Voice Symptom Tracker

Some patients are too sick even to use a phone. This Symptom Tracker lets them log their feelings and symptoms over time, so their care team can monitor their progress remotely.

Comment

Inspiration

I have worked on multiple products which we are researching and designing for people with chronic conditions and cancer treatment. From our research, we know that sometimes people feel so sick they can't get out of bed or use a phone. However, getting a real-time record of how they are feeling and symptom severity would greatly improve their care team's ability to adapt to their needs.

What it does

This voice-enabled Symptom Tracker would allow the user to log their overall distress rating, based on the nationally recognized "NCCN Distress Thermometer". as well as log specific symptoms that have been bothering them and the severity of each. These ratings currently get saved to an Airtable, but imagine they are going to their patient records the care team can access, and that would notify them if any red flag conditions start to appear.

We included an LLM option where the user can get recommendations on how to alleviate symptoms with non-medical, easy-to-do-at-home treatments. This could bring them immediate comfort, whereas alternatively, they may not have wanted to reach out to the doctor to ask for help.

How we built it

One other colleague and I put this together using VoiceFlow and Airtable. The subject matter is drawn from experience and nationally recognized healthcare frameworks to track the progression of Distress and Symptom Severity. Nothing here is proprietary to any specific company.

Challenges we ran into

It took some time to figure out how to get things to post to Airtable. There were some missing pieces of data in the tutorials that were available. Still not sure how to pull the data back down from the spreadsheet to read back to the users. Also, getting the AI capture step to recognize numbers that the user was speaking was harder than we would have expected.

Accomplishments that we're proud of

The empathetic tone we were able to achieve in the copy and voice that the app uses. It feels like a friendly, empathetic and encouraging coach during a tough time in the user's life. We think it will help many millions of people be more mindful of their care and will produce better outcomes. Also the LLM addition where it can respond in real-time to the user's problem is amazing!

What we learned

We learned a lot about how to adapt to the tool to get it to do what we wanted. Posting to Airtable and offering users a defined list of items to choose from.

What's next for Voice Symptom Tracker

I am looking forward to testing it with more people to refine the way we phrase things and they way it can adapt to user input that wasn't what it expected.

Built With

Share this project:

Updates