Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease

• Published in: Scientific reports Vol. 8; no. 1; pp. 7129 - 21
• Main Authors: Gao, Chao, Sun, Hanbo, Wang, Tuo, Tang, Ming, Bohnen, Nicolaas I., Müller, Martijn L. T. M., Herman, Talia, Giladi, Nir, Kalinin, Alexandr, Spino, Cathie, Dauer, William, Hausdorff, Jeffrey M., Dinov, Ivo D.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 08.05.2018; Nature Publishing Group; Nature Portfolio
• Subjects: 59/57; 639/705/1046; 692/617/375/346/1718; Accidental Falls - prevention & control; Aged; Animal models; Artificial intelligence; Classification; Clinical outcomes; Falls; Female; Gait; Gait - physiology; Gait Disorders, Neurologic - diagnosis; Gait Disorders, Neurologic - diagnostic imaging; Gait Disorders, Neurologic - physiopathology; Humanities and Social Sciences; Humans; Learning algorithms; Logistic Models; Machine Learning; Male; Middle Aged; Models, Theoretical; Movement disorders; multidisciplinary; Neural networks; Neuroimaging; Neuroimaging - methods; Parkinson Disease - diagnosis; Parkinson Disease - diagnostic imaging; Parkinson Disease - physiopathology; Parkinson's disease; Postural Balance - physiology; Posture; Prediction models; Science; Science (multidisciplinary); Support Vector Machine; Tremor
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-018-24783-4

In this study, we apply a multidisciplinary approach to investigate falls in PD patients using clinical, demographic and neuroimaging data from two independent initiatives (University of Michigan and Tel Aviv Sourasky Medical Center). Using machine learning techniques, we construct predictive models to discriminate fallers and non-fallers. Through controlled feature selection, we identified the most salient predictors of patient falls including gait speed, Hoehn and Yahr stage, postural instability and gait difficulty-related measurements. The model-based and model-free analytical methods we employed included logistic regression, random forests, support vector machines, and XGboost. The reliability of the forecasts was assessed by internal statistical (5-fold) cross validation as well as by external out-of-bag validation. Four specific challenges were addressed in the study: Challenge 1, develop a protocol for harmonizing and aggregating complex, multisource, and multi-site Parkinson’s disease data; Challenge 2, identify salient predictive features associated with specific clinical traits, e.g., patient falls; Challenge 3, forecast patient falls and evaluate the classification performance; and Challenge 4, predict tremor dominance (TD) vs. posture instability and gait difficulty (PIGD). Our findings suggest that, compared to other approaches, model-free machine learning based techniques provide a more reliable clinical outcome forecasting of falls in Parkinson’s patients, for example, with a classification accuracy of about 70–80%.