Leveraging Pre-trained and Transformer-derived Embeddings from EHRs to Characterize Heterogeneity Across Alzheimer's Disease and Related Dementias
This work addresses the need to understand disease subtypes for better treatment in Alzheimer's patients, but it appears incremental as it builds on existing methods for sub-type identification.
The researchers tackled the problem of characterizing heterogeneity in Alzheimer's disease and related dementias by using unsupervised learning on electronic health records, identifying sub-populations based on comorbidities and textual features.
Alzheimer's disease is a progressive, debilitating neurodegenerative disease that affects 50 million people globally. Despite this substantial health burden, available treatments for the disease are limited and its fundamental causes remain poorly understood. Previous work has suggested the existence of clinically-meaningful sub-types, which it is suggested may correspond to distinct etiologies, disease courses, and ultimately appropriate treatments. Here, we use unsupervised learning techniques on electronic health records (EHRs) from a cohort of memory disorder patients to characterise heterogeneity in this disease population. Pre-trained embeddings for medical codes as well as transformer-derived Clinical BERT embeddings of free text are used to encode patient EHRs. We identify the existence of sub-populations on the basis of comorbidities and shared textual features, and discuss their clinical significance.