Development and validation of an in-hospital mortality risk prediction model for patients with severe community-acquired pneumonia in the intensive care unit

Jingjing Pan; Wei Bu; Tao Guo; Zhi Geng; Min Shao

doi:10.1186/s12890-023-02567-5

Development and validation of an in-hospital mortality risk prediction model for patients with severe community-acquired pneumonia in the intensive care unit

BMC Pulm Med. 2023 Aug 17;23(1):303. doi: 10.1186/s12890-023-02567-5.

Authors

Jingjing Pan^#^{1

2}, Wei Bu^#¹, Tao Guo³, Zhi Geng^{4

5

6}, Min Shao⁷

Affiliations

¹ Department of Critical Care Medicine, The First Affiliated Hospital of Anhui Medical University, Hefei, China.
² Department of Respiratory Intensive Care Unit, Anhui Chest Hospital, Hefei, China.
³ Center for Biomedical Imaging, University of Science and Technology of China, Hefei, China.
⁴ Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China. gengzhi2017@163.com.
⁵ Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China. gengzhi2017@163.com.
⁶ Collaborative Innovation Center of Neuropsychiatric Disorders and Mental Health, Hefei, China. gengzhi2017@163.com.
⁷ Department of Critical Care Medicine, The First Affiliated Hospital of Anhui Medical University, Hefei, China. shaomin@ahmu.edu.cn.

^# Contributed equally.

Abstract

Background: A high mortality rate has always been observed in patients with severe community-acquired pneumonia (SCAP) admitted to the intensive care unit (ICU); however, there are few reported predictive models regarding the prognosis of this group of patients. This study aimed to screen for risk factors and assign a useful nomogram to predict mortality in these patients.

Methods: As a developmental cohort, we used 455 patients with SCAP admitted to ICU. Logistic regression analyses were used to identify independent risk factors for death. A mortality prediction model was built based on statistically significant risk factors. Furthermore, the model was visualized using a nomogram. As a validation cohort, we used 88 patients with SCAP admitted to ICU of another hospital. The performance of the nomogram was evaluated by analysis of the area under the receiver operating characteristic (ROC) curve (AUC), calibration curve analysis, and decision curve analysis (DCA).

Results: Lymphocytes, PaO2/FiO2, shock, and APACHE II score were independent risk factors for in-hospital mortality in the development cohort. External validation results showed a C-index of 0.903 (95% CI 0.838-0.968). The AUC of model for the development cohort was 0.85, which was better than APACHE II score 0.795 and SOFA score 0.69. The AUC for the validation cohort was 0.893, which was better than APACHE II score 0.746 and SOFA score 0.742. Calibration curves for both cohorts showed agreement between predicted and actual probabilities. The results of the DCA curves for both cohorts indicated that the model had a high clinical application in comparison to APACHE II and SOFA scoring systems.

Conclusions: We developed a predictive model based on lymphocytes, PaO2/FiO2, shock, and APACHE II scores to predict in-hospital mortality in patients with SCAP admitted to the ICU. The model has the potential to help physicians assess the prognosis of this group of patients.

Keywords: Intensive care unit; Mortality risk prediction; Nomogram; Severe community-acquired pneumonia.

MeSH terms

Community-Acquired Infections*
Hospital Mortality
Hospitals
Humans
Intensive Care Units
Pneumonia*
Respiratory Distress Syndrome*
Risk Factors