AliveCor's users record an EKG at home, see if it shows any of over 30 heart abnormalities, and share it with family or a carer.
AliveCor wanted people to check their heart at home and catch problems such as atrial fibrillation early, with readings their doctors can trust.
What changed
What stood in the way.
- The app, built in Java and Objective C, needed new features, newer technology and a better user experience; it could detect only 5 abnormalities.
- It had to meet FDA and HIPAA rules for remote monitoring, down to every detail of data exchange and privacy.
- 80MECGs recorded to date (as reported)
- 98% / 97%sensitivity and specificity of the devices' machine learning for atrial fibrillation, bradycardia and tachycardia (as reported)
What we built.
- An audit of the codebase: technical debt closed, the database moved from SQLite to Room and EKG graph pixelation fixed.
- A new version in Kotlin for Android and Swift for iOS.
- The client's atrial fibrillation algorithm integrated, so the app reads over 30 heart abnormalities, such as bradycardia and tachycardia, from a 6-lead EKG.
- A health diary for blood pressure, sugar, cholesterol, medication, symptoms and weight, entered by hand or from Apple Watch and Wear OS.
- Medication reminders, and EKGs shared with family or carers as a PDF to view, email or download.
- Kotlin
- Swift
- Room
- Apple Watch
- Wear OS
What this work shows about us.
A reading taken at home, explained in the app and shared as a PDF, brings the doctor in without a clinic visit.
FDA and HIPAA requirements shaped every detail of how data moves and who can see it.
Want to build a similar app for a connected EKG device? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.
Start your plan ↗If we built it today, with AI.
What we would add now, moment by moment.
An agent would explain a reading in plain words and, when it flags atrial fibrillation, help the user send it to their doctor. The algorithm still reads the rhythm, and the doctor diagnoses.
An agent would follow up missed medication reminders and diary gaps, and tell the user's care team when readings change.
Where this work fits.
- Hospitals & clinicsYour hospital is meant to deliver care without making patients wait.
- Care coordination & remote monitoringThe right clinician knows in time, and families know what happens next.
- Elite CareElite Care's patients leaving hospital get their follow-up care on time, with every task tracked.
- A European healthcare companyUsers get a diet plan built around their health, their allergies and the food sold where they live.
Facts and figures from the project records; nothing added.
Want this for your business?
Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.
Send us a note instead
An AI agent. This prototype uses prepared answers and sends nothing.
We use essential cookies to run this site. With your consent we also use analytics cookies to see which pages help. Privacy policy