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 3 Updates:
I accomplished three things this week.
1) Hardware v2.0 (Entirely Re-Designed, Bluetooth Low Energy support, cost reduced by 30%, size reduced by 5x)
Arduino Nano dimensions: 43.18 mm x 18.54 mm Arduino Uno dimensions: 68.6 mm x 53.3 mm
This week, I redesigned and rebuilt PlaySafe’s hardware. Here is a picture of the new hardware prototype:
I added Bluetooth Low Energy Support with the DMD Tech HC-08 Bluetooth 4.0 Slave:
I also replaced the Arduino Uno from v1.0 with a much smaller, ATmega328P Arduino Nano-based microcontroller board:
My 3D-printed design hasn’t arrived yet, so I improvised and used plastic casings from Neosporin tubes as the chassis:
Some Pioneers requested a cost analysis with a parts list in last week’s update, so here it is:
Hardware v1.0:
Part | Cost |
Arduino Uno Board | $18.36 |
PulseSensor | $23.99 |
Wires+ Plastic | $1.50 |
Breadboard | $6.99 |
Total Cost: | $50.84 |
Hardware v2.0:
Part | Cost |
ATmega328P Microcontroller Board | $3.99 |
HC-08 Bluetooth 4.0 Slave Module | $7.99 |
PulseSensor | $23.99 |
Wires+ Plastic | $1.50 |
Total Cost: | $37.47 |
Improvement in Total Cost from v1.0 to v2.0: ~30%
Some more pictures of the hardware prototype v2.0:
2) Improving Software Prototype
I improved the accuracy of the cardiac arrest prediction software from 79% to 87%, the highest one-week improvement I’ve achieved since the beginning. I’m planning on writing a white-paper with an overview of the algorithm and posting it soon.
3) Mobile Alerts Feature
To integrate PlaySafe with mobile devices and patient monitoring workflows, I made a mobile alerts feature that notifies coaches/family/doctors if a user’s cardiac arrest risk spikes. I used the Twilio API to create this with a Python integration. Here’s a sample message from the PlaySafe Mobile Alerts system: