Evaluating the ability of a predictive vision-based machine learning model to measure changes in gait in response to medication and DBS within individuals with Parkinson’s disease

Andrea Sabo, Andrea Iaboni, Babak Taati, Alfonso Fasano, Carolina Gorodetsky · 2023

Read Evaluating the ability of a predictive vision-based machine learning model to measure changes in gait in response to medication and DBS within individuals with Parkinson’s disease by Andrea Sabo, Andrea Iaboni, Babak Taati, Alfonso Fasano, Carolina Gorodetsky (2023) 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-10714555.txt.

Description

Andrea Sabo and co-authors test whether a vision based AI model can track gait change in Parkinson's disease. Their 2023 pilot study deals with walking problems in the illness. Drugs and deep brain stimulation can help, but response varies by person. Past video tools scored severity of gait. None had been tested on change within a person after treatment.

A graph based model was trained on 362 videos of fourteen older adults with drug induced parkinsonism. It learned to predict a standard gait score. It was then applied to forty two paired videos of thirteen people with Parkinson's. Videos were recorded with treatment on and off, in the same visit. Predicted scores were lower, meaning better gait, in the on state. The size of change matched clinician scores.

Catalog record

CREATORAndrea Sabo, Andrea Iaboni, Babak Taati, Alfonso Fasano, Carolina Gorodetsky
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE42 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10714555

Browse the full library · About the Tower of Babel