Machine Learning-Based Prediction of Pulmonary Embolism to Reduce Unnecessary Computed Tomography Scans in Gastrointestinal Cancer Patients: A Retrospective Multicenter Study

Abstract

Abstract Background Pulmonary embolism (PE) is one of the most important complications in cancer patients. Gastrointestinal cancers entail an increased risk of PE. However, there were few researches on predicting pulmonary embolism using machine learning (ML) in cancer patients. The purpose of this study was to develop an ML based prediction model for PE in gastrointestinal cancer patients. Methods We conducted a retrospective, multicenter study in which ML model was developed and subsequently internally and externally validated. We reviewed gastrointestinal cancer patients who had undergone computed tomographic pulmonary angiography (CTPA) from 2010 to 2020. Demographic and predictor variables including the Wells score and D-dimer were investigated. The ML model was based on the random forest model. The area under receiver operating curve (AUROC) was used to evaluate the performance of ML model. Results 446 patients in hospital A and 139 patients in hospital B were analyzed in this study. The training set comprised 356 patients in hospital A. The ML model was validated both internally (90 patients) and externally (139 patients). AUROC was 0.736 in hospital A and 0.669 in hospital B. The number of patients classified as requiring CTPA was significantly reduced according to the prediction with ML (hospital A; 100.0% vs 91.1%, P < 0.001, hospital B; 100.0% vs. 93.5%, P = 0.003). Conclusion Prediction model based on ML might have advantages in reducing the number of CTPA compared to the conventional diagnostic strategy for PE in patients with gastrointestinal cancer.