Robustness and generalizability of a speech‐based digital biomarker derived from recordings of the Clinical Dementia Rating (CDR) interview
Michael J Spilka, Mengdan Xu, Balazs Toth, Somaye Hashemifar, Rainier Amora, Jessica Robin, Edmond Teng, Cecilia Monteiro, William Simpson · 2025
Read Robustness and generalizability of a speech‐based digital biomarker derived from recordings of the Clinical Dementia Rating (CDR) interview by Michael J Spilka, Mengdan Xu, Balazs Toth, Somaye Hashemifar, Rainier Amora, Jessica Robin, Edmond Teng, Cecilia Monteiro, William Simpson (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-11712655.txt.
Description
How a person talks during a standard dementia interview can betray the disease, and a speech score built from nine voice and language features claims to track it. Michael Spilka and eight co-authors stress-test that score in this 2025 study. They apply it to recordings from an independent drug trial: eighty-one patients with mild-to-moderate Alzheimer's, in the placebo arm, recorded over a year.
The test is whether the score behaves the same outside its home data: rising or falling on schedule, matching clinical endpoints, and giving the same reading twice days apart. Recordings came from the part of the interview where patients recount a recent experience. Showing the marker travels well is the gate it must pass before trials can lean on it as an outcome. The work is part of a push toward objective, low-burden measures of decline.
Catalog record
| CREATOR | Michael J Spilka, Mengdan Xu, Balazs Toth, Somaye Hashemifar, Rainier Amora, Jessica Robin, Edmond Teng, Cecilia Monteiro, William Simpson |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |