Characterizing personalized neuropathology in dementia and mild cognitive impairment with explainable artificial intelligence

Deep learning applied to magnetic resonance imaging data have shown great promise as a translational technology for diagnosis and prognosis in dementia, but its impact clinically has thus far been limited. This is partially attributed to the opaqueness of deep learning models, causing insufficient understanding of what underlies their decisions. To overcome this, we trained convolutional neural nets to differentiate patients with dementia from healthy controls, and applied layerwise relevance propagation to procure individual-level explanations of the model predictions. Through extensive validations we demonstrate that patterns recognized by the model corroborate existing knowledge of neuropathology in dementia. Next, employing the explainable dementia classifier in a longitudinal dataset of patients with mild cognitive impairment, we show that the spatially rich explanations complement the prediction for prognosis, and help characterize the personalized manifestation of disease. Overall, our work exemplifies the clinical potential of explainable artificial intelligence in precision medicine. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This work was funded by the UiO:LifeScience Convergence Environment (project: 4MENT). ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The dataset was compiled from various sources, the most important being: ADNI: https://adni.loni.usc.edu/ AIBL: http://www.aibl.csiro.au/ MIRIAD: https://www.nitrc.org/projects/miriad/ OASIS3: https://www.oasis-brains.org/ I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes The raw data incorporated in this work were gathered from various resources. Material requests will need to be placed with individual principal investigators. A detailed overview of the independent datasets, and their origins, is provided in the supplementary information.