Center for Innovation to Implementation, VA Palo Alto Health Care System, Menlo Park, California.
Department of Health Policy, Stanford University, Stanford, California.
JAMA Intern Med. 2024 May 1;184(5):557-562. doi: 10.1001/jamainternmed.2024.0084.
Inpatient clinical deterioration is associated with substantial morbidity and mortality but may be easily missed by clinicians. Early warning scores have been developed to alert clinicians to patients at high risk of clinical deterioration, but there is limited evidence for their effectiveness.
To evaluate the effectiveness of an artificial intelligence deterioration model-enabled intervention to reduce the risk of escalations in care among hospitalized patients using a study design that facilitates stronger causal inference.
DESIGN, SETTING, AND PARTICIPANTS: This cohort study used a regression discontinuity design that controlled for confounding and was based on Epic Deterioration Index (EDI; Epic Systems Corporation) prediction model scores. Compared with other observational research, the regression discontinuity design facilitates causal analysis. Hospitalized adults were included from 4 general internal medicine units in 1 academic hospital from January 17, 2021, through November 16, 2022.
An artificial intelligence deterioration model-enabled intervention, consisting of alerts based on an EDI score threshold with an associated collaborative workflow among nurses and physicians.
The primary outcome was escalations in care, including rapid response team activation, transfer to the intensive care unit, or cardiopulmonary arrest during hospitalization.
During the study, 9938 patients were admitted to 1 of the 4 units, with 963 patients (median [IQR] age, 76.1 [64.2-86.2] years; 498 males [52.3%]) included within the primary regression discontinuity analysis. The median (IQR) Elixhauser Comorbidity Index score in the primary analysis cohort was 10 (0-24). The intervention was associated with a -10.4-percentage point (95% CI, -20.1 to -0.8 percentage points; P = .03) absolute risk reduction in the primary outcome for patients at the EDI score threshold. There was no evidence of a discontinuity in measured confounders at the EDI score threshold.
Using a regression discontinuity design, this cohort study found that the implementation of an artificial intelligence deterioration model-enabled intervention was associated with a significantly decreased risk of escalations in care among inpatients. These results provide evidence for the effectiveness of this intervention and support its further expansion and testing in other care settings.
住院患者的临床恶化与大量发病率和死亡率有关，但临床医生可能很容易忽略。早期预警评分已被开发出来，以提醒临床医生注意有临床恶化高风险的患者，但它们的有效性证据有限。
使用一种有助于更强因果推理的研究设计，评估人工智能恶化模型支持的干预措施降低住院患者护理升级风险的效果。
设计、设置和参与者：这项队列研究使用回归不连续性设计，控制了混杂因素，并基于 Epic 恶化指数（EDI；Epic Systems Corporation）预测模型评分。与其他观察性研究相比，回归不连续性设计有助于进行因果分析。从 2021 年 1 月 17 日至 2022 年 11 月 16 日，在一家学术医院的 4 个普通内科单位纳入住院成年人。
人工智能恶化模型支持的干预措施，包括基于 EDI 分数阈值的警报，以及护士和医生之间的协作工作流程。
主要结果是护理升级，包括快速反应小组的激活、转至重症监护病房或住院期间心肺骤停。
在研究期间，有 9938 名患者入住了 4 个单位之一，其中 963 名患者（中位数[IQR]年龄，76.1[64.2-86.2]岁；498 名男性[52.3%]）被纳入主要回归不连续性分析。在主要分析队列中，Elixhauser 合并症指数得分的中位数（IQR）为 10（0-24）。对于处于 EDI 评分阈值的患者，干预措施与主要结局的绝对风险降低 10.4 个百分点（95%CI，-20.1 至-0.8 个百分点；P = .03）相关。在 EDI 评分阈值处没有证据表明存在测量混杂因素的不连续性。
使用回归不连续性设计，这项队列研究发现，实施人工智能恶化模型支持的干预措施与住院患者护理升级风险的显著降低相关。这些结果为该干预措施的有效性提供了证据，并支持其在其他护理环境中的进一步扩展和测试。
