ABSTRACT
PURPOSE: This study evaluated the accuracy of the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) calculator in predicting outcomes after hepatectomy for colorectal cancer (CRC) liver metastasis in a Southeast Asian population. METHODS: Predicted and actual outcomes were compared for 166 patients undergoing hepatectomy for CRC liver metastasis identified between 2017 and 2022, using receiver operating characteristic curves with area under the curve (AUC) and Brier score. RESULTS: The ACS-NSQIP calculator accurately predicted most postoperative complications (AUC > 0.70), except for surgical site infection (AUC = 0.678, Brier score = 0.045). It also exhibited satisfactory performance for readmission (AUC = 0.818, Brier score = 0.011), reoperation (AUC = 0.945, Brier score = 0.002), and length of stay (LOS, AUC = 0.909). The predicted LOS was close to the actual LOS (5.9 vs. 5.0 days, P = 0.985). CONCLUSION: The ACS-NSQIP calculator demonstrated generally accurate predictions for 30-day postoperative outcomes after hepatectomy for CRC liver metastasis in our patient population.
Subject(s)
Colorectal Neoplasms , Hepatectomy , Liver Neoplasms , Postoperative Complications , Adult , Aged , Female , Humans , Male , Middle Aged , Asia, Southeastern , Colorectal Neoplasms/pathology , Colorectal Neoplasms/surgery , Length of Stay , Liver Neoplasms/surgery , Liver Neoplasms/secondary , Postoperative Complications/epidemiology , Retrospective Studies , Risk Assessment , Southeast Asian PeopleABSTRACT
This study aims to assess the quality and performance of predictive models for colorectal cancer liver metastasis (CRCLM). A systematic review was performed to identify relevant studies from various databases. Studies that described or validated predictive models for CRCLM were included. The methodological quality of the predictive models was assessed. Model performance was evaluated by the reported area under the receiver operating characteristic curve (AUC). Of the 117 articles screened, seven studies comprising 14 predictive models were included. The distribution of included predictive models was as follows: radiomics (n = 3), logistic regression (n = 3), Cox regression (n = 2), nomogram (n = 3), support vector machine (SVM, n = 2), random forest (n = 2), and convolutional neural network (CNN, n = 2). Age, sex, carcinoembryonic antigen, and tumor staging (T and N stage) were the most frequently used clinicopathological predictors for CRCLM. The mean AUCs ranged from 0.697 to 0.870, with 86% of the models demonstrating clear discriminative ability (AUC > 0.70). A hybrid approach combining clinical and radiomic features with SVM provided the best performance, achieving an AUC of 0.870. The overall risk of bias was identified as high in 71% of the included studies. This review highlights the potential of predictive modeling to accurately predict the occurrence of CRCLM. Integrating clinicopathological and radiomic features with machine learning algorithms demonstrates superior predictive capabilities.