Explainable Machine Learning for Estimating the Contrast Material Arrival Time in Computed Tomography Pulmonary Angiography.
Authors
Affiliations (6)
Affiliations (6)
- Department of Radiology, the Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi People's Hospital, Wuxi Medical Center, Nanjing Medical University.
- Department of Radiology, The Affiliated Changzhou No. 2 People's Hospital of Nanjing Medical University, Changzhou.
- Department of Radiology, Jiangnan University Medical Center, Wuxi.
- Department of Radiology, The Xuzhou Hospital Affiliated to Jiangsu University, Xuzhou.
- Department of Radiology, The Kunshan Affiliated Hospital of Jiangsu University, The First People's Hospital of Kunshan, Kunshan.
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China.
Abstract
To establish an explainable machine learning (ML) approach using patient-related and noncontrast chest CT-derived features to predict the contrast material arrival time (TARR) in CT pulmonary angiography (CTPA). This retrospective study included consecutive patients referred for CTPA between September 2023 to October 2024. Sixteen clinical and 17 chest CT-derived parameters were used as inputs for the ML approach, which employed recursive feature elimination for feature selection and XGBoost with SHapley Additive exPlanations (SHAP) for explainable modeling. The prediction target was abnormal TARR of the pulmonary artery (ie, TARR <7 seconds or >10 s), determined by the time to peak enhancement in the test bolus, with 2 models distinguishing these cases. External validation was conducted. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). A total of 666 patients (mean age, 70 [IQR, 59.3 to 78.0]; 46.8% female participants) were split into training (n = 353), testing (n = 151), and external validation (n = 162) sets. 86 cases (12.9%) had TARR <7 seconds, and 138 cases (20.7%) had TARR >10 seconds. The ML models exhibited good performance in their respective testing and external validation sets (AUC: 0.911 and 0.878 for TARR <7 s; 0.834 and 0.897 for TARR >10 s). SHAP analysis identified the measurements of the vena cava and pulmonary artery as key features for distinguishing abnormal TARR. The explainable ML algorithm accurately identified normal and abnormal TARR of the pulmonary artery, facilitating personalized CTPA scans.