Models for prediction of allogeneic hematopoietic stem transplantation (HSCT) related mortality partially account for transplant risk. Improving predictive accuracy requires understating of ...prediction limiting factors, such as the statistical methodology used, number and quality of features collected, or simply the population size. Using an in-silico approach (i.e., iterative computerized simulations), based on machine learning (ML) algorithms, we set out to analyze these factors. A cohort of 25,923 adult acute leukemia patients from the European Society for Blood and Marrow Transplantation (EBMT) registry was analyzed. Predictive objective was non-relapse mortality (NRM) 100 days following HSCT. Thousands of prediction models were developed under varying conditions: increasing sample size, specific subpopulations and an increasing number of variables, which were selected and ranked by separate feature selection algorithms. Depending on the algorithm, predictive performance plateaued on a population size of 6,611-8,814 patients, reaching a maximal area under the receiver operator characteristic curve (AUC) of 0.67. AUCs' of models developed on specific subpopulation ranged from 0.59 to 0.67 for patients in second complete remission and receiving reduced intensity conditioning, respectively. Only 3-5 variables were necessary to achieve near maximal AUCs. The top 3 ranking variables, shared by all algorithms were disease stage, donor type, and conditioning regimen. Our findings empirically demonstrate that with regards to NRM prediction, few variables "carry the weight" and that traditional HSCT data has been "worn out". "Breaking through" the predictive boundaries will likely require additional types of inputs.
•BRT for chemotherapy-refractory CNS lymphoma achieves rapid cytoreduction before CART.•CNS-BRT is associated with a favorable CNS response profile and CART–associated neurotoxicity profile.
Display ...omitted
Chimeric antigen receptor (CAR) T-cell therapy (CART) for central nervous system lymphoma (CNSL) is a promising strategy, yet responses are frequently not durable. Bridging radiotherapy (BRT) is used for extracranial lymphoma in which it can improve CART outcomes through cytoreduction of high-risk lesions. We hypothesized that BRT would achieve similar, significant cytoreduction before CART for CNSL (CNS-BRT). We identified patients with CNSL with non-Hodgkin B-cell lymphoma who received CNS-BRT before commercial CART. Cytoreduction from CNS-BRT was calculated as change in lesion size before CART. Twelve patients received CNS-BRT, and the median follow-up among survivors is 11.8 months (interquartile range, 8.5-21.9). Ten patients had CNSL (9 secondary, 1 primary) and 2 patients had epidural disease (evaluable for toxicity). All 10 patients with CNSL had progressive disease at the time of CNS-BRT. Of 12 patients, 1 experienced grade ≥3 cytokine release syndrome, and 3 of 12 patients experienced grade ≥3 immune effector cell–associated neurotoxicity syndrome. CNS-BRT achieved a 74.0% (95% confidence interval, 62.0-86.0) mean reduction in lesion size from baseline (P = .014) at a median of 12 days from BRT completion and before CART infusion. Best CNS response included 8 complete responses, 1 partial response, and 1 progressive disease. Three patients experienced CNS relapse outside the BRT field. Preliminary data suggest CNS-BRT achieves rapid cytoreduction and is associated with a favorable CNS response and safety profile. These data support further study of BRT as a bridging modality for CNSL CART.
Tumors initiate by mutations in cancer cells, and progress through interactions of the cancer cells with non-malignant cells of the tumor microenvironment. Major players in the tumor microenvironment ...are cancer-associated fibroblasts (CAFs), which support tumor malignancy, and comprise up to 90% of the tumor mass in pancreatic cancer. CAFs are transcriptionally rewired by cancer cells. Whether this rewiring is differentially affected by different mutations in cancer cells is largely unknown. Here we address this question by dissecting the stromal landscape of BRCA-mutated and BRCA Wild-type pancreatic ductal adenocarcinoma. We comprehensively analyze pancreatic cancer samples from 42 patients, revealing different CAF subtype compositions in germline BRCA-mutated vs. BRCA Wild-type tumors. In particular, we detect an increase in a subset of immune-regulatory clusterin-positive CAFs in BRCA-mutated tumors. Using cancer organoids and mouse models we show that this process is mediated through activation of heat-shock factor 1, the transcriptional regulator of clusterin. Our findings unravel a dimension of stromal heterogeneity influenced by germline mutations in cancer cells, with direct implications for clinical research.