Accuracy of Artificial Intelligence-Based Models Versus Conventional Scoring Systems (APACHE, SOFA, and SAPS) in Predicting Mortality Among ICU Patients: A Systematic Review and Meta-Analysis
Vimukta Pradhan, Himanshu Shekhar, Punam Kumari Munda, Ashutosh Kumar Tiwari, Sneha Jha, Pratibha Rai · 2026
Read Accuracy of Artificial Intelligence-Based Models Versus Conventional Scoring Systems (APACHE, SOFA, and SAPS) in Predicting Mortality Among ICU Patients: A Systematic Review and Meta-Analysis by Vimukta Pradhan, Himanshu Shekhar, Punam Kumari Munda, Ashutosh Kumar Tiwari, Sneha Jha, Pratibha Rai (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-13284171.txt.
Description
Vimukta Pradhan and colleagues reviewed in 2026 whether artificial intelligence models predict death in intensive care better than classic scoring systems. Tools such as APACHE, SOFA, and SAPS are widely used, yet they rest on fixed structures and straight-line assumptions. The team searched four databases for studies from 2015 to 2025 that compared AI models against those scores on the same patients, and rated bias risk with a standard tool.
Ten studies covering roughly half a million ICU admissions qualified. AI models sorted survivors from non-survivors more sharply, with accuracy scores from 0.83 to 0.97 and gains over classic scores in every study. Eight studies fed a combined diagnostic analysis. The authors still note that model type, dataset, and time handling shaped results across studies.
Catalog record
| CREATOR | Vimukta Pradhan, Himanshu Shekhar, Punam Kumari Munda, Ashutosh Kumar Tiwari, Sneha Jha, Pratibha Rai |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 76 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |