Artificial intelligence in 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.

Computer-aided therapeutics have changed the method of data interpretation for patients with neurodegenerative disorders. Artificial intelligence (AI)-based clinical practices are not only solving the knots of complex disorders, but also aiding for optimized interventions. . Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process.

The application of machine learning algorithms to medicine and scientific research has been widely discussed in recent years In the past decade, new technologies have enabled rapid accumulation of patient data such as ultrasonography and MRI readouts; omics profiles of biological samples; electronically captured clinical, behavioural and activity data; and social media-derived information. These big health datasets are high-dimensional, meaning the number of features (or variables) recorded per observation can sometimes exceed the total number of observations.

Despite the potential of machine learning, creating and applying machine learning algorithms to neurodegenerative disease data remains difficult. One challenge relates to the data itself — machine learning models are only as powerful as the data they rely on. The lack of large datasets, especially multidimensional patient data, for many diseases is a barrier to the application of machine learning. Patient datasets typically consist of only tens or hundreds of patients and tend to be noisy because of measurement inconsistency, error or participant drop-out; these factors all make statistical analyses more prone to errors.


Myszczynska, M.A., Ojamies, P.N., Lacoste, A.M.B. et al. Applications of machine learning to diagnosis and treatment of neurodegenerative diseases. Nat Rev Neurol 16, 440–456 (2020).

Leave a Reply

Your email address will not be published.