HealthyPi v4 - Unplugged

A wireless, wearable, open source vital signs monitor powered by ESP32

Oct 28, 2019

Project update 5 of 13

Extending HealthyPi v4 – Part 2

by Ashwin K Whitchurch

Thank you for a successful campaign!

First off, a big thank you to all of our backers. We are thrilled and humbled by your support. Though the campaign is not quite over yet, we are now moving full steam ahead with our manufacturing plans. As a reminder, you can still pre-order HealthyPi v4 from Crowd Supply, even after the campaign ends, but the price will increase by $50.

We have had a great time, throughout the HealthyPi v4 campaign period, and we’d also like to thank the Crowd Supply team for helping us complete our fourth successful campaign.

Keep making things with HealthyPi v4, and please keep sharing your experiences!

Extending HealthyPi v4 - Part 2

Following up on our previous post about Extending HealthyPi v4, below are a few additional ways in which you might want to integrate various QWIIC sensors currently available at SparkFun.

Scenario 1: Health vs. Environment

Want to track changes in vital signs with respect to changes taking place in the surrounding environment? We connected the SparkFun Environmental Combo Breakout - CCS811/BME280 (Qwiic) sensor to HealthyPi v4 in order to gather a variety of environmental data, including CO₂, barometric pressure, humidity, and temperature. Such data can be used, in combination with vital signs, to help give environmental context to our measurements. Check out the video below:

Scenario 2: Activity vs. Vital signs

As HealthyPi v4 is a wearable platform, it can be used in conjunction with any IMU based QWIIC sensor to recognize activity. In the video below, we connected the SparkFun Triple Axis Accelerometer Breakout - MMA8452Q (Qwiic) sensor to HealthyPi v4 and captured accurate activity data alongside the user’s vital signs.

More Possibilities

If you have not heard about the Physionet annual health challenges, they are a bunch of "challenges" that requires participants to design and implement a working, open-source algorithm that can detect conditions based only on the data provided. This year’s Physionet 2019 challenge asked participants to predict the chances of a patient developing Sepsis early.

Can you respond to this year’s PhysioNet challenge with your HealthyPi v4? One way might be to try Early Prediction of Sepsis using vital signs measured by the HealthyPi v4. What else can you observe from the data provided? We look forward to hearing more about your discoveries with HealthyPi v4!

Stay tuned for more updates once we start manufacturing and

Sign up to receive future updates for HealthyPi v4 - Unplugged.

Subscribe to the Crowd Supply newsletter, highlighting the latest creators and projects