2134/37746 David C. Wong David C. Wong Samuel D. Relton Samuel D. Relton Hui Fang Hui Fang Rami Qhawaji Rami Qhawaji Christopher D. Graham Christopher D. Graham Jane Alty Jane Alty Stefan Williams Stefan Williams Supervised classification of bradykinesia for Parkinson’s disease diagnosis from smartphone videos Loughborough University 2019 Classification Parkinson’s Bradykinesia Video Computer vision Diagnosis Support vector machine Information and Computing Sciences not elsewhere classified 2019-05-14 14:26:33 Conference contribution https://repository.lboro.ac.uk/articles/conference_contribution/Supervised_classification_of_bradykinesia_for_Parkinson_s_disease_diagnosis_from_smartphone_videos/9401510 Slowness of movement, known as bradykinesia, in an important early symptom of Parkinson’s disease. This symptom is currently assessed subjectively by clinical experts. However, expert assessment has been shown to be subject to inter-rater variability. We propose a low-cost, contactless system using smartphone videos to automatically determine the presence of bradykinesia. Using 70 videos recorded in a pilot study, we predict the presence of bradykinesia with an estimated test accuracy of 0.79 and the presence of Parkinson’s disease diagnosis with estimated test accuracy 0.63. Even on a small set of pilot data this accuracy is comparable to that recorded by blinded human experts.