Unsupervised Deep Learning of Electronic Health Records to Characterize Heterogeneity Across Alzheimer Disease and Related Dementias: Cross-Sectional Study
JMIR Aging · 2025
DOI: 10.2196/65178 ↗At a glance
Querschnittstudie in JMIR Aging, 2025. Written by Matthew West and 9 co-authors. Institution: Massachusetts General Hospital, Cambridge, MA, United States. Major MEDLINE topics: Electronic Health Records, Alzheimer Disease, Deep Learning, Unsupervised Machine Learning. Cited 9 times so far (Crossref); 63 references. The full text is freely available in PubMed Central. Funded by: NIA NIH HHS.
Topics: Demenz
Abstract (original language)
Background
Alzheimer disease and related dementias (ADRD) exhibit prominent heterogeneity. Identifying clinically meaningful ADRD subtypes is essential for tailoring treatments to specific patient phenotypes.
Objective
We aimed to use unsupervised learning techniques on electronic health records (EHRs) from memory clinic patients to identify ADRD subtypes.
Methods
We used pretrained embeddings of non-ADRD diagnosis codes (International Classification of Diseases, Ninth Revision) and large language model (LLM)–derived embeddings of clinical notes from patient EHRs. Hierarchical clustering of these embeddings was used to identify ADRD subtypes. Clusters were characterized regarding their demographic and clinical features.
Results
We analyzed a cohort of 3454 patients with ADRD from a memory clinic at Massachusetts General Hospital, each with a specialist diagnosis. Clustering pretrained embeddings of the non-ADRD diagnosis codes in patient EHRs revealed the following 3 patient subtypes: one with skin conditions, another with psychiatric disorders and an earlier age of onset, and a third with diabetes complications. Similarly, using LLM-derived embeddings of clinical notes, we identified 3 subtypes of patients as follows: one with psychiatric manifestations and higher prevalence of female participants (prevalence ratio: 1.59), another with cardiovascular and motor problems and higher prevalence of male participants (prevalence ratio: 1.75), and a third one with geriatric health disorders. Notably, we observed significant overlap between clusters from both data modalities (χ24=89.4; P
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Massachusetts General Hospital, Cambridge, MA, United States.
ORCID profiles: Matthew West, You Cheng, Yingnan He, Yu Leng, Colin Magdamo, Bradley T Hyman, John R Dickson, Alberto Serrano-Pozo, Deborah Blacker, Sudeshna Das
Funding
- NIA NIH HHS
Cite
APA
West, M., Cheng, Y., He, Y., Leng, Y., Magdamo, C., Hyman, B. T., Dickson, J. R., Serrano-Pozo, A., Blacker, D., & Das, S. (2025). Unsupervised Deep Learning of Electronic Health Records to Characterize Heterogeneity Across Alzheimer Disease and Related Dementias: Cross-Sectional Study. JMIR Aging. https://doi.org/10.2196/65178
Vancouver
West M, Cheng Y, He Y, Leng Y, Magdamo C, Hyman BT, et al. Unsupervised Deep Learning of Electronic Health Records to Characterize Heterogeneity Across Alzheimer Disease and Related Dementias: Cross-Sectional Study. JMIR Aging. 2025. doi:10.2196/65178
BibTeX
@article{West2025,
author = {West, Matthew and Cheng, You and He, Yingnan and Leng, Yu and Magdamo, Colin and Hyman, Bradley T and Dickson, John R and Serrano-Pozo, Alberto and Blacker, Deborah and Das, Sudeshna},
title = {Unsupervised Deep Learning of Electronic Health Records to Characterize Heterogeneity Across Alzheimer Disease and Related Dementias: Cross-Sectional Study},
journal = {JMIR Aging},
year = {2025},
doi = {10.2196/65178}
}
EUVIMED