Postoperative venous thromboembolism(VTE)in colorectal cancer(CRC)patients undergoing surgery results in poor prognosis.However,there are no effective tools for early screening and predicting VTE.In this study,we deve...Postoperative venous thromboembolism(VTE)in colorectal cancer(CRC)patients undergoing surgery results in poor prognosis.However,there are no effective tools for early screening and predicting VTE.In this study,we developed a machine learning(ML)-based model for predicting the risk of VTE following CRC surgery and tested its performance using an external dataset.A total of 3227 CRC surgery patients were enrolled from the Affiliated Hospital of Qingdao University and Yantai Yuhuangding Hospital(from January 2016 to December 2023).Subsequently,1596 patients from the Affiliated Hospital of Qingdao University were assigned to the training set,and 716 patients from Yantai Yuhuangding Hospital were assigned to the external validation set.A model was developed and trained using six ML algorithms using the stacking ensemble technique.Moreover,all models were developed using the tenfold cross-validation on the training set,and their performance was tested using an independent external validation set.In the training set,173(10.8%)patients developed VTE,163(10.2%)patients experienced deep venous thrombosis,and 29(1.82%)cases had pulmonary embolism(PE).In the external validation set,85(11.9%)cases of VTE,83(11.6%)cases of deep vein thrombosis,and 14(1.96%)cases of PE were recorded.The analysis revealed that the stacking model outperformed all other models in the external validation set,achieving significantly better performance in all metrics:the area under the receiver operating characteristic curve=0.840(0.790–0.887),accuracy=0.810(0.783–0.836),specificity=0.819(0.790–0.848),sensitivity=0.741(0.652–0.825),and recall=0.959(0.942–0.975).The stacking model for surgical CRC patients shows promise in enabling timely clinical detection of high-risk cases.This method facilitates the prioritized implementation of prophylactic anticoagulation in confirmed high-risk individuals,thereby mitigating unnecessary pharmacological intervention in low-risk populations.展开更多
文摘Postoperative venous thromboembolism(VTE)in colorectal cancer(CRC)patients undergoing surgery results in poor prognosis.However,there are no effective tools for early screening and predicting VTE.In this study,we developed a machine learning(ML)-based model for predicting the risk of VTE following CRC surgery and tested its performance using an external dataset.A total of 3227 CRC surgery patients were enrolled from the Affiliated Hospital of Qingdao University and Yantai Yuhuangding Hospital(from January 2016 to December 2023).Subsequently,1596 patients from the Affiliated Hospital of Qingdao University were assigned to the training set,and 716 patients from Yantai Yuhuangding Hospital were assigned to the external validation set.A model was developed and trained using six ML algorithms using the stacking ensemble technique.Moreover,all models were developed using the tenfold cross-validation on the training set,and their performance was tested using an independent external validation set.In the training set,173(10.8%)patients developed VTE,163(10.2%)patients experienced deep venous thrombosis,and 29(1.82%)cases had pulmonary embolism(PE).In the external validation set,85(11.9%)cases of VTE,83(11.6%)cases of deep vein thrombosis,and 14(1.96%)cases of PE were recorded.The analysis revealed that the stacking model outperformed all other models in the external validation set,achieving significantly better performance in all metrics:the area under the receiver operating characteristic curve=0.840(0.790–0.887),accuracy=0.810(0.783–0.836),specificity=0.819(0.790–0.848),sensitivity=0.741(0.652–0.825),and recall=0.959(0.942–0.975).The stacking model for surgical CRC patients shows promise in enabling timely clinical detection of high-risk cases.This method facilitates the prioritized implementation of prophylactic anticoagulation in confirmed high-risk individuals,thereby mitigating unnecessary pharmacological intervention in low-risk populations.
