Interpretable machine learning models using early dynamic clinical features to predict early hemodynamic stabilization after vasopressor initiation in patients with septic shock: development in MIMIC-IV and external validation in eICU
Shu-jiao Lu, Ze-kun Wei, Guo-chen Li, Qian-yu Bi, Le-run Zong, Li Kong, Fei-hu Zhang · 2026
Read Interpretable machine learning models using early dynamic clinical features to predict early hemodynamic stabilization after vasopressor initiation in patients with septic shock: development in MIMIC-IV and external validation in eICU by Shu-jiao Lu, Ze-kun Wei, Guo-chen Li, Qian-yu Bi, Le-run Zong, Li Kong, Fei-hu Zhang (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/pmc-13624129.txt.
Description
Septic shock is fought with pressor drugs that squeeze the vessels, and some patients settle fast while others spiral. Lu and co-authors build a forecast of that settling in 2026, from the first six hours of care. The signs are live ones — pressure, dose, and their drift — not a door snapshot.
Settling means pressure held in range from hour six to twenty-four, with no dose climb. Seven learning models were built on one great care database and tested cold on a second. The winners are built to be read, not just run: a clinician can see which signs drove each call. Scores weigh hit rate, truth of the odds, and bedside worth. Early sight of a spiral could change the first day's plan.
Catalog record
| CREATOR | Shu-jiao Lu, Ze-kun Wei, Guo-chen Li, Qian-yu Bi, Le-run Zong, Li Kong, Fei-hu Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 96 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |