BMJ Open (Sep 2023)

A nomogram for predicting hospital mortality of critical ill patients with sepsis and cancer: a retrospective cohort study based on MIMIC-IV and eICU-CRD

  • Hao Wang,
  • Hao Zhang,
  • Hai-Jun Wang,
  • Zhen-nan Yuan,
  • Yu-juan Xue,
  • Shi-ning Qu,
  • Chu-lin Huang,
  • Xue-zhong Xing

DOI
https://doi.org/10.1136/bmjopen-2023-072112
Journal volume & issue
Vol. 13, no. 9

Abstract

Read online

Objective Sepsis remains a high cause of death, particularly in immunocompromised patients with cancer. The study was to develop a model to predict hospital mortality of septic patients with cancer in intensive care unit (ICU).Design Retrospective observational study.Setting Medical Information Mart for Intensive Care IV (MIMIC IV) and eICU Collaborative Research Database (eICU-CRD).Participants A total of 3796 patients in MIMIC IV and 549 patients in eICU-CRD were included.Primary outcome measures The model was developed based on MIMIC IV. The internal validation and external validation were based on MIMIC IV and eICU-CRD, respectively. Candidate factors were processed with the least absolute shrinkage and selection operator regression and cross-validation. Hospital mortality was predicted by the multivariable logistical regression and visualised by the nomogram. The model was assessed by the area under the curve (AUC), calibration curve and decision curve analysis curve.Results The model exhibited favourable discrimination (AUC: 0.726 (95% CI: 0.709 to 0.744) and 0.756 (95% CI: 0.712 to 0.801)) in the internal and external validation sets, respectively, and better calibration capacity than Acute Physiology and Chronic Health Evaluation IV in external validation.Conclusions Despite that the predicted model was based on a retrospective study, it may also be helpful to predict the hospital morality of patients with solid cancer and sepsis.