Ganesh Kumar Raut

Metastatic breast cancer is an intractable disease that responds poorly to immunotherapy. We show that p38MAPKα inhibition (p38i) limits tumor growth by reprogramming the metastatic tumor microenvironment in a CD4+ T cell-, IFNγ-, and macrophage-dependent manner. To identify targets that further increased p38i efficacy, we utilized a stromal labeling approach and single-cell RNA sequencing. Thus, we combined p38i and an OX40 agonist that synergistically reduced metastatic growth and increased overall survival. Intriguingly, patients with a p38i metastatic stromal signature had better overall survival that was further improved by the presence of an increased mutational load, leading us to ask if our approach would be effective in antigenic breast cancer. The combination of p38i, anti-OX40, and cytotoxic T-cell engagement cured mice of metastatic disease and produced long-term immunologic memory. Our findings demonstrate that a detailed understanding of the stromal compartment can be used to design effective antimetastatic therapies. SIGNIFICANCE: Immunotherapy is rarely effective in breast cancer. We dissected the metastatic tumor stroma, which revealed a novel therapeutic approach that targets the stromal p38MAPK pathway and creates an opportunity to unleash an immunologic response. Our work underscores the importance of understanding the tumor stromal compartment in therapeutic design. This article is highlighted in the In This Issue feature, p. 1275.

BACKGROUND AND AIM: We analyzed an inclusive gradient boosting model to predict hospital admission from the emergency department (ED) at different time points. We compared its results to multiple models built exclusively at each time point. METHODS: This retrospective multisite study utilized ED data from the Mount Sinai Health System, NY, during 2015-2019. Data included tabular clinical features and free-text triage notes represented using bag-of-words. A full gradient boosting model, trained on data available at different time points (30, 60, 90, 120, and 150 min), was compared to single models trained exclusively at data available at each time point. This was conducted by concatenating the rows of data available at each time point to one data matrix for the full model, where each row is considered a separate case. RESULTS: The cohort included 1,043,345 ED visits. The full model showed comparable results to the single models at all time points (AUCs 0.84-0.88 for different time points for both the full and single models). CONCLUSION: A full model trained on data concatenated from different time points showed similar results to single models trained at each time point. An ML-based prediction model can use used for identifying hospital admission.