OBJECTIVES Develop and implement a machine learning algorithm to predict severe sepsis and septic shock and evaluate the impact on clinical practice and patient outcomes. DESIGN Retrospective cohort for algorithm derivation and validation, pre-post impact evaluation. SETTING Tertiary teaching hospital system in Philadelphia, PA. PATIENTS All non-ICU admissions; algorithm derivation July 2011 to June 2014 (n = 162,212); algorithm validation October to December 2015 (n = 10,448); silent versus alert comparison January 2016 to February 2017 (silent n = 22,280; alert n = 32,184). INTERVENTIONS A random-forest classifier, derived and validated using electronic health record data, was deployed both silently and later with an alert to notify clinical teams of sepsis prediction. MEASUREMENT AND MAIN RESULT Patients identified for training the algorithm were required to have International Classification of Diseases, 9th Edition codes for severe sepsis or septic shock and a positive blood culture during their hospital encounter with either a lactate greater than 2.2 mmol/L or a systolic blood pressure less than 90 mm Hg. The algorithm demonstrated a sensitivity of 26% and specificity of 98%, with a positive predictive value of 29% and positive likelihood ratio of 13. The alert resulted in a small statistically significant increase in lactate testing and IV fluid administration. There was no significant difference in mortality, discharge disposition, or transfer to ICU, although there was a reduction in time-to-ICU transfer. CONCLUSIONS Our machine learning algorithm can predict, with low sensitivity but high specificity, the impending occurrence of severe sepsis and septic shock. Algorithm-generated predictive alerts modestly impacted clinical measures. Next steps include describing clinical perception of this tool and optimizing algorithm design and delivery.

中文翻译：

---

一种预测严重脓毒症和脓毒性休克的机器学习算法：开发、实施和对临床实践的影响。

目标 开发和实施机器学习算法来预测严重脓毒症和脓毒性休克，并评估对临床实践和患者结果的影响。设计 用于算法推导和验证、事后影响评估的回顾性队列。设置宾夕法尼亚州费城的三级教学医院系统。患者 所有非 ICU 入院；2011 年 7 月至 2014 年 6 月的算法推导（n = 162,212）；算法验证 2015 年 10 月至 12 月（n = 10,448）；2016 年 1 月至 2017 年 2 月的沉默与警报比较（沉默 n = 22,280；警报 n = 32,184）。干预 使用电子健康记录数据派生和验证的随机森林分类器被静默部署，随后通过警报通知临床团队败血症预测。测量和主要结果 确定用于训练算法的患者需要具有国际疾病分类第 9 版严重脓毒症或感染性休克代码，并且在医院遇到乳酸大于 2.2 mmol/L 或收缩压升高时血培养呈阳性。血压低于 90 毫米汞柱。该算法的敏感性为 26%，特异性为 98%，阳性预测值为 29%，阳性似然比为 13。警报导致乳酸检测和静脉输液的小幅统计学显着增加。尽管转入 ICU 的时间有所减少，但在死亡率、出院处置或转入 ICU 方面没有显着差异。结论 我们的机器学习算法可以预测，灵敏度低但特异性高，即将发生的严重败血症和败血性休克。算法生成的预测警报对临床措施的影响不大。接下来的步骤包括描述该工具的临床感知以及优化算法设计和交付。