Modernizing a Remote Patient Monitoring (RPM) App for an EKG Recording Smart Device
AliveCor, Inc. is a privately held healthcare company, headquartered in Mountain View, California. It is known for its range of IoT-enabled, smart devices that capture EKG (Electrocardiogram) recordings and transmit EKG rhythms to the smartphone or tablet. The devices aim to transform cardiac care with early detection of atrial fibrillation (AF), normal sinus rhythm, and 28 other abnormalities in EKG.
All smart devices by the company are FDA approved and are used by patients at home and providers at care organizations. AliveCor is recognized by FastCompany as 2018’s most innovative company in Artificial Intelligence.
- 80 M ECGs recorded to-date
- 98% accurate sensitivity detection for atrial fibrillation, bradycardia, and tachycardia
- 97% accurate specificity detection for atrial fibrillation, bradycardia, and tachycardia
AliveCor’s smart devices have electrodes to sense and transmit EKG rhythms to the smartphone. The client already had an app that integrates with the smart device to collect and view EKG recordings. However, their app needed modernization with respect to its features, technology, and user experience.
AliveCor reached out to Daffodil for revamping the existing app with a new set of features, to bring detail and accuracy in the EKG report, update the legacy code with the latest technology, improve the user experience of the app, etc. The existing apps were built on Java and Objective C while the requirement was to update it with Kotlin and Swift. The key requirements were:
- To implement major feature updates including enabling the app to detect approx 30 abnormalities in EKG (which were previously limited to 5).
- To improve visibility of 6-lead EKG reading on the app along with some other UX fixes.
- To comply with FDA and HIPAA standards for remote care monitoring. Due to team AliveCor’s stringent compliance requirements, team Daffodil had to pay attention to every minute detail of data interoperability and data privacy.
The inception stage of development had been challenging for team Daffodil as it required auditing and optimizing the existing codebase for modernizing the entire app. As a result, a number of UX updates and performance fixes were done in the existing version of the app. The team closed all technical debt tickets (additional rework by the technical team), upgraded the database from SQLite to Room, improved graph pixelation (EKG reading), etc.
In the newer version of the app, Kotlin (for Android) and Swift (for iOS) were used as the core languages for development. The team integrated Atrial Fibrillation (AF) logic (an algorithm created by the client which monitors irregular and often rapid heart rate that occurs when the two upper chambers of your heart experience chaotic electrical signals) into the app that enabled it to analyze and predict over 30 heart-related abnormalities from a 6-lead EKG reading. The app now predicts heart abnormalities such as normal sinus rhythm, atrial fibrillation, bradycardia, tachycardia, etc. on the basis of EKG rhythms received from smart devices.
Previously, the app allowed users to manually add their blood pressure details within the app and keep a track of it. In the newer version, users were allowed to maintain a health diary, add and track various health vitals which include blood pressure, blood sugar, cholesterol, medication, symptoms, weight, etc. These health vitals can either be added manually into the app or through Apple Smart Watch or Wear OS by Google.
In addition to this, the app now supports a medication adherence feature that sends a reminder to the patients to take their medicine on time. Users can also share their EKGs with family or caregivers in the form of a PDF file. This PDF file can be viewed, emailed, or downloaded to maintain a history of ECG recordings.
The client has been extremely satisfied by the way Daffodil has executed the entire project. The client was able to launch the solution in a timely and desired manner as Daffodil ensured that the deliverables were provided on time while maintaining the utmost quality. The devices use machine learning to detect the three most common arrhythmias—atrial fibrillation, bradycardia, and tachycardia—with 98% sensitivity and 97% specificity. This gives patients and physicians a fast and highly reliable insight into health.
Read Related Case Studies
Get in Touch
Sign up for a 30 min no-obligation strategic session with us
Let us understand your business objectives, set up initial milestones, and plan your software project.
At the end of this 30 min session, walk out with:
- Validation of your project idea/ scope of your project
- Actionable insights on which technology would suit your requirements
- Industry specific best practices that can be applied to your project
- Implementation and engagement plan of action
- Ballpark estimate and time-frame for development