Screening for Parkinson’s disease using “computer vision”

• Published in: PloS one Vol. 20; no. 8; p. e0330373
• Main Authors: Kasemsap, Narongrit, Tikkapanyo, Purinat, Wanjantuk, Panupong, Vorasoot, Nisa, Kongbunkiat, Kannikar, Panitchote, Anupol
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 12.08.2025; Public Library of Science (PLoS)
• Subjects: Accuracy; Aged; Algorithms; Amplitudes; Biology and Life Sciences; Case-Control Studies; Computer and Information Sciences; Computer vision; Computers; Diagnosis; Female; Finger; Fingers; Fingers & toes; Fingers - physiopathology; Hands; Health aspects; Humans; Hypokinesia - diagnosis; Hypokinesia - physiopathology; Keyboards; Learning algorithms; Machine Learning; Machine vision; Male; Medical screening; Medicine and Health Sciences; Methods; Middle Aged; Motor task performance; Movement disorders; Neurodegenerative diseases; Parkinson Disease - diagnosis; Parkinson Disease - physiopathology; Parkinson's disease; Physical Sciences; Python; Research and Analysis Methods; Signal processing; Smartphones; Subjective assessment; Support vector machines; Technology application; Time series; Thailand
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0330373

Identifying bradykinesia is crucial for diagnosing Parkinson's disease (PD). Traditionally, the finger-tapping test has been used, relying on subjective assessments by physicians. Computer vision offers a non-contact and cost-effective alternative for assessing Parkinson's disease. This study aimed to detect Parkinson's disease by identifying bradykinesia using computer vision in the finger-tapping test and applying machine learning techniques for both hands. We recruited 100 patients with PD and healthy controls. Four neurologists assessed bradykinesia, and 10-second smartphone-recorded finger-tapping movements were analyzed using Google MediaPipe Hands software. Six machine learning models were trained using a nested cross-validation framework. The differences in tapping scores between the left and right hands were significantly greater in the PD group (2.8 (5.0) vs 0.4 (0.7), p = 0.001) than in the healthy controls. Moreover, the tapping amplitude variation and all amplitude decremental parameters in the PD group differed significantly from those of the standard controls. The PD group had significantly lower tapping scores than the normal subjects (right: 17.9 (7.8)/ left: 17.9 (5.6) vs. right: 24.6 (7.3)/ left: 24.6 (7.2), p < 0.001). The support vector machine outperformed the other models. The most influential features were the tapping difference, followed by the tapping score (right hand) and tapping amplitude mean (right hand). A computer vision method can accurately detect bradykinesia using the tapping feature from the finger-tapping method, which involves the simultaneous tapping of both hands.