PlaySafe is a digital health wearable that predicts whether someone is about to have a sudden cardiac arrest.
PlaySafe is focused towards three target groups:
- Athletes (According to the NIH, sudden cardiac death is the most common cause of death in young athletes)
- The elderly (According to Nature Cardiology, sudden cardiac death is a major cause of mortality in the elderly)
- ICU patients (Critically ill hospital patients are constantly at risk of dying from sudden cardiac arrest)
Also, these are two “metrics” I’m using to evaluate the overall PlaySafe system:
- Raw accuracy (what is the false positive rate?, how accurately does it identify cardiac arrest, etc;)
- Time to event (How much prior warning can PlaySafe give while maintaining its accuracy?)
Week 2 Updates:
I accomplished three things this week.
1) Hardware Prototype
I used the CAD model I made last week to make a fully functioning hardware prototype this week:
Here are pictures of it:
2) Improving Software Prototype
I added an SVM to my initial LSTM model and improved my prediction accuracy on the Holter dataset from 73% to 79%. (More graphs coming in the next couple weeks).
3) Visual GUI + Integration
Also, I was able to integrate the software with the hardware prototype to get real-time predictions of cardiac arrest onset. I made a simple Processing and Serial monitor GUI to visualize this.
The picture below shows heart rate ECG data as a real-time signal.
The picture belows show the prediction software in real-time. Notice the section where it says “Consecutive 4 minute windows passed threshold”. This means a cardiac arrest is imminent in the next 5 minutes and a warning is provided.