Unsupervised characterization of 100,272 EHR patients identifies high-risk groups and comorbidities linked to premature aging
Su Xian, Jordan W Smoller, Yuan Luo, Theresa L Walunas, Cong Liu, Atlas Khan, Chunhua Weng, Iftikhar J Kullo, Wei-Qi Wei, Gail P Jarvik, David R Crosslin · 2026
Read Unsupervised characterization of 100,272 EHR patients identifies high-risk groups and comorbidities linked to premature aging by Su Xian, Jordan W Smoller, Yuan Luo, Theresa L Walunas, Cong Liu, Atlas Khan, Chunhua Weng, Iftikhar J Kullo, Wei-Qi Wei, Gail P Jarvik, David R Crosslin (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13554212.txt.
Description
Su Xian leads an eleven-author team sorting more than one hundred thousand patients into groups by their disease patterns in a 2026 study. Health records hold rich but messy data on diagnoses, drugs, and tests. Without any labels, the team clustered 100,272 patients from a large research network. Seventy groups emerged, each with its own mix of conditions, shaped strongly by age and sex.
When diseases first appeared predicted a person's age with surprising accuracy, and tied to death risk too. Gene effects showed early, then faded as aging took over. Several groups carried heavy disease loads and signs of aging before their time. A second group of patients confirmed those high-risk clusters, giving doctors leads for targeted care.
Catalog record
| CREATOR | Su Xian, Jordan W Smoller, Yuan Luo, Theresa L Walunas, Cong Liu, Atlas Khan, Chunhua Weng, Iftikhar J Kullo, Wei-Qi Wei, Gail P Jarvik, David R Crosslin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 75807 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |