{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/vision-based-assessment-of-parkinsonism-and","title":"Vision-Based Assessment of Parkinsonism and Levodopa-Induced Dyskinesia with Deep Learning Pose Estimation","arxiv_id":"1707.09416","date":"2017-07-25","proceeding":null,"authors":["Michael H. Li","Tiago A. Mestre","Susan H. Fox","Babak Taati"],"abstract":"Objective: To apply deep learning pose estimation algorithms for vision-based\nassessment of parkinsonism and levodopa-induced dyskinesia (LID). Methods: Nine\nparticipants with Parkinson's disease (PD) and LID completed a levodopa\ninfusion protocol, where symptoms were assessed at regular intervals using the\nUnified Dyskinesia Rating Scale (UDysRS) and Unified Parkinson's Disease Rating\nScale (UPDRS). A state-of-the-art deep learning pose estimation method was used\nto extract movement trajectories from videos of PD assessments. Features of the\nmovement trajectories were used to detect and estimate the severity of\nparkinsonism and LID using random forest. Communication and drinking tasks were\nused to assess LID, while leg agility and toe tapping tasks were used to assess\nparkinsonism. Feature sets from tasks were also combined to predict total\nUDysRS and UPDRS Part III scores. Results: For LID, the communication task\nyielded the best results for dyskinesia (severity estimation: r = 0.661,\ndetection: AUC = 0.930). For parkinsonism, leg agility had better results for\nseverity estimation (r = 0.618), while toe tapping was better for detection\n(AUC = 0.773). UDysRS and UPDRS Part III scores were predicted with r = 0.741\nand 0.530, respectively. Conclusion: This paper presents the first application\nof deep learning for vision-based assessment of parkinsonism and LID and\ndemonstrates promising performance for the future translation of deep learning\nto PD clinical practices. Significance: The proposed system provides insight\ninto the potential of computer vision and deep learning for clinical\napplication in PD.","url_abs":"http://arxiv.org/abs/1707.09416v2","url_pdf":"http://arxiv.org/pdf/1707.09416v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"vision-based-assessment-of-parkinsonism-and","repo_url":"https://github.com/limi44/Parkinson-s-Pose-Estimation-Dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[{"slug":"parkinson-s-pose-estimation-dataset","name":"Parkinson's Pose Estimation Dataset","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}