Artificial intelligence for predicting 30-day mortality after emergency laparotomy
Sergei Bedrikovetski, Ishraq Murshed, Warren Seow, Zachary Bunjo, Jahan Singh De Fontgalland, Luke Traeger, Ryash Vather · 2026
Read Artificial intelligence for predicting 30-day mortality after emergency laparotomy by Sergei Bedrikovetski, Ishraq Murshed, Warren Seow, Zachary Bunjo, Jahan Singh De Fontgalland, Luke Traeger, Ryash Vather (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-13529842.txt.
Description
Sergei Bedrikovetski and six co-authors test whether AI can predict death within thirty days of emergency belly surgery. Their 2026 study uses a national audit database from Australia and New Zealand holding more than eight thousand operations. A sound risk guess before surgery guides staffing, beds, and honest talks with families.
The team built neural network models in full and slim forms and set them against a standard risk score and a classic regression model. In held-out tests, the standard score led, with the regression and one neural model close behind. Statistical checks found no firm gap among the top three. About six and a half percent of patients died within the month. The authors say AI matches, but does not beat, trusted tools here.
Catalog record
| CREATOR | Sergei Bedrikovetski, Ishraq Murshed, Warren Seow, Zachary Bunjo, Jahan Singh De Fontgalland, Luke Traeger, Ryash Vather |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |