Topiwala Raj, Patel Kanak, Twigg Joan, Rhule Jane, Meisenberg Barry
Department of Medicine, Anne Arundel Medical Center, Annapolis, MD.
Division of Infectious Diseases and Vaccinology, University of California Berkeley, Berkeley, CA.
Crit Care Explor. 2019 Sep 13;1(9):e0046. doi: 10.1097/CCE.0000000000000046. eCollection 2019 Sep.
To estimate performance characteristics and impact on care processes of a machine learning, early sepsis recognition tool embedded in the electronic medical record.
Retrospective review of electronic medical records and outcomes to determine sepsis prevalence among patients about whom a warning was received in real time and timing of that warning compared with clinician recognition of potential sepsis as determined by actions documented in the electronic medical record.
Acute care, nonteaching hospital.
Patients in the emergency department, observation unit, and adult inpatient care units who had sepsis diagnosed either by clinical codes or by Center for Medicare and Medicaid Services Severe Sepsis and Septic Shock: Management Bundle (SEP-1) criteria for severe sepsis and patients who had machine learning-generated advisories about a high risk of sepsis.
Noninterventional study.
Using two different definitions of sepsis as "true" sepsis, we measured the sensitivity and early warning clinical utility. Using coded sepsis to define true positives, we measured the positive predictive value of the early warnings. Sensitivity was 28.6% and 43.6% for coded sepsis and severe sepsis, respectively. The positive predictive value of an alert was 37.9% for coded sepsis. Clinical utility (true positive and earlier advisory than clinical recognition) was 2.2% and 1.6% for the two different definitions of sepsis. Use of the tool did not improve sepsis mortality rates.
Performance characteristics were different than previously described in this retrospective assessment of real-time warnings. Real-world testing of retrospectively validated models is essential. The early warning clinical utility may vary depending on a hospital's state of sepsis readiness and embrace of sepsis order bundles.
评估嵌入电子病历中的机器学习早期脓毒症识别工具的性能特征及其对护理流程的影响。
对电子病历和结果进行回顾性审查，以确定在实时收到警告的患者中脓毒症的患病率，并将该警告的时间与临床医生根据电子病历中记录的行动确定的潜在脓毒症识别时间进行比较。
急性护理非教学医院。
急诊科、观察病房和成人住院护理病房中通过临床编码或医疗保险和医疗补助服务中心严重脓毒症和脓毒性休克管理集束（SEP-1）标准诊断为脓毒症的患者，以及有机器学习生成的脓毒症高风险建议的患者。
非干预性研究。
使用两种不同的脓毒症定义作为“真正的”脓毒症，我们测量了敏感性和早期预警临床效用。使用编码脓毒症来定义真阳性，我们测量了早期预警的阳性预测值。编码脓毒症和严重脓毒症的敏感性分别为28.6%和43.6%。警报的阳性预测值对于编码脓毒症为37.9%。两种不同脓毒症定义的临床效用（真阳性且比临床识别更早发出建议）分别为2.2%和1.6%。使用该工具并未提高脓毒症死亡率。
在本次对实时警告的回顾性评估中，性能特征与先前描述的不同。对经回顾性验证的模型进行实际测试至关重要。早期预警临床效用可能因医院的脓毒症准备状态和对脓毒症医嘱集束的接受程度而异。
