Identifying dementia neuropathology using low-burden clinical data

Abstract

INTRODUCTION: Identifying dementia neuropathology is critical for guiding effective therapies and clinical trials. To tackle this, we developed semi-supervised models for identifying neuropathology using low-burden data to improve generalizability. METHODS: We defined low-burden data as being reasonably obtainable at a primary care setting. By using a semi-supervised learning paradigm, we can amplify the utility of low-burden data. We trained a clustering and a semi-supervised prediction model to yield clustering and prediction results for different neuropathology lesion types. RESULTS: Our clustering model identified two clinically meaningful outlier groups that were either neuropathology-enriched or -scarce. We predicted neuropathology burden across different pathology types and found that using low-burden data over multiple clinical visits can predict neuropathology on par with using higher-burden data. DISCUSSION: This work fills a critical gap in the field by using low-burden clinical data to predict neuropathology, thereby improving dementia screening, therapy, and targeted clinical trials. Highlights: Clinical data are useful for neuropathology screening in future clinical trials. Novel application of semi-supervised learning for identifying neuropathology. Clustering model found groups with highly different neuropathology prevalence. Low-burden data can provide relatively accurate predictions of pathology load. Higher-burden, longitudinal data are most helpful for predicting vascular lesions.