Predicting in-hospital death in pneumonic COPD exacerbation via BAP-65, CURB-65 and machine learning

Akihiro Shiroshita; Yuya Kimura; Hiroshi Shiba; Chigusa Shirakawa; Kenya Sato; Shinya Matsushita; Keisuke Tomii; Yuki Kataoka

doi:10.1183/23120541.00452-2021

Predicting in-hospital death in pneumonic COPD exacerbation via BAP-65, CURB-65 and machine learning

ERJ Open Res. 2022 Jan 24;8(1):00452-2021. doi: 10.1183/23120541.00452-2021. eCollection 2022 Jan.

Authors

Akihiro Shiroshita¹, Yuya Kimura², Hiroshi Shiba³, Chigusa Shirakawa⁴, Kenya Sato⁵, Shinya Matsushita⁵, Keisuke Tomii⁴, Yuki Kataoka^{6

7

8}

Affiliations

¹ Dept of Respiratory Medicine, Ichinomiyanishi Hospital, Ichinomiya, Japan.
² Dept of Respiratory Medicine, Clinical Research Center, National Hospital Organization Tokyo National Hospital, Tokyo, Japan.
³ Post Graduate Education Center, Kameda Medical Center, Kamogawa, Japan.
⁴ Department of Respiratory Medicine, Kobe City Medical Center General Hospital, Kobe, Japan.
⁵ Dept of Thoracic Medicine, Saiseikai Yokohamashi Tobu Hospital, Yokohama, Japan.
⁶ Dept of Internal Medicine, Kyoto Min-Iren Asukai Hospital, Kyoto, Japan.
⁷ Section of Clinical Epidemiology, Dept of Community Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan.
⁸ Dept of Healthcare Epidemiology, Graduate School of Medicine/Public Health, Kyoto University, Kyota, Japan.

Abstract

Introduction: There is no established clinical prediction model for in-hospital death among patients with pneumonic COPD exacerbation. We aimed to externally validate BAP-65 and CURB-65 and to develop a new model based on the eXtreme Gradient Boosting (XGBoost) algorithm.

Methods: This multicentre cohort study included patients aged ≥40 years with pneumonic COPD exacerbation. The input data were age, sex, activities of daily living, mental status, systolic and diastolic blood pressure, respiratory rate, heart rate, peripheral blood eosinophil count and blood urea nitrogen. The primary outcome was in-hospital death. BAP-65 and CURB-65 underwent external validation using the area under the receiver operating characteristic curve (AUROC) in the whole dataset. We used XGBoost to develop a new prediction model. We compared the AUROCs of XGBoost with that of BAP-65 and CURB-65 in the test dataset using bootstrap sampling.

Results: We included 1190 patients with pneumonic COPD exacerbation. The in-hospital mortality was 7% (88 out of 1190). In the external validation of BAP-65 and CURB-65, the AUROCs (95% confidence interval) of BAP-65 and CURB-65 were 0.69 (0.66-0.72) and 0.69 (0.66-0.72), respectively. XGBoost showed an AUROC of 0.71 (0.62-0.81) in the test dataset. There was no significant difference in the AUROCs of XGBoost versus BAP-65 (absolute difference 0.054; 95% CI -0.057-0.16) or versus CURB-65 (absolute difference 0.0021; 95% CI -0.091-0.088).

Conclusion: BAP-65, CURB-65 and XGBoost showed low predictive performance for in-hospital death in pneumonic COPD exacerbation. Further large-scale studies including more variables are warranted.