Predictive modeling for mortality risk in elderly patients with pulmonary embolism using machine learning algorithms

Abstract

Background Pulmonary Embolism (PE) is a condition that results in significant mortality and morbidity, particularly among the elderly. The aim of our study is to utilize machine learning (ML) algorithms specifically tailored for this population, thereby enhancing the accuracy of risk assessment. Methods Elderly patients with PE who were included between January 1, 2013, and December 31, 2023, were divided into two groups: training and validation sets. A total of five ML models, including decision tree, random forest (RF), extreme gradient boosting, support vector machine, and k-nearest neighbors, were developed to predict in-hospital mortality in these patients. The model demonstrating the best diagnostic performance was selected. Ultimately, the ML models were internally validated to assess their diagnostic performance using receiver operating characteristic analysis. Results The analysis included 250 patients, with 174 assigned to the training set and 76 to the validation set. The ML models were developed using nine clinical features: age, lactate levels, blood urea nitrogen, arterial oxygen partial pressure, red blood cell count, diastolic blood pressure, vasopressor use, acute kidney injury, and the requirement for continuous renal replacement therapy. Of the five evaluated ML models, the RF model demonstrated the best performance, attaining the highest area under the curve values of 0.950 for the training set and 0.835 for the validation set. Conclusion ML-based models exhibit strong predictive capabilities for identifying elderly patients with PE who are at risk of hospital mortality. These algorithms can aid physicians in the early detection of high-risk patients, facilitating timely and appropriate preventive interventions. Future prospective studies comparing ML models with established PE-specific risk stratification tools are warranted.