Machine Learning for Predicting Critical Postoperative Interventions: Proof-of-Concept Study Using the INSPIRE Dataset
Manan Shukla, Paul Fodor, Suresh Yelika, Nicholas Ahn, Nidhi Rohatgi · 2026
Read Machine Learning for Predicting Critical Postoperative Interventions: Proof-of-Concept Study Using the INSPIRE Dataset by Manan Shukla, Paul Fodor, Suresh Yelika, Nicholas Ahn, Nidhi Rohatgi (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/PMC13412138.txt.
Description
Manan Shukla and colleagues test in 2026 whether machine learning can predict which surgery patients will need critical support afterwards. Complications after operations drive much illness and death, and simple risk scores give only rough, group-level estimates. Using the public INSPIRE perioperative database of about 131,000 surgical cases, the team trained neural networks and random forests on lab results, medicines, surgery type, and vital signs recorded during operations.
Models forecast four supports: breathing machines, ECMO, balloon pumps, and continuous kidney therapy. Accuracy on a held-out set of nearly 39,000 patients ranged from about 95 to 99 percent depending on the outcome. The authors present the work as proof of concept for earlier, targeted intervention.
Catalog record
| CREATOR | Manan Shukla, Paul Fodor, Suresh Yelika, Nicholas Ahn, Nidhi Rohatgi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |