Background and Objective: Machine learning (ML) models are increasingly being utilized in oncology research for use in the clinic. However, while more complicated models may provide improvements in predictive or prognostic power, a hurdle to their adoption are limits of model interpretability, wherein the inner workings can be perceived as a "black box". Explainable artificial intelligence (XAI) frameworks including Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) are novel, model-agnostic approaches that aim to provide insight into the inner workings of the "black box" by producing quantitative visualizations of how model predictions are calculated. In doing so, XAI can transform complicated ML models into easily understandable charts and interpretable sets of rules, which can give providers with an intuitive understanding of the knowledge generated, thus facilitating the deployment of such models in routine clinical workflows.Methods: We performed a comprehensive, non-systematic review of the latest literature to define use cases of model-agnostic XAI frameworks in oncologic research. The examined database was PubMed/MEDLINE.
Portal vein tumor thrombosis (PVTT) from cancer involving the liver carries a dismal prognosis, with median overall survival (OS) ranging from 2 to 5 months. While treatment with yttrium-90 ( 90 Y) radioembolization alone may improve outcomes, overall prognosis remains poor. We hypothesize that the combination of 90 Y radioembolization to the parenchymal component of the tumor and stereotactic body radiation therapy (SBRT) to the vascular component is a safe and effective means of improving outcomes. Materials and Methods: A single center retrospective review identified 12 patients with cancers involving the liver who received both 90 Y radioembolization and SBRT to the PVTT between May 2015 to August 2020. Primary endpoint was the 90-day toxicity rate by the Common Terminology Criteria for Adverse Events version 5.0. Secondary endpoints were the best response rate based on the Response Evaluation Criteria in Solid Tumors v1.1, local control rate, portal vein (PV) patency rate, and median OS. Results: Patients received a median 90 Y dose of 104.3 Gy (range, 83.3 to 131.7 Gy) and a median 5-fraction SBRT dose of 32.5 Gy (range, 27.5 to 50 Gy). There were no late toxicities reported, and only 7 acute grade 1 toxicities reported: elevation of liver function tests (17%), nausea (17%), fatigue (17%), and esophagitis (8%). Local control was 83%. 58% of patients had a patent PV after treatment. With a median follow-up time of 28 months, 1-year OS was 55% with a median OS of 14 months. Conclusion: Combination 90 Y radioembolization and SBRT appears to be safe and effective in the treatment of PVTT. Larger prospective studies are warranted to better evaluate this combination treatment approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.