Machine Learning Algorithm to Estimate Distant Breast Cancer Recurrence at the Population Level with Administrative Data.

Purpose: High-quality population-based cancer recurrence data are scarcely available, mainly due to complexity and cost of registration. For the first time in Belgium, we developed a tool to estimate distant recurrence after a breast cancer diagnosis at the population level, based on real-world cancer registration and administrative data. Methods: Data on distant cancer recurrence (including progression) from patients diagnosed with breast cancer between 2009-2014 were collected from medical files at 9 Belgian centers to train, test and externally validate an algorithm (i.e., gold standard). Distant recurrence was defined as the occurrence of distant metastases between 120 days and within 10 years after the primary diagnosis, with follow-up until December 31, 2018. Data from the gold standard were linked to population-based data from the Belgian Cancer Registry (BCR) and administrative data sources. Potential features to detect recurrences in administrative data were defined based on expert opinion from breast oncologists, and subsequently selected using bootstrap aggregation. Based on the selected features, classification and regression tree (CART) analysis was performed to construct an algorithm for classifying patients as having a distant recurrence or not. Results: A total of 2507 patients were included of whom 216 had a distant recurrence in the clinical data set. The performance of the algorithm showed sensitivity of 79.5% (95% CI 68.8-87.8%), positive predictive value (PPV) of 79.5% (95% CI 68.8-87.8%), and accuracy of 96.7% (95% CI 95.4-97.7%). The external validation resulted in a sensitivity of 84.1% (95% CI 74.4-91.3%), PPV of 84.1% (95% CI 74.4-91.3%), and an accuracy of 96.8% (95% CI 95.4-97.9%). Conclusion: Our algorithm detected distant breast cancer recurrences with an overall good accuracy of 96.8% for patients with breast cancer, as observed in the first multi-centric external validation exercise.

Luminal Breast Cancer: Risk of Recurrence and Tumor-Associated Immune Suppression.

Hormone-receptor positive (HR+) breast cancer (BC) (including the luminal A and the luminal B subtypes) is the most common type of tumor in women diagnosed with early-stage BC (EBC). It represents a highly heterogeneous subgroup that is characterized by different risks of relapse. The aim of this review is to discuss the possible role played by the immune response in predicting this risk, along with the most common clinical and pathological factors and molecular tools that have been developed and are already in use. As opposed to what has previously been observed in the most aggressive human epidermal growth factor receptor 2 (HER2)-positive and triple-negative breast cancer (TNBC) subtypes, a high proportion of tumor-infiltrating lymphocytes (TILs)-reflecting a spontaneous and pre-existing immune response to the tumor-has been linked to a worse prognosis in HR+ EBC. This work provides some immune biological rationale explaining these findings and provides the basics to understand the principal clinical trials that are testing immunotherapy in HR+ (luminal) BC.

Immunohistochemical evaluation of potential molecular targets of desmoid-type fibromatosis.

Desmoid-type fibromatosis is locally aggressive tumor rare in general population, although commonly present in patients with familial adenomatous polyposis, significantly contributing to the morbidity and mortality of patients. To optimize and individualize the management of patients it is necessary to better understand the biology of these tumors. Immunohistochemical analysis of ß-catenin, VEGF, hormone receptors ERß, ERα and PR, COX-2, APC protein, EGFR, c-kit (CD117), bcl-2 and HER2 expression, potential therapeutic targets, was carried out on 15 archival biopsy samples together with APC gene mutational screening. ß-catenin expression was found in all samples, with over 73% showing high range positivity, however with no prognostic significance. Non-specific cytoplasmic localization of ß-catenin was observed FAP-associated cases lacking CTNNB1 mutations. Hormone receptor status demonstrated expression of ERß in 93% of lesions, without detectable ERα or PR. Distinct COX-2 expression of variable intensity was present in all but one desmoid-type fibromatosis case. All lesions demonstrated intense VEGF positivity. Immunoreactivity for the APC protein was found only in 4 cases associated with FAP. No EGFR, HER2, bcl-2 or c-kit expression was detected in any sample. Expression of ß-catenin, VEGF, ERß, COX-2 in high number of cases suggests a potential as future therapeutic targets in desmoid-type fibromatosis.

The Abscopal Effect in the Era of Cancer Immunotherapy: a Spontaneous Synergism Boosting Anti-tumor Immunity?

Radiotherapy is one of the main treatment strategies used in cancer. Aside from the local control of the disease, which is mediated by a direct cytotoxic effect on tumor cells, radiotherapy has also been shown to exert immune-mediated local and systemic effects. Radiotherapy can elicit anti-tumor responses in distant sites from the radiation field; this phenomenon is known as the abscopal effect and has been described in patients previously treated with immune checkpoint blockade (ICB). Considering that the efficacy of immunotherapy has been demonstrated only in a subset of patients-who often benefit with lasting responses-efforts are ongoing to potentiate its activity with the development of new combination strategies. Radiotherapy might represent a potential candidate for a synergistic combination with immunotherapy, by improving the immunogenicity of tumors and by enhancing local and systemic immune effects. This review aims to summarize the current pre-clinical and clinical data on the immune effects of radiotherapy and their potential implications for cancer immunotherapy.

Critical features and challenges associated with imaging in patients undergoing cancer immunotherapy.

Manipulating an individual's immune system through immune checkpoint blockade is revolutionizing the paradigms of cancer treatment. Peculiar patterns and kinetics of response have been observed with these new drugs, rendering the assessment of tumor burden particularly challenging in cancer immunotherapy. The mechanisms of action for immune checkpoint blockade, based upon engagement of the adaptive immune system, can generate unusual response patterns, including pseudoprogression, hyperprogression, atypical and delayed responses. In patients treated with immune checkpoint blockade and radiotherapy, a reduction in tumor burden at metastatic sites distant from the irradiation field (abscopal effect) has been observed, with synergistic systemic immune effects provoked by this combination. New toxicities have also been observed, due to excessive immune activity in several organs, including lung, colon, liver and endocrine glands. Efforts to standardize assessment of cancer immunotherapy responses include novel consensus guidelines derived by modifying World Health Organization (WHO) and Response Evaluation Criteria In Solid Tumors (RECIST) criteria. The aim of this review is to evaluate imaging techniques currently used routinely in the clinic and those being used as investigational tools in immunotherapy clinical trials.