The role of AI and machine learning in the diagnosis of Parkinson's disease and atypical parkinsonisms

Parkinson's disease is a neurodegenerative movement disorder associated with motor and non-motor symptoms causing severe disability as the disease progresses. The development of biomarkers for Parkinson's disease to diagnose patients earlier and predict disease progression is imperative. As artificial intelligence and machine learning techniques efficiently process data and can handle multiple data types, we reviewed the literature to determine the extent to which these techniques have been applied to biomarkers for Parkinson's disease and movement disorders. We determined that the most applicable machine learning techniques are support vector machines and neural networks, depending on the size and type of the data being analyzed. Additionally, more complex machine learning techniques showed increased accuracy when compared to less complex techniques, especially when multiple machine learning models were combined. We can conclude that artificial intelligence and machine learning techniques may have the capacity to significantly boost diagnostic capacity in movement disorders and Parkinson's disease. •Machine learning models can differentiate parkinsonisms from other movement disorders.•Performance is consistently high across movement disorders, including parkinsonism, dystonia, and essential tremor.•Higher diagnostic accuracy is achieved when multiple biomarkers are combined in models.•Artificial intelligence performs better when multiple machine learning models are combined.