RESUMEN
Objective:To explore the feasibility of a classification prediction model for gamma pass rates (GPRs) under different intensity-modulated radiation therapy techniques for pelvic tumors using a radiomics-based machine learning approach, and compare the classification performance of four integrated tree models.Methods:With a retrospective collection of 409 plans using different IMRT techniques, the three-dimensional dose validation results were adopted based on modality measurements, with a GPR criterion of 3%/2 mm and 10% dose threshold. Then prediction were built models by extracting radiomics features based on dose documentation. Four machine learning algorithms were used, namely random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM). Their classification performance was evaluated by calculating sensitivity, specificity, F1 score, and AUC value. Results:The RF, AdaBoost, XGBoost, and LightGBM models had sensitivities of 0.96, 0.82, 0.93, and 0.89, specificities of 0.38, 0.54, 0.62, and 0.62, F1 scores of 0.86, 0.81, 0.88, and 0.86, and AUC values of 0.81, 0.77, 0.85, and 0.83, respectively. XGBoost model showed the highest sensitivity, specificity, F1 score, and AUC value, outperforming the other three models. Conclusions:To build a GPR classification prediction model using a radiomics-based machine learning approach is feasible for plans using different intensity-modulated radiotherapy techniques for pelvic tumors, providing a basis for future multi-institutional collaborative research on GPR prediction.
RESUMEN
Objective:To investigate the efficacy and safety of different transcatheter arterial chemoembolization(TACE)-based regimens in patients with unresectable hepatocellular carcinoma(uHCC)and explore the optimal timing for combining TACE with tyrosine kinase inhibit-ors(TKIs)and immune checkpoint inhibitors(ICIs).Methods:A retrospective analysis was conducted on data from 555 patients with uHCC who underwent TACE-based treatment between April 2016 and December 2021 in Nanfang Hospital,Southern Medical University.The pa-tients were assigned into the following four groups according to different treatment regimens:TACE group(n=317),TACE combined with TKIs group(TACE+TKIs,n=66),TACE combined with ICIs group(TACE+ICIs,n=33),and TACE combined with TKIs+ICIs group(TACE+TKIs+ICIs,n=139).Subgroup analysis was performed within the TACE+TKIs+ICIs group,with patients being assigned into"pre-TACE"and"post-TACE"groups based on the timing of the combination therapy.Univariate and multivariate Cox regression analyses were conducted to identify pro-gnostic factors influencing overall survival(OS).Results:The TACE+TKIs+ICIs group showed the longest OS(21.9 months,95%confidence in-terval[CI]:17.2-26.6,P=0.030)and progression-free survival(PFS)(8.3 months,95%CI:7.3-9.3,P=0.004)compared to those in the other three groups.In the subgroup analysis,the"post-TACE"group had longer OS than the"pre-TACE"group(26.8 months vs.19.2 months,P = 0.011).The objective response rate(ORR)was 32.8%,41.1%,42.4%,and 52.5%(P=0.001)and the disease control rate(DCR)was 59.6%,71.2%,69.7%,and 82.7%(P<0.001)in the TACE,TACE+TKIs,TACE+ICIs,and TACE+TKIs+ICIs groups,respectively.The adverse events were similar to those reported in previous studies.Cox regression analysis revealed that tumor number,extrahepatic metastasis,and treatment regimen were independent factors influencing OS in patients(all P<0.05).Conclusions:TKIs or ICIs can improve OS and PFS in patients with uHCC receiving TACE,and the combination of TKIs+ICIs with TACE achieves better beneficial outcomes.The greatest OS was observed when the combination therapy TKIs+ICIs was initiated within 3 months after the first TACE procedure.