Subphenotype heterogeneity to guide predictive enrichment in acute kidney injury: insights from machine learning and target trial emulation
Jiayang Li, Mingyi Zhao, Qingnan He · 2025
Read Subphenotype heterogeneity to guide predictive enrichment in acute kidney injury: insights from machine learning and target trial emulation by Jiayang Li, Mingyi Zhao, Qingnan He (2025) 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/pmc-12752266.txt.
Description
Jiayang Li, Mingyi Zhao, and Qingnan He split acute kidney injury into data-driven subtypes, then ask which treatments suit each. Their 2025 study starts from a flaw in older clustering: it grouped patients by outcomes, not by the goal of tailored care. Records came from a large intensive care database, covering 31,030 patients diagnosed within two days of arrival.
A probabilistic mapping model found four subtypes. One was large and middling; another burned with inflammation, liver trouble, and severe injury; a third centered on heart-driven congestion. The team then emulated trials inside each subtype, comparing two blood-pressure drugs, dialysis modes, and dialysis timing. The point is predictive enrichment: matching the therapy to the subtype that gains from it.
Catalog record
| CREATOR | Jiayang Li, Mingyi Zhao, Qingnan He |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |