Original title: Sit-to-stand-to-sit analysis as a digital biomarker for Parkinson’s disease
Researchers recorded people with Parkinson’s disease standing up and sitting down repeatedly with a smartphone. They used video to estimate how each person’s center of gravityThe point that represents how a person’s body weight is distributed. moved, then grouped similar movement paths. The groups differed in measures such as balance, independence, age, and motor severity. A small neural network learned to classify the movement patterns with 81.2% accuracy.
Imagine watching someone pack a bag and noticing how they reach, bend, and shift their weight. The challenge is that two people can do the same task with different movement patterns, and those patterns may carry clues that a simple checklist misses. In this paper, the movements while standing up and sitting down are the packing task, and the path of the person’s balance is the clue used to sort movement patterns linked to Parkinson’s disease severity.
People with Parkinson’s disease may have trouble reaching in-person care for ongoing motor assessments. Smartphone videos could help clinicians track movement remotely, though this study shows an approximate indication of severity, not a replacement for clinical assessment.
The abstract describes 32 patients with Parkinson’s disease and reports classification of movement patterns, not a validated diagnostic test. It does not establish performance in other groups, in everyday unsupervised use, or over long-term monitoring. The movement patterns indicate motor severity only approximately.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
Sit-to-stand-to-sit analysis as a digital biomarker for Parkinson’s disease — Daisuke Ichimura, Makoto Sawada, Ken’ichi Morooka et al. — Journal of NeuroEngineering and Rehabilitation — doi:10.1186/s12984-026-02166-5
Abstract licence: CC BY
Explanation generated by Synthesis from the abstract — it is not the original paper.