FINE TUNING OF A PRETRAINED GAIT MODEL FOR FRAILTY CLASSIFICATION PREDICTION
Laura McDaniel, Ime Essien, Yuxiang Guo, Ayush Gupta, Vineet Shenoy, Peter Abadir, Rama Chellappa · 2024
Read FINE TUNING OF A PRETRAINED GAIT MODEL FOR FRAILTY CLASSIFICATION PREDICTION by Laura McDaniel, Ime Essien, Yuxiang Guo, Ayush Gupta, Vineet Shenoy, Peter Abadir, Rama Chellappa (2024) 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-11693144.txt.
Description
Laura McDaniel and six co-authors present a 2024 study that adapts a walking-analysis model to detect frailty. Frailty is a state of greater weakness and risk that comes with aging, raising the chances of falls and hospital care. The team fine-tuned GaitBase, a model first built to recognize people by their walk, using medical data instead.
Their data came from motion-capture video of 64 people classed as non-frail, pre-frail, or frail. Image tools produced body silhouettes and boxes from each frame, and the model used both silhouette and color video. Small datasets are a known problem, so the team used data augmentation and cross-validation to strengthen the results. A fast video-based check could help clinicians spot frailty earlier.
Catalog record
| CREATOR | Laura McDaniel, Ime Essien, Yuxiang Guo, Ayush Gupta, Vineet Shenoy, Peter Abadir, Rama Chellappa |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |