Abstract Neurodegenerative diseases such as Alzheimer’s disease (AD) and Parkinson’s disease (PD) are clinically heterogeneous, hampering the success of nonselective treatment strategies. Here we apply a transformer-based unsupervised clustering framework to longitudinal electronic health record data from over 100,000 patients across two UK cohorts, Clinical Practice Research Datalink Aurum and UK Biobank, to identify, validate and characterize subtypes of AD and PD. We uncover five reproducible subtypes for each condition, characterized by distinct comorbidity patterns, symptom trajectories, outcomes and genetic profiles. These include a high-mortality AD subtype with motor and cardiovascular features, and a genetically susceptible but clinically resilient PD subtype. We also identify metabolic–inflammatory and vascular–psychiatric phenotypes shared across AD and PD, suggesting cross-disease mechanisms. By integrating routinely collected electronic health record data with genetic analyses, our study provides a scalable framework for early, biologically informed subtyping, laying the groundwork for future targeted interventions in neurodegenerative diseases.
Lian et al. (2026) studied this question.