Soft phenotyping for sepsis via EHR time-aware soft clustering.

OBJECTIVE: Sepsis is one of the most serious hospital conditions associated with high mortality. Sepsis is the result of a dysregulated immune response to infection that can lead to multiple organ dysfunction and death. Due to the wide variability in the causes of sepsis, clinical presentation, and the recovery trajectories, identifying sepsis sub-phenotypes is crucial to advance our understanding of sepsis characterization, to choose targeted treatments and optimal timing of interventions, and to improve prognostication. Prior studies have described different sub-phenotypes of sepsis using organ-specific characteristics. These studies applied clustering algorithms to electronic health records (EHRs) to identify disease sub-phenotypes. However, prior approaches did not capture temporal information and made uncertain assumptions about the relationships among the sub-phenotypes for clustering procedures. METHODS: We developed a time-aware soft clustering algorithm guided by clinical variables to identify sepsis sub-phenotypes using data available in the EHR. RESULTS: We identified six novel sepsis hybrid sub-phenotypes and evaluated them for medical plausibility. In addition, we built an early-warning sepsis prediction model using logistic regression. CONCLUSION: Our results suggest that these novel sepsis hybrid sub-phenotypes are promising to provide more accurate information on sepsis-related organ dysfunction and sepsis recovery trajectories which can be important to inform management decisions and sepsis prognosis.

The prognostic implications and tumor-suppressive functions of CYR61 in estrogen receptor-positive breast cancer.

Due to the therapeutic resistance of endocrine therapy and the limited efficacy of immune checkpoint inhibitors in estrogen receptor (ER)-positive breast cancer (BRCA), there is an urgent need to develop novel prognostic markers and understand the regulation of the tumor immune microenvironment (TIME). As a matricellular protein, CYR61 has been shown to either promote or suppress cancer progression depending on cancer types. However, how CYR61 functions in ER-positive BRCA remains elusive. In this study, we comprehensively analyzed the expression of CYR61 in BRCA based on the TCGA and METABRIC databases. Our findings showed that the expression of CYR61 is downregulated in different subtypes of BRCA, which is associated with elevated promoter methylation levels and predicts bad clinical outcomes. By comparing the high or low CYR61 expression groups of ER-positive BRCA patients, we found that CYR61 is intimately linked to the expression of genes involved in tumor-suppressive pathways, such as the TGF-ß and TNF signaling pathways, and genes related to cytokine-receptor interaction that may regulate cancer immunity. Moreover, reduced CYR61 expression is associated with an altered TIME that favors cancer progression. Finally, experimental analyses ascertained that CYR61 is downregulated in clinical BRCA tissues compared to matched normal breast tissues. Furthermore, CYR61 is able to impede the proliferation and colony formation of ER-positive BRCA cells. In summary, our study reveals that CYR61 could serve as a novel prognostic marker for ER-positive BRCA, and function as an inhibitor of cancer progression by both acting on cancer cells and remodeling the TIME.