Short-course radiotherapy followed by chemotherapy before total mesorectal excision (TME) versus preoperative chemoradiotherapy, TME, and optional adjuvant chemotherapy in locally advanced rectal cancer (RAPIDO) RAPIDO collaborative investigators; Bahadoer

A European Society for Medical Oncology (ESMO)-sponsored expert meeting was held in Paris on 8 March 2018 which comprised 11 experts from academia, 11 experts from the pharmaceutical industry and 2 clinicians who were representatives of ESMO. The focus of the meeting was exclusively on the intratumoral injection/delivery of immunostimulatory agents with the aim of harmonizing the standard terms and methodologies used in the reporting of human intratumoral immunotherapy (HIT-IT) clinical trials to ensure quality assurance and avoid a blurring of the data reported from different studies. The goal was to provide a reference document, endorsed by the panel members that could provide guidance to clinical investigators, pharmaceutical companies, ethics committees, independent review boards, patient advocates and the regulatory authorities and promote an increase in the number and quality of HIT-IT clinical trials in the future. Particular emphasis was placed not only on the development of precise definitions to facilitate a better understanding between investigators but also on the importance of systematic serial biopsies as a driver for translational research and the need for the recording and reporting of data, to facilitate a better understanding of the key processes involved.

Cox Proportional Hazards (CPH) analysis is the standard for survival analysis in oncology. Recently, several machine learning (ML) techniques have been adapted for this task. Although they have shown to yield results at least as good as classical methods, they are often disregarded because of their lack of transparency and little to no explainability, which are key for their adoption in clinical settings. In this paper, we used data from the Netherlands Cancer Registry of 36,658 non-metastatic breast cancer patients to compare the performance of CPH with ML techniques (Random Survival Forests, Survival Support Vector Machines, and Extreme Gradient Boosting [XGB]) in predicting survival using the $$c$$ c -index. We demonstrated that in our dataset, ML-based models can perform at least as good as the classical CPH regression ($$c$$ c -index $$\sim \,0.63$$ ∼ 0.63 ), and in the case of XGB even better ($$c$$ c -index $$\sim 0.73$$ ∼ 0.73 ). Furthermore, we used Shapley Additive Explanation (SHAP) values to explain the models’ predictions. We concluded that the difference in performance can be attributed to XGB’s ability to model nonlinearities and complex interactions. We also investigated the impact of specific features on the models’ predictions as well as their corresponding insights. Lastly, we showed that explainable ML can generate explicit knowledge of how models make their predictions, which is crucial in increasing the trust and adoption of innovative ML techniques in oncology and healthcare overall.

No abstract