Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review.
Borchert RJ., Azevedo T., Badhwar A., Bernal J., Betts M., Bruffaerts R., Burkhart MC., Dewachter I., Gellersen HM., Low A., Lourida I., Machado L., Madan CR., Malpetti M., Mejia J., Michopoulou S., Muñoz-Neira C., Pepys J., Peres M., Phillips V., Ramanan S., Tamburin S., Tantiangco HM., Thakur L., Tomassini A., Vipin A., Tang E., Newby D., Deep Dementia Phenotyping (DEMON) Network None., Ranson JM., Llewellyn DJ., Veldsman M., Rittman T.
INTRODUCTION: Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia. METHODS: We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases. RESULTS: A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort. DISCUSSION: The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice. HIGHLIGHTS: There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.