Uncertainty-aware personalized estimation of Parkinson’s disease severity from longitudinal speech
Khondakar Ashik Shahriar · 2026
Read Uncertainty-aware personalized estimation of Parkinson’s disease severity from longitudinal speech by Khondakar Ashik Shahriar (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-0343191.txt.
Description
Khondakar Shahriar proposes in 2026 a personalised system for estimating Parkinson's severity from speech recordings taken over time. Rating severity normally needs an in person visit and expert judgement, which limits how often patients can be checked. Speech changes early in the disease, so voice offers a remote window. The system learns each patient's own pattern and states its uncertainty openly.
On a held back set of unseen patients, severity estimates landed very close to expert scores, and a three stage grouping was sorted with high accuracy. The method beat standard learning and global time based rivals. Frequent home monitoring could become practical if wider tests confirm the result.
Catalog record
| CREATOR | Khondakar Ashik Shahriar |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54051 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |