcare environments, including outpatient clinics, hospitals, and administrative offices, as a supportive tool for documentation, decision-making, and patient care coordination. - **Patient Population:** While not directly interacting with patients, Ozwell supports healthcare providers working with diverse patient populations. - **Goals and Use Cases:** The intervention aims to streamline documentation (e.g., SOAP notes, DAP notes, etc.), provide general healthcare guidance, and enhance efficiency in healthcare workflows. It is not intended to replace clinical judgment or provide real-time clinical decision-making. 6. **Intended patient population(s) for the intervention’s use**: - **Intended Populations:** Ozwell is designed to support healthcare professionals working with a broad range of patient populations, including but not limited to: Patients with chronic conditions (e.g., diabetes, hypertension). - Patients requiring routine care or preventive services. - Patients in outpatient or primary care settings. - **Populations for Which the Intervention Should Not Be Used:** Patients in emergency or critical care settings where real-time clinical decision-making is required. - Patients requiring highly specialized care (e.g., advanced pain management, complex physical therapy). - Patients in scenarios where direct clinical judgment or immediate action is necessary, such as emergency department (ED) or hospital inpatients. 7. **Intended user(s)**: - **Care Setting**: Ozwell is intended to be used in a variety of healthcare settings, including outpatient clinics, hospitals, and administrative offices. - **Purpose of Intervention**: The intervention is designed to assist with documentation, provide general healthcare guidance, and support healthcare workflows. - **Intended Users**: Primary care physicians. - Specialists - Nurses and nurse practitioners. - Physician assistants. - Healthcare administrators and support staff involved in documentation and care coordination. 8. **Intended decision-making role for which the intervention was designed to be used/for (e.g., informs, augments, replaces clinical management)**: - Intended to **inform** and **augment** decision-making but not to replace clinical management. ## Cautioned Out-of-Scope Use of the Intervention 9. **Description of tasks, situations, or populations where a user is cautioned against applying the intervention**: - **Tasks or Situations to Avoid:** Self-treating complex medical conditions without professional oversight. - Employing Ozwell in emergency or critical care situations where real-time clinical decision-making is required. - Using the intervention as a substitute for professional medical judgment or expertise. - **Populations to Avoid:** Patients requiring highly specialized or nuanced care, such as advanced pain management or rare disease treatment. 10. **Known risks, inappropriate settings, inappropriate uses, or known limitations**: - **Known Risks:** Misaligned medical advice could lead to: Incorrect age-based medication dosing, potentially causing adverse drug reactions in pediatric or geriatric populations. - Prescribing antibiotics for viral infections, contributing to antibiotic resistance. - Recommending antidepressants for conditions like anxiety without proper evaluation, leading to suboptimal treatment outcomes. - **Inappropriate Settings:** Emergency or critical care settings where real-time, high-stakes decisions are required. - **Inappropriate Uses:** Using Ozwell as a substitute for professional medical judgment or as a definitive source for clinical decision-making. - Applying outputs without verifying their alignment with current clinical guidelines or patient-specific factors. - Using Ozwell as a substitute for human health literacy, where the intervention's outputs may be misinterpreted or misapplied without proper guidance. - **Known Limitations:** Some models are limited to knowledge up to May 31, 2024 and may not reflect the latest medical research or guidelines. ## Intervention Development Details and Input Features 11. **Exclusion and inclusion criteria that influenced the training data set**: - Ozwell utilizes models created by third-party providers, such as OpenAI. OpenAI provides some publicly available documentation on inclusion and exclusion criteria related to OpenAI's training data, though specific details about datasets and their exact curation methods aren't fully disclosed. Read more here: [https://cdn.openai.com/papers/gpt-4.pdf](https://cdn.openai.com/papers/gpt-4.pdf) 12. **Use of demographic variables (Race, Ethnicity, Language, Sexual Orientation, Gender Identity, Sex, Date of Birth, Social determinants of health data, Health status assessment data)** as input features: - Ozwell generates outputs based on user-provided text inputs as well as information from a patient’s chart when integrated with an EHR. If the chart, or the user, provides any of the following demographic elements, Ozwell may use them to inform its output: race, ethnicity, age, preferred language, sex, sexual orientation, or gender identity. 13. **Description of demographic representativeness according to variables (Race, Ethnicity, Language, Sexual Orientation, Gender Identity, Sex, Date of Birth, Social determinants of health data, Health status assessment data)** **including, at a minimum, those used as input features in the intervention**: - Ozwell utilizes models created by third-party providers, such as OpenAI. OpenAI provides some publicly available documentation on inclusion and exclusion criteria related to OpenAI's training data, though specific details about datasets, demographic inputs, and their exact curation methods aren't fully disclosed. Read more here: [https://cdn.openai.com/papers/gpt-4.pdf](https://cdn.openai.com/papers/gpt-4.pdf) 14. **Description of relevance of training data to intended deployed setting**: - Ozwell utilizes models created by third-party providers, such as OpenAI. OpenAI provides some publicly available documentation on inclusion and exclusion criteria related to OpenAI's training data, though specific details about datasets and their exact curation methods aren't fully disclosed. Read more here: [https://cdn.openai.com/papers/gpt-4.pdf](https://cdn.openai.com/papers/gpt-4.pdf) ## Process Used to Ensure Fairness in Development of the Intervention 15. **Description of the approach the intervention developer has taken to ensure that the intervention’s output is fair**: - Ozwell utilizes models created by third-party providers, such as OpenAI. OpenAI provides some publicly available documentation related to OpenAI's training data, though specific details about datasets and their exact curation methods aren't fully disclosed. Read more here: [https://cdn.openai.com/papers/gpt-4.pdf](https://cdn.openai.com/papers/gpt-4.pdf) 16. **Description of approaches to manage, reduce, or eliminate bias**: - In addition to internal testing, external validation involved collaboration with healthcare professionals and domain experts who provided real-world scenarios and feedback to assess the intervention’s performance. This includes pragmatic trials in simulated healthcare workflows and evaluation by clinical end users in real clinical settings. ## External Validation Process 17. **Description of the data source, clinical setting, or environment where an intervention’s validity and fairness has been assessed, other than the source of training and testing data**: - **Pragmatic Trials:** Ozwell has been evaluated in simulated healthcare workflows to mimic routine clinical practice. These trials provided insights into real-world implementation challenges, user experiences, and the intervention’s ability to integrate seamlessly into existing workflows. - **Clinical Setting:** The external data and feedback used for validation were derived from general healthcare environments, including outpatient clinics, hospitals, and administrative offices. These settings were chosen to reflect the diverse use cases for which Ozwell is intended. - **Purpose of External Validation:** The external validation process was designed to ensure that Ozwell’s outputs are accurate, fair, and generalizable when applied to new populations or clinical scenarios. - By incorporating clinician feedback, post-market surveillance, and pragmatic trials, Ozwell’s development team ensures that the intervention remains relevant, unbiased, and effective in real-world settings. 18. **Party that conducted the external testing**: - **Entity Responsible for External Testing:** The external testing of Ozwell was conducted by BlueHive Health, LLC, the developer of the intervention. - In addition to internal testing, external validation involved collaboration with healthcare professionals and domain experts who provided real-world scenarios and feedback to assess the intervention’s performance. - **Independent Third-Party Involvement:** - While no independent third-party organization was formally engaged for external testing, feedback from stakeholders, including clinicians and healthcare administrators, served as an additional layer of validation. - These stakeholders provided insights into the intervention’s fairness, accuracy, and usability in diverse clinical settings. - **Purpose of External Testing:** The external testing process was designed to evaluate Ozwell’s outputs in real-world scenarios, ensuring that the intervention is generalizable, fair, and effective across various healthcare environments. 19. **Description of demographic representativeness of external data according to variables (Race, Ethnicity, Language, Sexual Orientation, Gender Identity, Sex, Date of Birth, Social determinants of health data, Health status assessment data) including, at a minimum, those used as input features in the intervention**: - **N/A** 20. **Description of external validation process**: - **N/A** ## Quantitative Measures of Performance 21. **Validity of intervention in test data derived from the same source as the initial training data**: - **Overview of Validity and Performance Measures:** The validity of Ozwell was assessed using performance measures appropriate for its task as a recommendation and guidance system. Since Ozwell generates text-based outputs rather than numerical predictions, traditional metrics like mean-squared error are not directly applicable. Instead, qualitative and task-specific measures were used to evaluate its performance. - **Hold-Out Set:** During initial development, the training data was split into training and hold-out sets. The model was trained on the training data and evaluated on the unseen hold-out set to provide a preliminary assessment of generalizability. - **Performance Measures Used:** **Relevance and Accuracy:** Outputs were evaluated for their relevance to user-provided prompts and alignment with standard clinical guidelines. - Accuracy was assessed by comparing Ozwell’s responses to known correct answers or established medical knowledge. - **Consistency:** The intervention’s ability to provide consistent outputs across similar inputs was tested to ensure reliability. - **Precision and Recall:** For scenarios where Ozwell provided multiple recommendations or options, precision (correctness of recommendations) and recall (completeness of recommendations) were evaluated. - **User Feedback:** Feedback from healthcare professionals was used to assess the perceived validity and usefulness of Ozwell’s outputs in real-world scenarios. - **Results of Validity Testing:** Testing on data derived from the same source as the initial training data demonstrated high relevance and accuracy of Ozwell’s outputs. - The intervention consistently aligned with standard clinical guidelines and provided contextually appropriate recommendations. - **Limitations:** While the intervention performed well on test data from the same source as the training data, this does not fully account for its performance in novel or highly specialized scenarios. - As a text-based recommendation system, Ozwell does not rely on clinical guidelines to support decision-making but instead generates outputs based on patterns in its training data. Users are advised to verify outputs against current clinical guidelines and patient-specific information. 22. **Fairness of intervention in test data derived from the same source as the initial training data**: - **Overview of Fairness Evaluation:** The fairness of Ozwell’s outputs was evaluated to ensure that the intervention does not produce biased recommendations or disproportionately impact specific groups. - Given that Ozwell is a text-based recommendation system, fairness measures were selected based on the relevance of the intervention’s task and its potential impact on users. - **Fairness Measures Used:** **Statistical Parity:** Outputs were reviewed to ensure that recommendations were equally distributed across hypothetical subgroups, such as race, ethnicity, sex, gender identity, and age, even though these variables were not explicitly used as input features. - **False Positive and False Negative Error Rate Balance:** Scenarios were tested to measure the difference in false positive and false negative rates across subgroups. For example, the intervention’s ability to provide accurate recommendations was evaluated to ensure no subgroup experienced disproportionately higher error rates. - **Positive Predictive Parity:** The accuracy of recommendations was assessed across subgroups to ensure that the likelihood of a correct recommendation was consistent regardless of subgroup characteristics. - **Equivalent Calibration Within Groups:** Outputs were evaluated to ensure that the intervention’s recommendations were equally reliable across different subgroups. - **Relevant Groups and Factors:** While Ozwell does not explicitly use demographic variables (e.g., race, ethnicity, gender identity) as input features, fairness was evaluated across these factors to ensure that outputs were not inadvertently biased. - Additional factors considered included age, language, and social determinants of health, as these can influence healthcare outcomes and access. - **Results of Fairness Testing:** Testing on data derived from the same source as the training data demonstrated that Ozwell’s outputs were consistent and unbiased across hypothetical subgroups. - No significant disparities were identified in the distribution or accuracy of recommendations across subgroups. - **Limitations:** Since Ozwell does not process real-world demographic data, fairness testing relied on simulated scenarios and hypothetical subgroups. - The intervention’s fairness in highly specialized or stigmatized areas of care (e.g., reproductive or behavioral health) may require further evaluation in real-world settings. - **Ongoing Monitoring:** Fairness is continuously monitored through user feedback and periodic testing to identify and address any emerging biases. - Updates to the intervention incorporate new data and fairness measures to ensure alignment with ethical standards and user expectations. 23. **Validity of intervention in data external to or from a different source than the initial training data**: - **Overview of External Validity Testing:** The validity of Ozwell was assessed using data and scenarios external to the initial training and test data. This evaluation aimed to determine how well the intervention generalizes to new environments and data sources. - While Ozwell does not process real-time or proprietary patient data, external validation was conducted using simulated real-world scenarios and publicly available healthcare resources. - **Approaches Used for External Validation:** **Cross-Validation:** Cross-validation techniques were employed to divide the data into multiple folds. The model was trained on a combination of folds and evaluated on the remaining fold, repeating the process across all folds. This provided a robust estimate of the model’s ability to generalize. - **Simulated Real-World Scenarios:** External validation included testing Ozwell’s outputs against new, simulated clinical scenarios provided by healthcare professionals. These scenarios were designed to reflect diverse clinical workflows and patient cases not represented in the training data. - **Transfer Learning:** While transfer learning techniques were not explicitly applied, the intervention’s ability to adapt to new data sources was evaluated by comparing its outputs to benchmarks derived from external healthcare resources. - **Performance Metrics:** The validity of Ozwell’s outputs was measured using task-specific metrics, such as relevance, accuracy, and consistency. - Outputs were compared to established clinical guidelines and expert feedback to ensure alignment with real-world expectations. - **Results of External Validation:** Testing on external data demonstrated that Ozwell’s outputs were accurate, relevant, and generalizable across diverse clinical scenarios. - The intervention performed consistently when applied to new environments, providing confidence in its ability to support healthcare professionals in different settings. - **Limitations:** External validation relied on simulated scenarios and publicly available data rather than real-world patient data. - The intervention’s performance in highly specialized or rare clinical scenarios may require further evaluation in real-world settings. - **Transparency for Users:** Users are informed that Ozwell’s external validation was conducted using simulated scenarios and publicly available data. While the results indicate strong generalizability, users are encouraged to verify outputs against current clinical guidelines and patient-specific information. 24. **Fairness of intervention in data external to or from a different source than the initial training data**: - **Overview of Fairness Testing in External Data:** The fairness of Ozwell’s outputs was evaluated using data external to the initial training and test data to assess its ability to provide unbiased and equitable recommendations in diverse environments and for varied populations. - While Ozwell does not process real-world demographic data, fairness testing relied on simulated scenarios and publicly available data to evaluate its performance across hypothetical subgroups. - **Approaches Used for Fairness Evaluation:** **Simulated Real-World Scenarios:** External fairness testing included scenarios designed to represent diverse clinical workflows and patient populations. These scenarios were created to evaluate whether Ozwell’s outputs were consistent and unbiased across different subgroups. - **Hypothetical Subgroup Analysis:** Fairness was assessed across hypothetical subgroups based on factors such as race, ethnicity, gender identity, age, and social determinants of health. - Statistical measures, such as false positive and false negative error rate balance, were used to identify potential disparities in outputs across these subgroups. - **Independent Feedback:** Feedback from healthcare professionals and domain experts was used to evaluate the perceived fairness of Ozwell’s outputs in external scenarios. - **Results of Fairness Testing in External Data:** Testing on external data demonstrated that Ozwell’s outputs were consistent and unbiased across simulated subgroups. - No significant disparities were identified in the distribution or accuracy of recommendations across hypothetical subgroups. - **Limitations:** External fairness testing relied on simulated scenarios and publicly available data rather than real-world patient data. - The intervention’s fairness in highly specialized or stigmatized areas of care (e.g., reproductive or behavioral health) may require further evaluation in real-world settings. - **Transparency for Users:** Users are informed that Ozwell’s fairness testing in external data was conducted using simulated scenarios and publicly available data. While the results indicate strong fairness and generalizability, users are encouraged to verify outputs against current clinical guidelines and patient-specific information. - **Ongoing Monitoring:** Fairness is continuously monitored through user feedback and periodic testing to identify and address any emerging biases. - Updates to the intervention incorporate new data and fairness measures to ensure alignment with ethical standards and user expectations. 25. **References to evaluation of use of the intervention on outcomes, including, bibliographic citations or hyperlinks to evaluations of how well the intervention reduced morbidity, mortality, length of stay, or other outcomes**: - **Availability of Outcome Evaluations:** Currently, there are no formal bibliographic citations or independent evaluations available that assess how Ozwell has directly impacted specific clinical outcomes, such as reduced morbidity, mortality, length of stay, or other important healthcare metrics. - **Reason for Lack of Outcome Data:** Ozwell is designed as a general healthcare assistant to support healthcare professionals in documentation, workflows, and decision-making. It does not directly interact with patients or provide clinical interventions, which limits its ability to be directly evaluated for clinical outcomes. - The intervention’s outputs are intended to complement clinical expertise rather than replace it, making it challenging to isolate its impact on specific healthcare outcomes. - **Transparency for Users:** Users are informed that while Ozwell has been validated for accuracy, fairness, and generalizability in simulated and external scenarios, no formal studies have been conducted to evaluate its direct impact on clinical outcomes. - Users are encouraged to use Ozwell as a supportive tool and verify its outputs against current clinical guidelines and patient-specific information. - **Future Considerations:** BlueHive Health, LLC, remains committed to ongoing evaluation and improvement of Ozwell. Future studies may explore the intervention’s indirect impact on healthcare outcomes, such as improved workflow efficiency or reduced documentation burden for healthcare professionals. ## Ongoing Maintenance of Intervention Implementation and Use 26. **Description of process and frequency by which the intervention’s validity is monitored over time**: - **Process for Monitoring Validity and Fairness:** **Define Success Metrics:** Metrics used to assess validity include: **Relevance:** The degree to which Ozwell’s outputs align with user-provided prompts and clinical guidelines. - **Accuracy:** The correctness of recommendations or guidance provided by the intervention. - **Consistency:** The ability of the intervention to provide reliable outputs across similar inputs. - Metrics used to assess fairness include: **Statistical Parity:** Ensuring outputs are equally distributed across hypothetical subgroups (e.g., race, ethnicity, gender identity, age). - **Error Rate Balance:** Monitoring false positive and false negative rates across subgroups to identify potential disparities. - **Positive Predictive Parity:** Evaluating the likelihood of correct recommendations across subgroups. - **Data Collection Plan:** Data on these metrics is collected through: User feedback from healthcare professionals interacting with Ozwell. - Simulated real-world scenarios designed to test the intervention’s performance in diverse clinical settings. - Periodic internal testing using updated data sets to assess the intervention’s outputs. - **Monitoring Schedule:** **Frequency of Monitoring:** Ozwell’s performance is evaluated quarterly to ensure that its outputs remain valid, accurate, and fair. - Additional assessments are conducted when significant updates are made to the intervention or when new risks are identified. - **Factors Influencing Frequency:** The complexity of Ozwell’s task as a general healthcare assistant requires regular monitoring to address evolving clinical guidelines and user needs. - The broad applicability of the intervention across diverse healthcare settings necessitates periodic reassessment to ensure generalizability. - **Analysis and Reporting:** Collected data is analyzed to identify trends, potential risks, or areas for improvement. - Reports summarizing findings are generated quarterly and reviewed by the development team at BlueHive Health, LLC. - **Decision-Making and Risk Mitigation:** If poor performance or low fairness is identified, corrective actions are taken, including: Refining the intervention’s logic or decision-making processes. - Updating the training data to address identified gaps or biases. - Modifying the intervention’s scope or target use cases to better align with its capabilities. - **Frequency of Updates:** Ozwell is updated at least twice-yearly to incorporate new data, address identified risks, and improve performance. - Updates are informed by user feedback, internal testing, and external validation results. - **Transparency for Users:** Users are informed of the monitoring and update schedule to provide insight into the likelihood that the intervention’s performance may have degraded since its last update. - Regular communication ensures that users are aware of any changes or improvements made to the intervention. - **Ongoing Commitment to Validity and Fairness:** BlueHive Health, LLC, remains committed to continuous monitoring and improvement of Ozwell to ensure that it provides valid, accurate, and fair outputs over time. 27. **Validity of intervention in local data**: - **N/A** 28. **Description of the process and frequency by which the intervention’s fairness is monitored over time**: - **Process for Updating the Intervention:** Updates to Ozwell are designed to ensure that the intervention remains accurate, relevant, and aligned with evolving clinical guidelines and user needs. - The update process includes: **Data Review:** Periodic review of training data to incorporate new medical knowledge, guidelines, and best practices. - **User Feedback Integration:** Feedback from healthcare professionals is analyzed to identify areas for improvement and inform updates. - **Performance Monitoring:** Results from validity and fairness assessments are used to refine the intervention’s logic and outputs. - **Frequency of Updates:** **Lower-Risk Intervention:** As a general healthcare assistant, Ozwell is considered a lower-risk intervention. Updates are conducted at least twice-yearly to ensure that the intervention remains effective and relevant. - **Additional Updates:** Updates may occur more frequently if significant risks, gaps, or changes in clinical guidelines are identified. - For example, if user feedback highlights a recurring issue or if new medical standards are released, an interim update may be implemented. - **Factors Influencing Update Frequency:** **Intervention Complexity:** While Ozwell is not a high-risk or highly complex intervention, its broad applicability across diverse healthcare settings necessitates regular updates to maintain generalizability. - **Rate of Change in Target Population:** Updates are informed by changes in healthcare practices, user needs, and emerging trends in patient care. - **Resource Availability:** Updates are balanced with available resources to ensure that they are thorough and effective without compromising quality. - **Transparency for Users:** Users are informed of the update schedule and any significant changes made to the intervention. - Regular communication ensures that users are aware of improvements and can adjust their use of the intervention accordingly. - **Ongoing Commitment to Improvement:** BlueHive Health, LLC, remains committed to continuously updating Ozwell to ensure that it provides accurate, fair, and effective support to healthcare professionals. 29.**Fairness of intervention in local data**: - **Overview of Local Fairness Monitoring:** Fairness in local data is evaluated to ensure that Ozwell provides unbiased and equitable outputs within specific environments and for diverse subgroups. - OpenAI maintains fairness principles to fine-tune models for both first-person fairness: ensuring results are unbiased and respectful toward the user, and third-person fairness: ensuring results are unbiased and respectful toward the subject or patient being discussed. - **Results of Local Fairness Testing:** Testing in local contexts has demonstrated that the OpenAI models used for Ozwell maintain consistent unbiased quality across all genders and races. - Around 0.1% of responses contained subtle wording or content that reflected gender or cultural stereotypes; however, these were equally distributed across subgroups. - No significant disparities have been identified in the distribution or accuracy of recommendations across subgroups in local environments. ## Update and Continued Validation or Fairness Assessment Schedule 30. **Description of process and frequency by which the intervention is updated**: - **Measures Used to Assess Validity:** **Relevance:** The degree to which Ozwell’s outputs align with user-provided prompts and clinical guidelines. - **Accuracy:** The correctness of recommendations or guidance provided by the intervention. - **Consistency:** The reliability of outputs across similar inputs. - **Trend Analysis:** Tracking changes in performance metrics over time to identify potential degradation in validity. - **Groups Across Which Fairness is Evaluated:** Fairness is evaluated across hypothetical subgroups, including: **Demographic Factors:** Race, ethnicity, gender identity, age, and language. - **Social Determinants of Health:** Factors such as socioeconomic status and access to care. - **Clinical Contexts:** Different healthcare settings (e.g., outpatient clinics, hospitals) and patient populations. - **Criteria for Identifying Poor Performance or Low Fairness:** **Validity Risks:** Significant deviations from established benchmarks for relevance, accuracy, or consistency. - Trends indicating a decline in performance over time or in specific contexts. - **Fairness Risks:** Disparities in error rates (e.g., false positives, false negatives) across subgroups. - Unequal distribution of outputs or recommendations across subgroups. - Feedback from users indicating perceived bias or inequity in outputs. - **Process for Correcting Risks:** **Risk Identification:** Risks related to validity and fairness are identified through regular monitoring, user feedback, and periodic assessments. - **Corrective Actions:** **Refining the Intervention:** Adjusting the logic or decision-making processes to address identified gaps or limitations. - **Updating Training Data:** Incorporating new data to improve the intervention’s performance and address biases. - **Reassessing Metrics:** Re-evaluating performance and fairness metrics to ensure alignment with user needs and ethical standards. - **Frequency of Corrections:** Corrections are implemented as needed, with regular updates conducted at least twice-yearly to address identified risks and improve performance. - **Transparency for Users:** Users are informed of the criteria used to assess validity and fairness, as well as the process for addressing identified risks. - Regular communication ensures that users are aware of any updates or improvements made to the intervention. - **Ongoing Commitment to Improvement:** BlueHive Health, LLC, remains committed to continuously monitoring and improving Ozwell’s performance to ensure that it provides valid, accurate, and fair outputs over time. 31. **Description of frequency by which the intervention’s performance is corrected when risks related to validity and fairness are identified**: - **Frequency of Performance Evaluation:** Ozwell’s performance is evaluated quarterly to ensure that its outputs remain valid, accurate, and fair. - Additional evaluations are conducted when significant updates are made to the intervention, new risks are identified, or user feedback highlights potential issues. - **Frequency of Updates:** Ozwell is updated at least twice-yearly to incorporate new data, address identified risks, and improve performance. - Interim updates may occur if critical issues related to validity or fairness are identified during monitoring or through user feedback. - **Process for Monitoring and Updates:** **Regular Monitoring:** Performance metrics, including relevance, accuracy, and fairness, are tracked over time to identify trends or potential degradation. - Fairness is evaluated across hypothetical subgroups (e.g., race, ethnicity, gender identity, age) to ensure equitable outputs. - **Risk Identification:** Poor performance or low fairness is identified through user feedback, periodic assessments, and statistical analysis of performance metrics. - **Corrective Actions:** Identified risks are addressed through updates to the intervention’s logic, training data, or scope of use. - Updates are designed to improve the intervention’s outputs while maintaining alignment with user needs and ethical standards. - **Transparency for Users:** Users are informed of the evaluation and update schedule to provide insight into the likelihood that the intervention’s performance may have degraded since its last update. - Regular communication ensures that users are aware of any changes or improvements made to the intervention. - **Ongoing Commitment to Improvement:** BlueHive Health, LLC, remains committed to continuously monitoring and updating Ozwell to ensure that it provides valid, accurate, and fair outputs over time. --- ## The Healthcare Documentation Crisis: Why AI Isn’t a Luxury- It’s a Necessity URL: https://ozwell.ai/blog/the-healthcare-documentation-crisis-why-ai-isnt-a-luxury-its-a-necessity/ Published: February 11, 2025 Author: Evelyna Bellamy Tags: ai for doctors, ai in healthcare, ai powered medical scribe, electronic health records ehr, healthcare automation, healthcare documentation, healthcare technology, medical documentation ai, physician burnout ## Medicine Is Losing Its Soul to Documentation. Can We Get It Back? Midway through a busy clinic day, Dr. Jeff Margolis, a practicing medical oncologist in Royal Oak, Michigan, and president of Michigan Health Professionals, the largest private practice in the state with nearly 500 physicians, shares a candid reflection on modern medicine. In a recent testimonial for an AI-powered clinical documentation solution, Dr. Jeff Margolis is asked, 'How do you keep your head on straight?' He responds candidly: > *“Sometimes I don’t know. But the difference between me and a lot of administrators is I’m actually seeing patients every day.”* This highlights a core challenge in today’s healthcare: while many administrators are mired in paperwork, dedicated clinicians like Dr. Margolis continue to focus on patient care. Yet even the most committed physicians find that the shift from paper charts to electronic health records (EHRs) has not been entirely beneficial. With endless tick boxes, template fields, and mouse clicks, the very soul of medicine risks being lost in a labyrinth of administrative tasks ([BlueHive, 2024](https://www.youtube.com/watch?v=dtKOnvus41k&list=PLkzpXV2D-y4TK80mB6J0nn08ZfqSt-EUO)). Unfortunately, Dr. Margolis isn’t alone. The modern healthcare system forces countless providers to spend more time staring at electronic charts than engaging directly with patients. Recent studies by the American Medical Association ([Sinsky et al., 2016](https://doi.org/10.7326/M16-0961)), Mayo Clinic ([Shanafelt et al., 2022](https://www.mayoclinicproceedings.org/article/S0025-6196(22)00515-8/)), and others illustrate the scope of the problem: - For every hour spent with a patient, physicians dedicate nearly two additional hours to documentation. In a detailed time-and-motion study led by Dr. Christine Sinsky, researchers found that EHR tasks and desk work frequently overshadow face-to-face interactions, underscoring the unsustainable nature of current documentation demands. - 63% of physicians report burnout, citing emotional exhaustion and detachment from their work; a figure that reflects a significant rise over the years and points to escalating psychological stress in healthcare. - Administrative burden is the second-leading cause of physician burnout, with bureaucratic tasks and documentation overload fueling chronic fatigue and disconnection from patient care. - With annual expenditures on administrative complexity estimated at $286 billion ([Shrank et al., 2019](https://jamanetwork.com/journals/jama/article-abstract/2752664)), this financial drain diverts vital resources away from patient-facing activities and exacerbates systemic inefficiencies. And while countless “*fixes*” have been proposed, many only add new layers of complexity. ## The “Fixes” That Are Making the Problem Worse ### EHRs: A Necessary Tool That Became a Burden When Electronic Health Records (EHRs) first arrived, they promised a new era of clarity and accuracy: *goodbye, illegible handwriting and missing charts.* Yet for Dr. Margolis, who remembers the transition from paper charts, it felt like a giant step backward: > *“On paper charts, I could look a patient in the eye, talk with them, and just jot down occasional notes. I was a doctor first, and the chart came second.With EMRs, it became clear that the EMR had to be taken care of first, and sometimes the patient felt secondary. ”* Statistics confirm his frustration: - Primary care physicians devote about half of their workday, 5.9 hours out of 11.4, to EHR-related tasks, leaving less time for face-to-face patient interactions ([Arndt et al., 2017](https://www.annfammed.org/content/15/5/419.short)). - Emergency physicians in a community hospital logged roughly 4,000 mouse clicks per shift just to complete EHR documentation tasks, illustrating the time-intensive nature of current systems ([Hill et al., 2013](https://doi.org/10.1016/j.ajem.2013.06.028)). ### Cultural Reflections on the Documentation Crisis Recall a time when a doctor's note was a testament to empathy and human connection? Now it often resembles a "bloated ransom note" engineered to meet bureaucratic demands ([ZDoggMD, 2015](https://www.youtube.com/watch?v=xB_tSFJsjsw)). Influential voice and veteran clinician, ZDoggMD – *whose commentary on the EHR crisis has resonated widely*– reminds us that technology should unite us, not shackle us with endless checkboxes. The stark reality is that modern documentation systems have stripped physicians of their role as caregivers, exacting a heavy toll on patient outcomes, financial stability, and the professional spirit of the field. Burnout is often cited as a symptom, yet beneath that label lies a profound moral injury that erodes the very ethics that compelled physicians to dedicate their lives to healing ([ZDoggMD, 2019](https://www.youtube.com/watch?v=L_1PNZdHq6Q)). ### Scribes and Dictation: A Band-Aid, Not a Cure To offset the burden, many providers turn to medical scribes or voice dictation software. While these can temporarily ease some burdens, they bring their own headaches. Scribes must be hired and trained, dictation often requires heavy edits, and neither addresses the root cause of documentation overload. ## The Real Cost: Patient Satisfaction, Revenue Loss, and Burnout As documentation demands pile up, the consequences can be severe. Wrestling with EHRs undermines the core mission of healthcare: to heal. The ripple effects are far-reaching: - **Medical errors are recognized as the third leading cause of death in the United States,** surpassed only by heart disease and cancer ([Makary & Daniel, 2016](https://doi.org/10.1136/bmj.i2139)). In a system flooded with overlapping tabs, dropdowns, and multiple logins, critical lab results or medication changes can be overlooked. This fragmented documentation environment can delay diagnoses, complicate care coordination, and in the worst cases, contribute to adverse patient events. - **Complex billing and coding errors can lead to major financial losses,** as small mistakes like missing codes or incomplete entries can ripple into denied claims and reduced reimbursements. According to a recent scoping review, AI has the potential to streamline health financing and minimize administrative pitfalls by better handling massive data sets ([Ramezani et al., 2023](https://pmc.ncbi.nlm.nih.gov/articles/PMC10626800/)), ultimately boosting financial stability for hospitals and private practices alike. - **Face-to-face interaction diminishes when physicians focus heavily on screen-based tasks,** relegating patient engagement to a secondary role ([Honavar, 2020](https://pmc.ncbi.nlm.nih.gov/articles/PMC7043175/)). Studies show that when patients feel their doctor is distracted or rushed, they rate their care experience lower. Eye contact, personal conversation, and the overall “human touch” often wane when providers are tied to EHR documentation, eroding bedside rapport and potentially undermining trust, communication, and clinical outcomes. For Dr. Margolis, the real benefit of reducing documentation is clear: it allows him to reconnect with his patients. He shares that BlueHive AI [Ozwell] has enabled him to 'just look at the patient, talk, and be a doctor,' illustrating how even modest gains in efficiency can restore the essential human connection at the heart of healthcare. This shift is crucial for boosting patient satisfaction, as meaningful interaction remains a pillar in the foundation of quality care. ## From Burden to Breakthrough: AI’s Role in Healthcare For years, artificial intelligence in healthcare was considered a lofty, futuristic concept- promising, yet not ready for prime time. That conversation has changed. AI is already delivering real, measurable results: - In a large retrospective study of nearly 30,000 outpatient visits in ophthalmology, the use of scribes reduced physicians’ total documentation time from 7.6 minutes per note to 4.7 minutes- an overall decrease of nearly 38% ([Dusek et al., 2021](https://pmc.ncbi.nlm.nih.gov/articles/PMC8765735/)). - An AI-powered ICD-10 coding system was shown to raise coding accuracy from 83% to 92%. This boost in accuracy means that mistakes in billing are likely to drop and healthcare providers can more easily meet regulatory standards ([Chen et al., 2021](https://pmc.ncbi.nlm.nih.gov/articles/PMC8441604/)). - In an ambulatory urology practice, the introduction of medical scribes led to higher patient satisfaction scores; patients felt they received more focused and personalized care when physicians were less distracted by documentation tasks ([Koshy et al., 2010](https://pubmed.ncbi.nlm.nih.gov/20483153/)). **A “Game Changer” for Dr. Margolis** After just two weeks of using BlueHive AI [Ozwell], Dr. Margolis sums up the impact in one word: “**liberating**.” > *“It was the first time it felt like we got it right. I could stop staring at the monitor and just be a doctor. BlueHive did the documentation part for me.”* > *“Most of us who switched gained an hour or two hours back of our day. It has just been remarkable how much it's improved our patient care and allowed us to go back to being doctors.”* ## Built to Work With You, Not Against You Adopting new technology often comes with a major concern: workflow disruption. Healthcare organizations can’t afford to rip out their current systems or retrain entire teams overnight, which is why Ozwell is designed to enhance, not replace, existing workflows. Like an extra set of capable hands working in the background, Ozwell effortlessly manages documentation tasks, ensuring providers can focus on patients – *not paperwork*. Ozwell is seamless and adaptable: - Works with existing health systems including Enterprise Health, WebChart & BlueHive as part of a larger ecosystem. - Capability to expand to other systems with flexible interoperability. - Operable as a standalone AI-powered assistant for those without an EHR or EMR. Because the solution to documentation overload isn’t just to use another system, it’s a smarter way to use the ones we already have. ## Final Thoughts: AI Is the Way Forward In today’s healthcare landscape, where physician shortages and administrative burdens drive burnout, the answer isn’t to simply demand more effort, it’s to embrace smarter solutions. AI offers the means to reclaim the most valuable resource in medicine: time. Time that can be redirected from what feels like endless paperwork to meaningful patient care. Dr. Jeff Margolis’s testimonial underscores this shift, as he describes how AI has given him the ability to refocus on what truly matters. The bottom line: AI isn’t a replacement for physicians – it’s a restoration of their purpose. Let them practice medicine, not data entry. ## References Arndt, B. G., Beasley, J. W., Wattemaker, B. L., Temte, J. L., Tuan, W. J., Sinsky, C. A., & Gilchrist, V. J. (2017). *Tethered to the EHR: Primary care physician workload assessment using EHR event log data and time-motion observations*. Annals of Internal Medicine, 166(9), 488–494. [https://www.annfammed.org/content/15/5/419.short](https://www.annfammed.org/content/15/5/419.short) BlueHive. (2024, November 14). *BlueHive AI Testimonial – Jeffrey Margolis, M.D. [Video interview conducted by Ashley Horner]*. YouTube. [https://www.youtube.com/watch?v=dtKOnvus41k&list=PLkzpXV2D-y4TK80mB6J0nn08ZfqSt-EUO](https://www.youtube.com/watch?v=dtKOnvus41k&list=PLkzpXV2D-y4TK80mB6J0nn08ZfqSt-EUO) Chen, P.-F., Wang, S.-M., Liao, W.-C., Kuo, L.-C., Chen, K.-C., Lin, Y.-C., Yang, C.-Y., Chiu, C.-H., Chang, S.-C., & Lai, F. (2021, August 31). *Automatic ICD-10 coding and training system: Deep neural network based on supervised learning*. JMIR Medical Informatics, 9(8), e23230. [https://pmc.ncbi.nlm.nih.gov/articles/PMC8441604/](https://pmc.ncbi.nlm.nih.gov/articles/PMC8441604/) Dusek, H. L., Goldstein, I. H., Rule, A., Chiang, M. F., & Hribar, M. R. (2021). “Clinical Documentation During Scribed and Non-scribed Ophthalmology Office Visits.” Ophthalmology Science, 1(4), 100088. [https://pmc.ncbi.nlm.nih.gov/articles/PMC8765735/](https://pmc.ncbi.nlm.nih.gov/articles/PMC8765735/) Hill, R. G., Jr., Sears, L. M., & Melanson, S. W. (2013). *4000 clicks: A productivity analysis of electronic medical records in a community hospital ED*. The American Journal of Emergency Medicine, 31(11), 1591–1594. [https://doi.org/10.1016/j.ajem.2013.06.028](https://doi.org/10.1016/j.ajem.2013.06.028) Honavar, S. G. (2020). *Electronic medical records – The good, the bad and the ugly*. Indian Journal of Ophthalmology, 68(3), 417–419. [https://pmc.ncbi.nlm.nih.gov/articles/PMC7043175/](https://pmc.ncbi.nlm.nih.gov/articles/PMC7043175/) Kane, L. (2023, January 27). *“I cry but no one cares”: Physician burnout & depression report 2023*. Medscape. [https://www.medscape.com/slideshow/2023-lifestyle-burnout-6016058](https://www.medscape.com/slideshow/2023-lifestyle-burnout-6016058) Koshy, S., Feustel, P. J., Hong, M., & Kogan, B. A. (2010). *Scribes in an ambulatory urology practice: Patient and physician satisfaction*. Journal of Urology, 184(1), 258–262. [https://pubmed.ncbi.nlm.nih.gov/20483153/](https://pubmed.ncbi.nlm.nih.gov/20483153/) Makary, M. A., & Daniel, M. (2016). *Medical error—the third leading cause of death in the US*. BMJ, 353, i2139. [https://doi.org/10.1136/bmj.i2139](https://doi.org/10.1136/bmj.i2139) Ramezani, M., Takian, A., Bakhtiari, A., Rabiee, H. R., Fazaeli, A. A., & Sazgarnejad, S. (2023). *The application of artificial intelligence in health financing: A scoping review*. [https://pmc.ncbi.nlm.nih.gov/articles/PMC10626800/](https://pmc.ncbi.nlm.nih.gov/articles/PMC10626800/) Shanafelt, T. D., West, C. P., Dyrbye, L. N., Trockel, M., Tutty, M., & Sinsky, C. A. (2022). *Changes in burnout and satisfaction with work-life integration in physicians and the general US working population between 2011 and 2021*. Mayo Clinic Proceedings, 97(8), 1599–1614. [https://www.mayoclinicproceedings.org/article/S0025-6196(22)00515-8/](https://www.mayoclinicproceedings.org/article/S0025-6196(22)00515-8/) Shrank, W. H., Rogstad, T. L., & Parekh, N. (2019). *Waste in the US health care system: Estimated costs and potential for savings*. JAMA, 322(15), 1501–1509. [https://jamanetwork.com/journals/jama/article-abstract/2752664](https://jamanetwork.com/journals/jama/article-abstract/2752664) Sinsky, C., Colligan, L., Li, L., Ray, K., Sharp, L., & Privitera, M. R. (2016). *Allocation of physician time in ambulatory practice: A time and motion study in 4 specialties*. Annals of Internal Medicine, 165(11), 753–760. [https://doi.org/10.7326/M16-0961](https://doi.org/10.7326/M16-0961) ZDoggMD. [Damania, Z.]. (2015, October 19). *EHR State of Mind | An Electronic Medical Records Parody* [Video]. YouTube.[https://www.youtube.com/watch?v=xB_tSFJsjsw](https://www.youtube.com/watch?v=xB_tSFJsjsw) ZDoggMD. [Damania, Z.]. (2019, March 8). *It's Not Burnout, It's Moral Injury | Dr. Zubin Damania on physician "burnout"* [Video]. YouTube.[https://www.youtube.com/watch?v=L_1PNZdHq6Q](https://www.youtube.com/watch?v=L_1PNZdHq6Q) --- ## Release Notes: 2025.01-2025.05 URL: https://ozwell.ai/blog/release-notes-2025-01-2025-05/ Published: February 5, 2025 Author: Chris Davis BlueHive is pleased to announce that **BlueHive AI has been renamed to Ozwell!** You’ll likely notice a subtle shift in branding, but don’t be alarmed; Ozwell is still here to help you in the same way as BlueHive AI – with new and exciting features coming very soon! Throughout the month of January, our developers have been busy implementing the brand transition, as well as adding and upgrading features and the user experience and fixing bugs. You can watch our release notes video above for a brief overview or read about each feature in-depth below: ## Features: - BlueHive Labs Experimental Features Ozwell now has the ability to recognize and understand the following: Procedures - Conditions - Allergies - Medications - Observations - In addition to recognizing the above, Ozwell can also add these observations directly into a patient’s WebChart EHR. - Ozwell can now recommend patient charts when connected with an EMR. - If a patient is connected to an Ozwell session and they are removed from the session, any associated encounter is also removed. - Introduced the ability to search for a patient when starting a session, if integrated with an EMR. - Enabled changing and/or reconnecting EMR integrations. ## User Experience/User Interface: - When Ozwell is taking a little more time than normal to process your request, you’ll now receive a little feedback to let you know that he’s still working in the background. - As new and experimental features are being added, there will occasionally be mistakes – especially during the Beta phase. A notification has been added to remind you that Ozwell may mess up every once in a while. - When you’re discussing a topic with Ozwell, the chat window will now resize as you type. - Added a pencil icon next to session titles with a tooltip indicating that they can be edited. - Improved the loading screen with updated Ozwell branding. ## Bug Fixes: - Clicking on a document now allows the user to view it directly, instead of opening the edit mode. --- ## Introduction to BlueHive Health’s IRM Practices URL: https://ozwell.ai/blog/introduction-to-bluehive-healths-irm-practices/ Published: January 30, 2025 Author: William Reiske BlueHive Health is committed to the responsible development and deployment of artificial intelligence (AI) in healthcare. As part of this commitment, BlueHive Health has implemented robust Intervention Risk Management (IRM) practices for Predictive Decision Support Interventions (DSIs) supplied through its Ozwell workspace. Ozwell is an advanced AI model engine router designed to support multiple AI models across text, image, and voice modalities, making it a powerful tool for delivering safe, effective, and efficient clinical decision support. Instead of relying solely on an AI model’s training data, Ozwell employs Retrieval-Augmented Generation (RAG). RAG dynamically fetches the latest and most relevant information, ensuring responses stay accurate and aligned with current standards of care. In addition, clinicians can upload their own trusted guidelines from professional organizations (e.g., the American College of Cardiology (ACC), the National Comprehensive Cancer Network (NCCN), and the American College of Occupational and Environmental Medicine (ACOEM)). This capability ensures that AI-powered DSIs remain personalized, up-to-date, and reflective of best practices—fostering a collaborative environment where clinicians maintain control over the guidelines used. BlueHive Health recognizes the transformative potential of AI in healthcare but also acknowledges the importance of addressing potential risks to prioritize patient safety, data privacy, and fairness. The following sections outline BlueHive Health’s IRM framework, highlighting risk analysis, risk mitigation, governance, and continuous improvement. These practices guide the responsible deployment of AI-powered tools in the Ozwell workspace while advancing the overall quality and trustworthiness of care. ## Overview of IRM Practices Intervention Risk Management (IRM) is a critical process for developing and deploying Predictive DSIs responsibly. BlueHive Health leverages the NIST AI Risk Management Framework (AI RMF) as a guide to tailor its practices to organizational needs and resources. While not mandatory, this framework helps structure BlueHive Health’s proactive, transparent, and continuously improving approach to responsible AI. ### Key Principles of BlueHive Health’s IRM Framework - **Proactive Risk Identification**BlueHive Health anticipates and identifies potential risks associated with each Predictive DSI throughout its lifecycle. This includes considering key characteristics of trustworthy AI—validity, reliability, robustness, fairness, intelligibility, safety, security, and privacy. - **Tailored Risk Mitigation**Strategies to address identified risks are customized per DSI. Approaches may include data preprocessing, model monitoring, user training, or ongoing evaluations to ensure responsible usage and minimize unintended consequences. - **Robust Data Governance**BlueHive Health enforces policies and controls governing data acquisition, management, and usage for Predictive DSIs in the Ozwell workspace. Data security, privacy, and ethical considerations form the core of these governance policies. - **Ozwell as an IRM Facilitator**The Ozwell workspace itself is designed to mitigate AI-related risks and enable responsible deployment. Key capabilities include: Secure API connections to organizational datasets - Access controls for both users and APIs - Detailed audit trails recording all interactions and modifications - **Continuous Monitoring and Improvement**Processes exist for periodic review and updates to IRM procedures, documentation, and risk assessments. BlueHive Health actively incorporates stakeholder feedback, tracks AI-industry best practices, and adapts its framework as needed. By adhering to these principles, BlueHive Health maximizes the benefits of AI in healthcare while minimizing potential risks—promoting trust, safety, and ethical integrity in the Ozwell workspace. ## Risk Analysis – IRM Practices A cornerstone of BlueHive Health’s responsible AI approach is performing thorough risk analyses for each Predictive DSI. Guided by the NIST AI RMF’s focus on trustworthy AI characteristics, BlueHive Health identifies and evaluates potential risks that could affect patient safety, operational integrity, or equitable access to care. ### Characteristics of Trustworthy AI BlueHive Health’s risk analysis process concentrates on the eight key characteristics often cited in discussions of trustworthy AI: - **Validity**Verifying that DSIs produce accurate, reliable outputs aligned with intended use cases. - **Reliability**Ensuring consistency of DSI outputs across varied clinical settings and data inputs. - **Robustness**Assessing resilience against disruptions, unexpected inputs, or adversarial attacks. - **Fairness**Checking for biases or inequities within model outputs that could disproportionately affect certain populations. - **Intelligibility**Evaluating how understandable the DSI’s logic, algorithms, and outputs are to clinical users. - **Safety**Determining whether DSI outputs could cause harm under normal or stressed conditions. - **Security**Ensuring DSIs are protected against unauthorized access, manipulation, or data breaches. - **Privacy**Verifying adherence to privacy regulations and ethical considerations regarding data collection, storage, and sharing. ### Examples of Potential Risks and Adverse Impacts - **Bias in Training Data**DSIs may inadvertently learn biases from historical datasets, perpetuating health disparities among underserved groups. - **Varying Performance Across Clinical Settings**Models might perform differently across demographics or institutions with unique protocols and data quality. - **Security Vulnerabilities**Unauthorized access to systems or data could compromise patient information and disrupt care. - **Guidelines in RAG**Because clinicians can upload guidelines independently, there is a risk of outdated, conflicting, or poorly formatted guidelines that may reduce the DSI’s accuracy or reliability. By examining these and other potential risks through the lens of the eight trustworthy AI characteristics, BlueHive Health ensures thorough, proactive analyses that underpin safer AI deployments in the Ozwell workspace. ## Risk Mitigation for Predictive DSIs To address identified risks, BlueHive Health implements a range of targeted mitigation strategies. These strategies reflect best practices in user-centered design, systematic quality management, and alignment with recognized AI risk management principles (including insights from the NIST AI RMF). ### Addressing Validity, Reliability, Robustness, Fairness, and Bias - **Action**: Empower clinicians to report issues they observe regarding performance, fairness, or any unexpected behavior. - **Implementation**: In the Ozwell workspace, a “flagging” functionality allows clinicians to quickly mark questionable outputs or content. Flagged issues automatically alert BlueHive Health, prompting a root cause analysis and targeted remedies. ### Ensuring Intelligibility and Explainability - **Action**: Provide DSIs that offer clear, comprehensible insights into AI-driven recommendations. - **Implementation**: BlueHive Health collects real-world feedback from clinicians to refine the clarity of DSI outputs over time. Feedback is reviewed to improve interpretability and user understanding. ### Safety and Managing Outdated or Inaccurate Content - **Action**: Give clinicians full control over uploading current, validated guidelines into the Ozwell workspace. - **Implementation**: Clinicians can replace outdated or inaccurate guidelines at any time. Any flagged content triggers a review process, ensuring timely updates and accuracy. ### Security and Privacy - **Action**: Employ robust technical and administrative safeguards. - **Implementation**: Measures include encryption, access controls, secure data storage, and periodic security audits—all designed to protect confidential patient data from unauthorized access or breaches. ### Ongoing Monitoring and Improvement - **Continuous Monitoring**: BlueHive Health actively monitors flagged issues to detect performance or compliance concerns promptly. - **Flagging and Feedback**: Alerts generated by clinicians’ flags feed directly into BlueHive Health’s analysis pipeline, driving iterative fixes and enhancements. - **Review and Updates**: Risk mitigation measures are regularly re-evaluated and improved upon, incorporating user feedback and staying current with evolving industry guidelines. - **Transparency**: Users receive clear communication on risk mitigation actions and can easily access channels to report concerns. This clinician-centric model relies on real-world, expert feedback to adapt and refine DSIs continually—ensuring safe, effective AI-driven interventions in the Ozwell workspace. ## Governance BlueHive Health’s governance framework ensures that DSIs—along with Retrieval-Augmented Generation (RAG) and prompt engineering—are used responsibly. This framework also allows clients to integrate their own governance systems for guideline management within Ozwell. ### BlueHive Health’s Governance Framework - **Defined Procedures for DSI Development** Structured processes guide how RAG and prompt engineering are configured to keep outputs clinically relevant. - An internal DSI and Quality Committee reviews new DSIs, ensuring safety, efficacy, and usability standards are met before deployment. - **Public and Professional Guidelines** BlueHive Health integrates non-proprietary, widely recognized guidelines from sources like the Centers for Medicare & Medicaid Services (CMS). - Clinicians can add or remove these guidelines based on institutional needs. - **Client-Driven Governance** Each client retains autonomy over governance for the guidelines they incorporate. - Major decisions—such as adopting, modifying, or discarding guidelines—are typically made by senior leadership (e.g., a Chief Medical Officer). - **Customization and Oversight** Providers can upload proprietary guidelines relevant to their institution’s needs. - BlueHive Health offers support tools to simplify integration and track modifications to these guidelines. - **Transparency and Accountability** The Ozwell workspace maintains logs of guideline usage and changes, promoting accountability for both BlueHive Health and client organizations. - Clinicians can flag concerns related to DSIs or guidelines for immediate review and resolution. - **Collaborative Governance** BlueHive Health partners with clients to align governance structures with best practices in AI safety. - Ongoing enhancements incorporate end-user feedback, industry best practices, and evolving regulatory landscapes. Through this dual-level governance (at BlueHive Health and within client organizations), Predictive DSIs are deployed effectively while reflecting each healthcare setting’s unique requirements. ## Continuous Monitoring and Improvement of Predictive DSIs BlueHive Health upholds a robust approach to the ongoing refinement of its Predictive DSIs. This includes proactive monitoring, responsiveness to clinician feedback, and iterative updates to align with both clinical evidence and technological advancements. ### Leveraging Maintenance Principles and Continuous Updates Although not tied to formal EHR certifications, BlueHive Health follows regular update cycles and best practices to ensure the Ozwell workspace remains interoperable, safe, and reflective of new clinical and regulatory standards. ### Intervention Risk Management (IRM) in Action - **Source Attribute Transparency**: Users have access to up-to-date references describing the data sources and guidelines driving DSIs, helping clinicians gauge the outputs’ appropriateness. - **Performance and Bias Checks**: Ongoing monitoring helps identify errors, performance drift, or biases, triggering real-time adjustments as needed. ### User Feedback as a Driver of Improvement - **Flagging and Issue Review**: The Ozwell workspace empowers clinicians to flag any questionable content or system response. - **Root Cause Analysis**: When an issue is flagged, BlueHive Health investigates the underlying cause and deploys timely updates to resolve it. - **Open Communication**: BlueHive Health maintains transparency about changes made in response to clinician feedback. ### Proactive Monitoring and Reporting - **Regular Evaluations**: Predictive DSIs are regularly reviewed to ensure their recommendations remain clinically sound and align with emerging evidence-based guidelines. - **Data-Driven Insights**: Usage metrics, flagged issues, and feedback trends inform the prioritization and evolution of risk mitigation measures. ### Commitment to Long-Term Improvement - **Evolving Standards**: BlueHive Health keeps DSIs responsive to new clinical guidelines, interoperability protocols, and AI advancements. - **Living Framework**: Governance, IRM practices, and continuous improvement processes evolve in tandem with new technologies and real-world feedback—fostering a future-proof, trustworthy AI environment. ## Conclusion BlueHive Health’s Predictive Decision Support Interventions (DSIs), powered by the Ozwell workspace, demonstrate a steadfast commitment to developing and deploying AI responsibly in healthcare. Through RAG and clinician-driven guideline management, Ozwell enables providers to harness evidence-based, up-to-date insights while retaining autonomy over the guidelines and data that shape these interventions. By embedding robust governance, thorough risk analysis, proactive risk mitigation strategies, and a continuous feedback loop, BlueHive Health ensures that the Ozwell workspace remains adaptive, transparent, and aligned with both clinical best practices and ethical standards. This approach builds trust in AI tools, paving the way for their safe and innovative use in modern healthcare.