Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925–0.953; ED: 0.938–0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.

脓毒症是全世界发病和死亡的主要原因。脓毒症的早期识别很重要，因为它可以及时进行可能挽救生命的复苏和抗菌治疗。我们提出了 COMPOSER（脓毒症风险的形式多维预测），这是一种用于早期预测脓毒症的深度学习模型，专门设计用于通过检测因错误数据、缺失、分布变化和数据漂移而引起的不熟悉的患者/情况来减少误报。 COMPOSER 将这些不熟悉的情况标记为不确定，而不是做出虚假的预测。从美国重症监护病房 (ICU) 和急诊科 (ED) 的两个医疗保健系统中筛选出的 6 个患者队列（515,720 名患者）用于训练并在外部和时间上验证该模型。在顺序预测设置中，COMPOSER 实现了持续较高的曲线下面积 (AUC)（ICU：0.925–0.953；ED：0.938–0.945）。在超过 600 万个预测窗口中，非脓毒症患者和脓毒症患者中分别约有 20% 和 8% 被确定为不确定。 COMPOSER 在临床上可操作的时间范围内（ICU：12.2 [3.2 22.8] 和 ED：在首次抗生素治疗前 2.1 [0.8 4.5] 小时）对所有六个队列提供了早期预警，从而可以识别脓毒症高风险患者并对其进行优先排序。