Comparison of clinical scores for predicting stroke-associated pneumonia after intracerebral hemorrhage (ICH): potential tools for personalized care and clinical trials for ICH

Ruijun Ji; Yanfang Liu; Xinyu Liu; Linlin Wang; Dandan Wang; Wenjuan Wang; Runhua Zhang; Ruixuan Jiang; Jiaokun Jia; Hao Feng; Zeyu Ding; Gaifen Liu; Jingjing Lu; Yi Ju; Xingquan Zhao

doi:10.21037/atm-21-4046

Comparison of clinical scores for predicting stroke-associated pneumonia after intracerebral hemorrhage (ICH): potential tools for personalized care and clinical trials for ICH

Ann Transl Med. 2022 Apr;10(7):397. doi: 10.21037/atm-21-4046.

Authors

Ruijun Ji^{1

2

3

4

5}, Yanfang Liu^{1

2}, Xinyu Liu¹, Linlin Wang¹, Dandan Wang^{1

2}, Wenjuan Wang^{1

2}, Runhua Zhang^{1

2}, Ruixuan Jiang^{1

2}, Jiaokun Jia^{1

2}, Hao Feng^{1

2}, Zeyu Ding^{1

2}, Gaifen Liu^{1

2}, Jingjing Lu^{1

2}, Yi Ju^{1

2}, Xingquan Zhao^{1

2

3

4

5}

Affiliations

¹ Department of Neurology, Tiantan Hospital, Capital Medical University, Beijing, China.
² China National Clinical Research Center for Neurological Diseases, Beijing, China.
³ Center of Stroke, Beijing Institute for Brain Disorders, Beijing, China.
⁴ Beijing Key Laboratory of Translational Medicine for Cerebrovascular Disease, Beijing, China.
⁵ Beijing Key Laboratory of Brain Function Reconstruction, Beijing, China.

Abstract

Background: This study aimed to systematically compare the discrimination and calibration of 5 clinical scores for stroke-associated pneumonia (SAP) after intracerebral hemorrhage (ICH).

Methods: We derived a validation cohort from the Beijing Registration of Intracerebral Hemorrhage. SAP was then diagnosed according to the Center for Disease Control and Prevention's criteria for hospital-acquired pneumonia. The area under the receiver operating characteristic curve (AUROC) and Hosmer-Lemeshow goodness-of-fit test were used to assess model discrimination and calibration.

Results: A total of 1964 patients were enrolled in the study. The mean age was 56.8±14.4 years, and 67.6% were male. The median National Institutes of Health Stroke Scale (NIHSS) score at admission was 11 [interquartile range (IQR), 3-21], while the median length of stay (LOS) was 16 days (IQR, 8-22 days). A total of 575 (29.2%) patients were diagnosed with in-hospital SAP after ICH. The AUROC of the 5 clinical scores ranged from 0.732 to 0.800. In comparing these scores, we found that the ICH-associated pneumonia score-B (ICH-APS-B 0.800; 95% CI: 0.780-0.820; P<0.001) showed a statistically better discrimination than did the other risk models (all P<0.001). Furthermore, all clinical scores performed better in patients with an LOS >72 h. The ICH-APS-B (0.827; 95% CI: 0.806-0.848; P<0.001) still showed statistically better discrimination than did the other risk models in patients with an LOS longer than 72 hours. The Hosmer-Lemeshow test also revealed that the ICH-APS-B. had the largest Cox and Snell R2 result for in-hospital SAP after ICH.

Conclusions: Among the 5 models for predicting SAP after ICH, the ICH-APS-B showed the best predictive performance, suggests it may be a useful tool for implementing the personalized care of patients and conducting clinical trials of SAP after ICH.

Keywords: Intracerebral hemorrhage (ICH); calibration; discrimination; risk score; stroke-associated pneumonia (SAP).