Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost
importance 7/10
ai assisted
Sepsis Diagnosis and Treatment critical care stage: research
Problem
Predicting 30-day mortality in ICU sepsis-3 patients (MIMIC-III) early enough to guide treatment and improve survival.
Why it matters
Sepsis is a major cause of in-hospital death, especially in ICU patients.
What the AI did
An XGBoost machine learning model was developed to predict 30-day mortality and compared against logistic regression and SAPS-II scoring.
Results
not stated in source
Impact
Aims to outperform traditional prediction models, but the comparison outcome is not stated in the abstract.
Record
| Venue | Journal of Translational Medicine |
|---|---|
| Published | 2020 |
| Work type | article |
| Authors | Nianzong Hou, Mingzhe Li, Lu He, Bing Xie, Lin Wang, Rumin Zhang, Yong Yu, Xiaodong Sun et al. |
| Citations | 568 (OpenAlex, at import time) |
| References | 47 |
| Model or method | XGBoost |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1186/s12967-020-02620-5 |
| Open access | gold |
| Keywords | sepsis, XGBoost, mortality prediction, MIMIC-III, machine learning |
Importance rating
7
significant — thousands to millions affected
Abstract states sepsis is a significant cause of in-hospital mortality, especially in ICU, and early prediction can improve survival; major clinical problem, though population-level scale is not quantified.