Early ICU Mortality Prediction and Survival Analysis for Respiratory Failure

Yilin Yin; Chun-An Chou

Early ICU Mortality Prediction and Survival Analysis for Respiratory Failure

Machine Learning 2021-09-08 v1

Authors: Yilin Yin , Chun-An Chou

Abstract

Respiratory failure is the one of major causes of death in critical care unit. During the outbreak of COVID-19, critical care units experienced an extreme shortage of mechanical ventilation because of respiratory failure related syndromes. To help this, the early mortality risk prediction in patients who suffer respiratory failure can provide timely support for clinical treatment and resource management. In the study, we propose a dynamic modeling approach for early mortality risk prediction of the respiratory failure patients based on the first 24 hours ICU physiological data. Our proposed model is validated on the eICU collaborate database. We achieved a high AUROC performance (80-83%) and significantly improved AUCPR 4% on Day 5 since ICU admission, compared to the state-of-art prediction models. In addition, we illustrated that the survival curve includes the time-varying information for the early ICU admission survival analysis.

Keywords

early icu mortality prediction respiratory failure survival analysis dynamic modeling eICU database AUROC AUCPR

Cite

@article{arxiv.2109.03048,
  title  = {Early ICU Mortality Prediction and Survival Analysis for Respiratory Failure},
  author = {Yilin Yin and Chun-An Chou},
  journal= {arXiv preprint arXiv:2109.03048},
  year   = {2021}
}

Related papers

View all related →