Comparing machine and deep learning models for pediatric anxiety classification using structured EHRs and area-based measures of health data
Eric W Lee, Sanghyun Choo, Dakotah Maguire, Abhishek Shivanna, Daniel Santel, Surbhi Bhatnagar, Ian Goethert, Kelly Patterson · 2026
Read Comparing machine and deep learning models for pediatric anxiety classification using structured EHRs and area-based measures of health data by Eric W Lee, Sanghyun Choo, Dakotah Maguire, Abhishek Shivanna, Daniel Santel, Surbhi Bhatnagar, Ian Goethert, Kelly Patterson (2026) 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/plos-pone-0324673.txt.
Description
Eric W. Lee and co-workers compare computer models that flag children at risk of anxiety disorders from their medical records. Early warning could help clinics step in before anxiety takes hold. Their 2026 study trains several standard learning models and several deep learning models on structured health records, with and without added neighborhood-level health measures for each child's area.
Models that read a child's record history over time performed best overall. A strong standard model using recent record snapshots also did well and was simpler to run. Adding neighborhood measures brought little gain in either case. The work shows routine records already carry useful warning signs, which could support earlier, kinder outreach to families.
Catalog record
| CREATOR | Eric W Lee, Sanghyun Choo, Dakotah Maguire, Abhishek Shivanna, Daniel Santel, Surbhi Bhatnagar, Ian Goethert, Kelly Patterson |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41115 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |