Parkinson’s disease assessment with selfie video via feature engineering and explainable AI

Sitthatka Jaratsaeng, Anchalee Techasen, Narongrit Kasemsap, Thanapong Intharah · 2026

Read Parkinson’s disease assessment with selfie video via feature engineering and explainable AI by Sitthatka Jaratsaeng, Anchalee Techasen, Narongrit Kasemsap, Thanapong Intharah (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-0357902.txt.

Description

Sitthatka Jaratsaeng and three colleagues test whether a phone selfie video can help assess Parkinson's disease, in PLOS ONE in 2026. The illness stiffens facial expression as well as movement, and clinic visits capture only snapshots. The team recorded forty participants with a standard smartphone front camera across several facial movement tasks, engineered measurements from the footage, and trained models to flag the disease and estimate its severity.

Smiling videos carried the most signal. The best classifier sorted patients from controls with accuracy near seventy-seven percent, and a companion model estimated standard motor scores, though with wide error margins. An explainability analysis showed the system leaned most on movements of the lips and mouth corners, which matches what clinicians watch. The authors present phone video as a low cost screening aid for remote follow up, not a stand alone diagnosis.

Catalog record

CREATORSitthatka Jaratsaeng, Anchalee Techasen, Narongrit Kasemsap, Thanapong Intharah
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE82719
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0357902

Browse the full library · About the Tower of Babel