Alignment of natural language processing-derived RDoC scores with depression, anhedonia, and anxiety in psychiatric electronic health records
Manuel Kuhn, Seoin Ahn, Vincent Holstein, Annah Rossvall, Savannah Layfield, Lucie A. Duffy, Samantha Wong, Robyn Ellis, Eliot Gelwan, Fernando Rodriguez-Villa, Agustin Yip, Ipsit Vahia · 2026
Read Alignment of natural language processing-derived RDoC scores with depression, anhedonia, and anxiety in psychiatric electronic health records by Manuel Kuhn, Seoin Ahn, Vincent Holstein, Annah Rossvall, Savannah Layfield, Lucie A. Duffy, Samantha Wong, Robyn Ellis, Eliot Gelwan, Fernando Rodriguez-Villa, Agustin Yip, Ipsit Vahia (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/PMC13627714.txt.
Description
Manuel Kuhn leads a team checking whether a computer reading doctors' notes can recover the dimensions of mental illness. Diagnoses sort patients into boxes, while the Research Domain Criteria framework scores two brain systems instead: positive valence, tied to reward, and negative valence, tied to threat. The team extracted those scores with language software from the notes of 358 psychiatric patients at McLean Hospital and set them against standard mood questionnaires.
Deeper depression and stronger loss of pleasure each tracked with lower positive and higher negative scores, just as theory predicts. Anxiety tracked only the negative system, again matching the framework. The match between machine-read notes and trusted scales, the authors argue, validates note mining as a window on symptom dimensions that charts already contain but diagnoses hide.
Catalog record
| CREATOR | Manuel Kuhn, Seoin Ahn, Vincent Holstein, Annah Rossvall, Savannah Layfield, Lucie A. Duffy, Samantha Wong, Robyn Ellis, Eliot Gelwan, Fernando Rodriguez-Villa, Agustin Yip, Ipsit Vahia |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |