RESUMEN
This study addresses the potential of machine learning in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). Using an IRB-approved retrospective study of patients discussed at a multidisciplinary tumor board, clinical and imaging variables were extracted and used in a gradient-boosting machine learning algorithm, XGBoost. The algorithm's performance was assessed using confusion matrix metrics and the area under the Receiver Operating Characteristics (ROC) curve. The study included 140 patients (mean age 67.7 ± 8.9 years), and the algorithm was found to be predictive of all eight treatment recommendations made by the board. The model's predictions were more accurate than those based on published therapeutic guidelines by ESMO and NCCN. The study concludes that a machine learning model incorporating clinical and imaging variables can predict treatment recommendations made by an expert multidisciplinary tumor board, potentially aiding clinical decision-making in settings lacking subspecialty expertise.
RESUMEN
Systemically administered immunotherapies have revolutionized the care of patients with cancer; however, for many cancer types, most patients do not exhibit objective responses. Intratumoral immunotherapy is a burgeoning strategy that is designed to boost the effectiveness of cancer immunotherapies across the spectrum of malignancies. By locally administering immune-activating therapies into the tumor itself, immunosuppressive barriers in the tumor microenvironment can be broken. Moreover, therapies too potent for systemic delivery can be safely administered to target location to maximize efficacy and minimize toxicity. In order for these therapies to be effective, though, they must be effectively delivered into the target tumor lesion. In this review, we summarize the current landscape of intratumoral immunotherapies and highlight key concepts that influence intratumoral delivery, and by extension, efficacy. We also provide an overview of the breadth and depth of approved minimally invasive delivery devices that can be considered to improve delivery of intratumoral therapies.