Development of a Tremor Detection Algorithm for use in an Academic Movement Disorders Center

Abstract

AbstractTremor, defined as an “involuntary, rhythmic, oscillatory movement of a body part,” is a key feature of many neurological conditions, but is still clinically assessed by visual observation. Methodologies for objectively quantifying tremor are promising but remain non-standardized across centers. Our center performs full-body behavioral testing with 3D motion capture for clinical and research purposes for patients with Parkinson’s disease, essential tremor, and other conditions. The objective of this study was to assess the ability of several candidate processing pipelines to identify the presence or absence of tremor in kinematic data from movement disorders patients compared to expert ratings from movement disorders specialists. We curated a database of 2,272 separate kinematic data recordings from our center, each of which was contemporaneously annotated as tremor present or absent by a clinical provider. We compared the ability of six separate processing pipelines to recreate clinician ratings based on F1 score, in addition to accuracy, precision, and recall. We found generally comparable performance across algorithms. The averageF1 score was 0.84±0.02 (Mean±SD; range 0.81−0.87), with allF1 confidence intervals overlapping. The highest performing algorithm (cross-validatedF1 = 0.87) was a hybrid that used engineered features adapted from an algorithm in longstanding clinical use with a modern Support Vector Machine classifier. Taken together, our results suggest the potential to update legacy clinical decision support systems to incorporate modern machine learning classifiers in order to create better performing tools.