Machine learning-based prediction of in-hospital mortality in patients with pneumonic chronic obstructive pulmonary disease exacerbations

AbstractObjective While linear regression and LASSO models have been established for predicting in-hospital mortality, there is currently no validated clinical prediction algorithm to predict in-hospital mortality for patients with chronic obstructive pulmonary disease (COPD) exacerbations using machine learning. Thus, we will evaluate the BAP-65 and CURB-65, and construct a novel prediction model using the random forest (RF) technique.Methods A dataset of 1,418 patients with COPD exacerbations was collected. Age, gender, mental status, vital signs, and laboratory results were all taken into account for predictors. The categorical outcome variable was hospital-based mortality of people over 65 years. The dataset was divided randomly into a training dataset (70%) and a testing dataset (30%). We trained three prediction models, BAP-65, CURB-65, and the RF model, estimated the area under the receiver operating characteristic curve (AUROC) for the entire dataset. We also conducted a comparison of the AUROC values using the Delong test.Results A total of 658 individuals with COPD acute exacerbations were enrolled. Our analysis using the receiver operating characteristic curve demonstrated that the RF model exhibited excellent performance, with an AUROC of 0.80 (95% confidence interval: 0.75-0.84). In comparison, the BAP-65 prediction model yielded an AUROC of 0.72 (0.68-0.75), while the CURB-65 prediction model achieved an AUROC of 0.69 (0.67-0.73).Conclusions The RF model demonstrated superior predictive capabilities than the BAP-65 and CURB-65 models in predicting in-hospital mortality. The results further highlighted significant factors for predicting in-hospital mortality, including blood eosinophil count, systolic blood pressure, and prior history of asthma.Keywords: Chronic obstructive pulmonary diseasemachine learningrandom forestmortality AcknowledgmentThis manuscript was edited by Changsha Shiyu Translation Service Co., Ltd.Declaration of interestThe authors declare there is no Complete of Interest at this study.Research ethics approvalThis study was approved by the research ethics committee of Chengdu Secondary People’s Hospital (2022CYFYIRB-BZ).Patient and public involvementThis study will not have any patient or public involvement.Author contributionsLY, XR, WH, NH, JZ, JH, RH, and KY all contributed to the work’s conception and design. WH assisted with data collection. LY, KY, NH, JZ, JH, RH, and KY assisted in data analysis and interpretation. LY and XR wrote the manuscript. The text was edited and approved by all authors. KY was responsible to hold all the authors accountable for every aspects of the task.Data sharingThe complete datasets used to train and evaluate the ML algorithms include personal information and are not publicly available. We provided a sample dataset used for model training and it could be found in supplemental material. Researchers interested in obtaining the complete data for research reasons can contact Mr. Wenbo Huang (19435061@life.hkbu.edu.hk).Code availabilityThe statistical coding and machine learning methods used in this study will be made available to the author upon reasonable request.Disclosure statementNo potential conflict of interest was reported by the authors.Additional informationFundingThis work was supported by the Applied Basic Research of Sichuan Department of Science and Technology (2021YJ0470), the Youth Innovation Project of Sichuan Medical Association (Q17025).