Background: Lenvatinib and transarterial chemoembolization (TACE) are first-line treatments for unresectable hepatocellular carcinoma (HCC), but the objective response rate (ORR) is not satisfactory. We aimed to predict the response to lenvatinib combined with TACE before treatment for unresectable HCC using machine learning (ML) algorithms based on clinical data. Methods: Patients with unresectable HCC receiving the combination therapy of lenvatinib combined with TACE from two medical centers were retrospectively collected from January 2020 to December 2021. The response to the combination therapy was evaluated over the following 4–12 weeks. Five types of ML algorithms were applied to develop the predictive models, including classification and regression tree (CART), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The performance of the models was assessed by the receiver operating characteristic (ROC) curve and area under the receiver operating characteristic curve (AUC). The Shapley Additive exPlanation (SHAP) method was applied to explain the model. Results: A total of 125 unresectable HCC patients were included in the analysis after the inclusion and exclusion criteria, among which 42 (33.6%) patients showed progression disease (PD), 49 (39.2%) showed stable disease (SD), and 34 (27.2%) achieved partial response (PR). The nonresponse group (PD + SD) included 91 patients, while the response group (PR) included 34 patients. The top 40 most important features from all 64 clinical features were selected using the recursive feature elimination (RFE) algorithm to develop the predictive models. The predictive power was satisfactory, with AUCs of 0.74 to 0.91. The SVM model and RF model showed the highest accuracy (86.5%), and the RF model showed the largest AUC (0.91, 95% confidence interval (CI): 0.61–0.95). The SHAP summary plot and decision plot illustrated the impact of the top 40 features on the efficacy of the combination therapy, and the SHAP force plot successfully predicted the efficacy at the individualized level. Conclusions: A new predictive model based on clinical data was developed using ML algorithms, which showed favorable performance in predicting the response to lenvatinib combined with TACE for unresectable HCC. Combining ML with SHAP could provide an explicit explanation of the efficacy prediction.

No abstract

BackgroundSarcopenia has a remarkable negative impact on patients with liver diseases. We aimed to evaluate the impact of preoperative sarcopenia on the short-term outcomes after hepatectomy in patients with benign liver diseases.MethodsA total of 558 patients with benign liver diseases undergoing hepatectomy were prospectively reviewed. Both the muscle mass and strength were measured to define sarcopenia. Postoperative outcomes including complications, major complications and comprehensive complication index (CCI) were compared among four subgroups classified by muscle mass and strength. Predictors of complications, major complications and high CCI were identified by univariate and multivariate logistic regression analysis. Nomograms based on predictors were constructed and calibration cures were performed to verify the performance.Results120 patients were involved for analysis after exclusion. 33 patients were men (27.5%) and the median age was 54.0 years. The median grip strength was 26.5 kg and the median skeletal muscle index (SMI) was 44.4 cm2/m2. Forty-six patients (38.3%) had complications, 19 patients (15.8%) had major complications and 27 patients (22.5%) had a CCI ≥ 26.2. Age (p = 0.005), SMI (p = 0.005), grip strength (p = 0.018), surgical approach (p = 0.036), and operation time (p = 0.049) were predictors of overall complications. Child-Pugh score (p = 0.037), grip strength (p = 0.004) and surgical approach (p = 0.006) were predictors of major complications. SMI (p = 0.047), grip strength (p < 0.001) and surgical approach (p = 0.014) were predictors of high CCI. Among the four subgroups, patients with reduced muscle mass and strength showed the worst short-term outcomes. The nomograms for complications and major complications were validated by calibration curves and showed satisfactory performance.ConclusionSarcopenia has an adverse impact on the short-term outcomes after hepatectomy in patients with benign liver diseases and valuable sarcopenia-based nomograms were constructed to predict postoperative complications and major complications.