Exploring Mortality and Prognostic Factors of Heart Failure with In-Hospital and Emergency Patients by Electronic Medical Records: A Machine Learning Approach

Cheng-Sheng Yu,1– 4,&ast; Jenny L Wu,5,&ast; Chun-Ming Shih,6– 8 Kuan-Lin Chiu,9 Yu-Da Chen,9,10 Tzu-Hao Chang5,11 1Graduate Institute of Data Science, College of Management, Taipei Medical University, New Taipei City, 235603, Taiwan; 2Clinical Data Center, Office of Data Science, Taipei Medical University, New Taipei City, 235603, Taiwan; 3Fintech Innovation Center, Nan Shan Life Insurance Co., Ltd., Taipei, 11049, Taiwan; 4Beyond Lab, Nan Shan Life Insurance Co., Ltd., Taipei, 11049, Taiwan; 5Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, New Taipei City, 235603, Taiwan; 6Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei, 11031, Taiwan; 7Cardiovascular Research Center, Taipei Medical University Hospital, Taipei, 11031, Taiwan; 8Taipei Heart Institute, Taipei Medical University, Taipei, 11031, Taiwan; 9Department of Family Medicine, Taipei Medical University Hospital, Taipei, 11031, Taiwan; 10School of Medicine, College of Medicine, Taipei Medical University, Taipei, 11031, Taiwan; 11Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei, 11031, Taiwan&ast;These authors contributed equally to this workCorrespondence: Tzu-Hao Chang; Yu-Da Chen, Email [email protected]; [email protected]: As HF progresses into advanced HF, patients experience a poor quality of life, distressing symptoms, intensive care use, social distress, and eventual hospital death. We aimed to investigate the relationship between morality and potential prognostic factors among in-patient and emergency patients with HF.Patients and Methods: A case series study: Data are collected from in-hospital and emergency care patients from 2014 to 2021, including their international classification of disease at admission, and laboratory data such as blood count, liver and renal functions, lipid profile, and other biochemistry from the hospital’s electrical medical records. After a series of data pre-processing in the electronic medical record system, several machine learning models were used to evaluate predictions of HF mortality. The outcomes of those potential risk factors were visualized by different statistical analyses.Results: In total, 3871 hF patients were enrolled. Logistic regression showed that intensive care unit (ICU) history within 1 week (OR: 9.765, 95% CI: 6.65, 14.34; p-value < 0.001) and prothrombin time (OR: 1.193, 95% CI: 1.098, 1.296; < 0.001) were associated with mortality. Similar results were obtained when we analyzed the data using Cox regression instead of logistic regression. Random forest, support vector machine (SVM), Adaboost, and logistic regression had better overall performances with areas under the receiver operating characteristic curve (AUROCs) of > 0.87. Naïve Bayes was the best in terms of both specificity and precision. With ensemble learning, age, ICU history within 1 week, and respiratory rate (BF) were the top three compelling risk factors affecting mortality due to HF. To improve the explainability of the AI models, Shapley Additive Explanations methods were also conducted.Conclusion: Exploring HF mortality and its patterns related to clinical risk factors by machine learning models can help physicians make appropriate decisions when monitoring HF patients’ health quality in the hospital.Keywords: mortality, risk factor, cardiovascular disease, multivariate statistical analysis, machine learning, artificial intelligence