Background: In Parkinson’s disease (PD), there is heterogeneity in the clinical presentation and underlying biology. Research on PD subtypes aims to understand this heterogeneity with potential contribution for the knowledge of disease pathophysiology, natural history and therapeutic development. There have been many studies of PD subtypes but their impact remains unclear with limited application in research or clinical practice. Objective: To critically evaluate PD subtyping systems. Methods: We conducted a systematic review of PD subtypes, assessing the characteristics of the studies reporting a subtyping system for the first time. We completed a critical appraisal of their methodologic quality and clinical applicability using standardized checklists. Results: We included 38 studies. The majority were cross-sectional (n = 26, 68.4%), used a data-driven approach (n = 25, 65.8%), and non-clinical biomarkers were rarely used (n = 5, 13.1%). Motor characteristics were the domain most commonly reported to differentiate PD subtypes. Most of the studies did not achieve the top rating across items of a Methodologic Quality checklist. In a Clinical Applicability Checklist, the clinical importance of differences between subtypes, potential treatment implications and applicability to the general population were rated poorly, and subtype stability over time and prognostic value were largely unknown. Conclusion: Subtyping studies undertaken to date have significant methodologic shortcomings and most have questionable clinical applicability and unknown biological relevance. The clinical and biological signature of PD may be unique to the individual, rendering PD resistant to meaningful cluster solutions. New approaches that acknowledge the individual-level heterogeneity and that are more aligned with personalized medicine are needed.

Despite the effectiveness of levodopa for treatment of Parkinson’s disease (PD), prolonged usage leads to development of motor complications, most notably levodopa-induced dyskinesia (LID). Persons with PD and their physicians must regularly modify treatment regimens and timing for optimal relief of symptoms. While standardized clinical rating scales exist for assessing the severity of PD symptoms, they must be administered by a trained medical professional and are inherently subjective. Computer vision is an attractive, non-contact, potential solution for automated assessment of PD, made possible by recent advances in computational power and deep learning algorithms. The objective of this paper was to evaluate the feasibility of vision-based assessment of parkinsonism and LID using pose estimation. Nine participants with PD and LID completed a levodopa infusion protocol, where symptoms were assessed at regular intervals using the Unified Dyskinesia Rating Scale (UDysRS) and Unified Parkinson’s Disease Rating Scale (UPDRS). Movement trajectories of individual joints were extracted from videos of PD assessment using Convolutional Pose Machines, a pose estimation algorithm built with deep learning. Features of the movement trajectories (e.g. kinematic, frequency) were used to train random forests to detect and estimate the severity of parkinsonism and LID. Communication and drinking tasks were used to assess LID, while leg agility and toe tapping tasks were used to assess parkinsonism. Feature sets from tasks were also combined to predict total UDysRS and UPDRS Part III scores. For LID, the communication task yielded the best results (detection: AUC = 0.930, severity estimation: r = 0.661). For parkinsonism, leg agility had better results for severity estimation (r = 0.618), while toe tapping was better for detection (AUC = 0.773). UDysRS and UPDRS Part III scores were predicted with r = 0.741 and 0.530, respectively. The proposed system provides insight into the potential of computer vision and deep learning for clinical application in PD and demonstrates promising performance for the future translation of deep learning to PD clinical practices. Convenient and objective assessment of PD symptoms will facilitate more frequent touchpoints between patients and clinicians, leading to better tailoring of treatment and quality of care.