Machine-learning prediction of treatment response to stereotactic body radiation therapy in oligometastatic gynecological cancer: A multi-institutional study.

BACKGROUND AND PURPOSE: We aimed to develop and validate different machine-learning (ML) prediction models for the complete response of oligometastatic gynecological cancer after SBRT. MATERIAL AND METHODS: One hundred fifty-seven patients with 272 lesions from 14 different institutions and treated with SBRT with radical intent were included. Thirteen datasets including 222 lesions were combined for model training and internal validation purposes, with an 80:20 ratio. The external testing dataset was selected as the fourteenth Institution with 50 lesions. Lesions that achieved complete response (CR) were defined as responders. Prognostic clinical and dosimetric variables were selected using the LASSO algorithm. Six supervised ML models, including logistic regression (LR), classification and regression tree analysis (CART) and support vector machine (SVM) using four different kernels, were trained and tested to predict the complete response of uterine lesions after SBRT. The performance of models was assessed by receiver operating characteristic curves (ROC), area under the curve (AUC) and calibration curves. An explainable approach based on SHapley Additive exPlanations (SHAP) method was deployed to generate individual explanations of the model's decisions. RESULTS: 63.6% of lesions had a complete response and were used as ground truth for the supervised models. LASSO strongly associated complete response with three variables, namely the lesion volume (PTV), the type of lesions (lymph-nodal versus parenchymal), and the biological effective dose (BED10), that were used as input for ML modeling. In the training set, the AUCs for complete response were 0.751 (95% CI: 0.716-0.786), 0.766 (95% CI: 0.729-0.802) and 0.800 (95% CI: 0.742-0.857) for the LR, CART and SVM with a radial basis function kernel, respectively. These models achieve AUC values of 0.727 (95% CI: 0.669-0.795), 0.734 (95% CI: 0.649-0.815) and 0.771 (95% CI: 0.717-0.824) in the external testing set, demonstrating excellent generalizability. CONCLUSION: ML models enable a reliable prediction of the treatment response of oligometastatic lesions receiving SBRT. This approach may assist radiation oncologists to tailor more individualized treatment plans for oligometastatic patients.

BRIDGE -1 TRIAL: BReak Interval Delayed surgery for Gastrointestinal Extraperitoneal rectal cancer, a multicentric phase III randomized trial.

Design: Neoadjuvant chemoradiotherapy (nCRT) followed by surgery is the standard of care for locally advanced rectal cancer (LARC).Several studies have shown a correlation between a longer interval between the end of nCRT and surgery (surgical interval - SI) and an increased pathological complete response (pCR) rate, with a maximum obtained between 10 and 13 weeks.The primary endpoint of this multicenter, 2-arm randomised trial is to investigate SI lengthening, evaluating the difference in terms of complete response (CR) and Tumor Regression Grade (TRG)1 rate in the two arms. Secondly, the impact of SI lengthening on survival outcomes and quality of life (QoL) will be investigated. Methods: Intermediate-risk LARC patients undergoing nCRT will be prospectively included in the study. nCRT will be administered with a total dose of 55 Gy in 25 fractions on Gross Tumor Volume (GTV) plus the corresponding mesorectum of 45 Gy in 25 fractions on the whole pelvis. Chemotherapy with oral capecitabine will be administered continuously.The patients achieving a clinical major or complete response assessed at clinical-instrumental re-evaluation at 7-8 weeks after treatment completion, will be randomized into two groups, to undergo surgery or local excision at 9-11 weeks (control arm) or at 13-16 weeks (experimental arm). Pathological response will be assessed on the surgical specimen using the AJCC TNM v.7 and the TRG according to Mandard. Patients will be followed up to evaluate toxicity and QoL.The promoter center of the trial will conduct the randomization process through an automated procedure to prevent any possible bias.For sample size calculation, using CR difference of 20% as endpoint, 74 patients per arm will be enrolled. Conclusions: The results of this study may prospectively provide a new time frame for the clinical re-evaluation for complete/major responders patients in order to increase the CR rate to nCRT.Trial registration:ClinicalTrials.gov Identifier: NCT03581344.