Monitoring Substance Use with Fitbit Biosignals: A Case Study on Training Deep Learning Models Using Ecological Momentary Assessments and Passive Sensing
Shizhe Li, Chunzhi Fan, Ali Kargarandehkordi, Yinan Sun, Christopher Slade, Aditi Jaiswal, Roberto M Benzo, Kristina T Phillips, Peter Washington · 2024
Read Monitoring Substance Use with Fitbit Biosignals: A Case Study on Training Deep Learning Models Using Ecological Momentary Assessments and Passive Sensing by Shizhe Li, Chunzhi Fan, Ali Kargarandehkordi, Yinan Sun, Christopher Slade, Aditi Jaiswal, Roberto M Benzo, Kristina T Phillips, Peter Washington (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12065672.txt.
Description
Shizhe Li, Chunzhi Fan, Ali Kargarandehkordi, and a team of co-authors test whether a wrist-worn Fitbit can help spot substance use as it happens. Disorders tied to drug use affect a large share of adults, and catching use in the moment could one day let support arrive right when it is needed.
Nine people wore Fitbit Charge 5 devices and answered quick phone check-ins that labeled when use occurred. The team trained a personal neural network for each person, and a version that first learns on its own from unlabeled data did a bit better than the plain supervised one. They are frank that nine people is a small group, so the results are a pilot that calls for larger studies.
Catalog record
| CREATOR | Shizhe Li, Chunzhi Fan, Ali Kargarandehkordi, Yinan Sun, Christopher Slade, Aditi Jaiswal, Roberto M Benzo, Kristina T Phillips, Peter Washington |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |