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, identifying targeted treatments and optimal timing of interventions, and improving prognostication. Prior studies have described different sub-phenotypes of sepsis with 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 between the sub-phenotypes for clustering procedures. We develop a time-aware soft clustering algorithm guided by clinical context to identify sepsis sub-phenotypes using data from the EHR. 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. Our results suggest that these novel sepsis hybrid sub-phenotypes are promising to provide more precise information on the recovery trajectory which can be important to inform management decisions and sepsis prognosis.

翻译：脓毒症是医院中最危重的病症之一，具有高死亡率。该病由感染引起的免疫应答失调导致，可引发多器官功能障碍甚至死亡。由于脓毒症的病因、临床表现及康复轨迹存在显著差异，识别其亚表型对于深入理解脓毒症特征、确定靶向治疗及最佳干预时机、改善预后评估具有关键意义。已有研究基于器官特异性特征描述了不同脓毒症亚表型，这些研究通过将聚类算法应用于电子病历数据来识别疾病亚表型。然而，现有方法未能捕捉时序信息，且对亚表型间关系做出了不确定假设。本研究开发了临床情境引导的时序感知软聚类算法，利用电子病历数据识别脓毒症亚表型。我们识别出六种新型混合亚表型，并对其医学合理性进行了评估。此外，通过逻辑回归构建了脓毒症早期预警预测模型。研究结果表明，这些新型混合亚表型有望提供更具精准性的康复轨迹信息，对指导治疗决策和脓毒症预后评估具有重要价值。