Interpretable Machine Learning Approach for Predicting 30-Day Mortality of Critical Ill Patients with Pulmonary Embolism and Heart Failure: A Retrospective Study
Authors:
Open Access
- 1 January 2024
- journal article
- research article
- Published by SAGE Publications in Clinical and Applied Thrombosis/Hemostasis
- Vol. 30
Abstract
Background: Pulmonary embolism (PE) patients combined with heart failure (HF) have been reported to have a high short-term mortality. However, few studies have developed predictive tools of 30-day mortality for these patients in intensive care unit (ICU). This study aimed to construct and validate a machine learning (ML) model to predict 30-day mortality for PE patients combined with HF in ICU. Methods: We enrolled patients with PE combined with HF in the Medical Information Mart for Intensive Care Database (MIMIC) and developed six ML models after feature selection. Further, eICU Collaborative Research Database (eICU-CRD) was utilized for external vali- dation. The area under curves (AUC), calibration curves, decision curve analysis (DCA), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were performed to evaluate the prediction performance. Shapley additive explanation (SHAP) was performed to enhance the interpretability of our models. Results: A total of 472 PE patients combined with HF were included. We developed six ML models by the 13 selected features. After internal validation, the Support Vector Ma- chine (SVM) model performed best with an AUC of 0.835, a superior calibration degree, and a wider risk threshold (from 0% to 90%) for obtaining clinical benefit, which also outperformed traditional mortality risk evaluation systems,as evaluated by NRI and IDI. The SVM model was still reliable after external validation. SHAP was performed to explain the model. Moreover, an online application was developed for further clinical use. Conclusion: This study developed a potential tool for identify short-term mortality risk to guide clinical decision making for PE patients combined with HF in the ICU. The SHAP method also helped clinicians to better understand the model.Keywords
Funding Information
- Foundation of Hebei Provincial Department of Science and Technology (223777114D)
This publication has 50 references indexed in Scilit:
- In-Hospital Mortality Benefit of Inferior Vena Cava Filters in Patients With Pulmonary Embolism and Congestive Heart FailureAmerican Journal of Roentgenology, 2018
- Peripheral artery disease and risk of adverse outcomes in heart failure with preserved ejection fractionClinical Cardiology, 2017
- Impact of Peripheral Artery Disease on Prognosis in Hospitalized Heart Failure PatientsCirculation Journal, 2015
- White blood cell count and mortality in patients with acute pulmonary embolismAmerican Journal of Hematology, 2013
- In-hospital mortality for pulmonary embolism: relationship with chronic kidney disease and end-stage renal disease. The hospital admission and discharge database of the Emilia Romagna region of ItalyInternal and Emergency Medicine, 2012
- Association between the Pulmonary Embolism Severity Index (PESI) and short-term clinical deteriorationThrombosis and Haemostasis, 2011
- Role of inflammation in right ventricular damage and repair following experimental pulmonary embolism in ratsInternational Journal of Experimental Pathology, 2008
- Pulmonary embolism causes endomyocarditis in the human heartHeart, 2007
- Derivation and Validation of a Prognostic Model for Pulmonary EmbolismAmerican Journal of Respiratory and Critical Care Medicine, 2005
- Incidence and Clinical Predictors of Pulmonary Embolism in Severe Heart Failure Patients Admitted to a Coronary Care UnitChest, 2005