68. Predicting executive dysfunction in mood disorders using a multimodal machine learning approach
J-W Lai, Y-M Bai, Y-H Hu, R-Y Wu, C-C Shen · 2026
Read 68. Predicting executive dysfunction in mood disorders using a multimodal machine learning approach by J-W Lai, Y-M Bai, Y-H Hu, R-Y Wu, C-C Shen (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/pmc-13556404.txt.
Description
A five-author team from Taiwan tests whether the sound and words of a patient's speech can flag weak executive function in mood disorders. Thinking problems often linger in depression and bipolar disorder even when mood is stable. The team recorded 196 patients and healthy controls describing their recent feelings and lives, and tested their planning skills with a card sorting task.
Models using only basic facts about a person reached modest accuracy. Adding voice features, such as rhythm and tone, improved the guesses clearly, and word-use features helped as well. Combining voice, text, and personal facts worked best, with the impaired group made up mostly of mood disorder patients. The authors suggest that short speech samples could become a simple digital marker of thinking problems, helping clinics spot patients who need closer cognitive care.
Catalog record
| CREATOR | J-W Lai, Y-M Bai, Y-H Hu, R-Y Wu, C-C Shen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |