Subject Harmonization of Multi‐Modal Digital Markers: Improved Detection of Mild Cognitive Impairment Using Language and Facial Expression
Bao Hoang, Yijiang Pang, Hiroko H Dodge, Jiayu Zhou · 2025
Read Subject Harmonization of Multi‐Modal Digital Markers: Improved Detection of Mild Cognitive Impairment Using Language and Facial Expression by Bao Hoang, Yijiang Pang, Hiroko H Dodge, Jiayu Zhou (2025) 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-11715931.txt.
Description
Bao Hoang and co-authors published this study in two thousand twenty-five on spotting mild cognitive impairment from talk and face cues. Mild impairment is an early stage on the way to dementia, and catching it early helps both care and trials.
The team used more than three thousand recorded chats with sixty-nine older adults from an online social trial. They pulled features from word choice, sentence build, and reply length. They also read seven basic emotions from face images. A key snag is that each person's style swamps the disease signal. Their fix, called subject harmonization, strips out person-specific patterns. With that fix on the language data, detection improved. Mixing the emotion data in needed more care. The authors say such low-cost digital signs could aid early screening.
Catalog record
| CREATOR | Bao Hoang, Yijiang Pang, Hiroko H Dodge, Jiayu Zhou |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |