Applications of machine learning to diagnosis and treatment of neurodegenerative diseases

Globally, there is a huge unmet need for effective treatments for neurodegenerative diseases. The complexity of the molecular mechanisms underlying neuronal degeneration and the heterogeneity of the patient population present massive challenges to the development of early diagnostic tools and effective treatments for these diseases. Machine learning, a subfield of artificial intelligence, is enabling scientists, clinicians and patients to address some of these challenges. In this Review, we discuss how machine learning can aid early diagnosis and interpretation of medical images as well as the discovery and development of new therapies. A unifying theme of the different applications of machine learning is the integration of multiple high-dimensional sources of data, which all provide a different view on disease, and the automated derivation of actionable insights. In this Review, the authors describe the latest developments in the use of machine learning to interrogate neurodegenerative disease-related datasets. They discuss applications of machine learning to diagnosis, prognosis and therapeutic development, and the challenges involved in analysing health-care data. Key points Machine learning and natural language processing are forms of artificial intelligence that enable robust interrogation of multiple datasets to identify previously undiscovered patterns and relationships in the data. Machine learning approaches have been applied to the study of neurodegenerative diseases and show promise in the areas of early diagnosis, prognosis and development of new therapies. A substantial number of machine learning algorithms exist, and choosing the correct algorithm to apply to different types of data is crucial to obtain reliable results. Neuroimaging was the first area of neurology to benefit from the application of machine learning approaches to improve diagnosis; more recently, application of machine learning methods to motor function and language feature analysis has shown promise in decreasing the time taken to perform clinical assessments. The application of machine learning to longitudinal patient data collection and electronic health records has the potential to inform prognosis prediction and patient stratification. Large collections of curated datasets and robust assessment of machine learning methods will be needed to achieve full integration of machine learning into diagnostic and prognostic neurology practice and the design of future therapeutics.