A scoping review of machine learning for sepsis prediction- feature engineering strategies and model performance: a step towards explainability
Authors' conclusion
Key dynamic indicators, including vital signs and critical laboratory values, are instrumental in the early detection of sepsis. Applying feature selection methods significantly boosts model precision, with models like Random Forest and XG Boost showing promising results.
Study context
- Population
- Patients in diverse clinical settings (Intensive Care Units (ICU), ED, others) in studies of Machine Learning (ML) sepsis prediction
- Participants
- 1,147,202 patients · 29 studies
- Comparison
- Feature engineering strategies across ML models for sepsis prediction
- Outcome
- Pivotal features for predicting sepsis across ML models; model efficacy (AUROC, sensitivity, specificity)
Main finding
As reported in the abstract
Model performance by feature engineering strategy
- Feature extraction techniques notably outperformed others in sensitivity and AUROC
- Diversity in prediction strategies and timeframes
Original publication
A scoping review of machine learning for sepsis prediction- feature engineering strategies and model performance: a step towards explainability. Crit Care. Published 28 May 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →