Early Prediction of Mortality for Septic Patients Visiting Emergency Room Based on Explainable Machine Learning: A Real-World Multicenter Study.
Sang-Won ParkNa Young YeoSeong Uk KangTaejun HaTae-Hoon KimDoo Hee LeeDowon KimSeheon ChoiMinkyu KimDongHoon LeeDoHyeon KimWoo Jin KimSeung-Joon LeeYeon-Jeong HeoDa Hye MoonSeon-Sook HanYoon KimHyun-Soo ChoiDong Kyu OhSu Yeon LeeMi-Hyeon ParkChae-Man LimJeongwon Heonull nullPublished in: Journal of Korean medical science (2024)
Newly established ML-based models achieved good prediction of mortality in patients with sepsis. Using several clinical variables acquired at the baseline can provide more accurate results for early predictions than using SOFA components. Additionally, the impact of each variable was identified.
Keyphrases
- machine learning
- end stage renal disease
- acute kidney injury
- cardiovascular events
- ejection fraction
- newly diagnosed
- chronic kidney disease
- emergency department
- risk factors
- healthcare
- public health
- intensive care unit
- prognostic factors
- cardiovascular disease
- peritoneal dialysis
- high resolution
- coronary artery disease
- patient reported outcomes
- septic shock
- deep learning
- patient reported