有和无人工智能的早期预警评分比较
该回顾性队列研究在耶鲁纽黑文健康系统7家医院纳入2019年3月9日至2023年11月9日全部连续成人内外科病房住院 encounters,共362,926例,比较3种专有人工智能早期预警评分(EDI、RI、eCARTv5)与3种公开简单加权评分(MEWS、NEWS、NEWS2)对临床恶化的预测性能。主要终点为病房转入ICU或观察后24小时内死亡,共16,693例(4.6%)发生恶化事件。eCART的AUC最高为0.895,其后依次为NEWS2 0.831、NEWS 0.829、RI 0.828、EDI 0.808、MEWS 0.757;在匹配NEWS=5的中危敏感度水平,PPV从EDI 41分的6.3%到eCART 94分的17.3%;匹配NEWS=7的高危特异度水平,PPV从EDI 54分的14.5%到eCART 97分的23.3%。中危阈值所有评分均提供至少20小时中位提前预警时间。
要点
- 在362,926例成人内外科病房住院中,eCART的AUC最高为0.895(95%CI 0.891-0.900),优于NEWS2 0.831、NEWS 0.829、RI 0.828、EDI 0.808和MEWS 0.757。
- 匹配NEWS=5的中危敏感度水平,PPV从EDI 41分的6.3%(95%CI 6.1%-6.4%)到eCART 94分的17.3%(95%CI 16.9%-17.8%)。
- 匹配NEWS=7的高危特异度水平,PPV从EDI 54分的14.5%(95%CI 14.0%-15.2%)到eCART 97分的23.3%(95%CI 22.7%-24.2%)。
- 中危阈值下所有评分的中位提前预警时间至少20小时;高危阈值下eCART中位提前11小时(IQR 0-69),NEWS 8小时(IQR 0-63),EDI仅1小时(IQR 0-39)。
- 非AI公开评分NEWS显著优于AI评分EDI;作者认为鉴于准确性差异大,可能需要对早期预警工具增加透明度和监管。
适用人群与场景
- 2019年3月9日至2023年11月9日在耶鲁纽黑文健康系统7家医院连续纳入的全部成人内外科病房住院患者,共362,926例住院 encounters,中位年龄64岁(IQR 47-77),女性200,642例(55.3%)。
诊断标准与关键阈值
- 临床恶化定义为从病房转入重症监护室或观察后24小时内死亡。
- 中危敏感度水平以NEWS评分5分匹配;高危特异度水平以NEWS评分7分匹配。
研究设计与关键结果
- 回顾性队列研究,7家医院,362,926例成人内外科病房住院,16,693例(4.6%)发生临床恶化事件。
- eCART的AUC最高为0.895(95%CI 0.891-0.900),其后为NEWS2 0.831(95%CI 0.826-0.836)、NEWS 0.829(95%CI 0.824-0.835)、RI 0.828(95%CI 0.823-0.834)、EDI 0.808(95%CI 0.802-0.812)、MEWS 0.757(95%CI 0.750-0.764)。
- 匹配NEWS=5的中危敏感度水平,总体PPV从EDI评分41分的6.3%(95%CI 6.1%-6.4%)到eCART评分94分的17.3%(95%CI 16.9%-17.8%)。
- 匹配NEWS=7的高危特异度水平,总体PPV从EDI评分54分的14.5%(95%CI 14.0%-15.2%)到eCART评分97分的23.3%(95%CI 22.7%-24.2%)。
- 中危阈值下所有评分提供至少20小时的中位提前预警时间。
- 高危阈值下中位提前预警时间:eCART 11小时(IQR 0-69),NEWS 8小时(IQR 0-63),NEWS2 6小时(IQR 0-62),MEWS 5小时(IQR 0-56),EDI 1小时(IQR 0-39),RI 0小时(IQR 0-42)。
证据类型、等级与局限
- 证据类型:回顾性队列研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,鉴于各早期预警工具准确性差异大,可能需要对早期预警工具增加透明度和监管。
- 原文未据此给出其他推荐。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
IMPORTANCE: Early warning decision support tools to identify clinical deterioration in the hospital are widely used, but there is little information on their comparative performance.
OBJECTIVE: To compare 3 proprietary artificial intelligence (AI) early warning scores and 3 publicly available simple aggregated weighted scores.
DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study was performed at 7 hospitals in the Yale New Haven Health System. All consecutive adult medical-surgical ward hospital encounters between March 9, 2019, and November 9, 2023, were included.
EXPOSURES: Simultaneous Epic Deterioration Index (EDI), Rothman Index (RI), eCARTv5 (eCART), Modified Early Warning Score (MEWS), National Early Warning Score (NEWS), and NEWS2 scores.
MAIN OUTCOMES AND MEASURES: Clinical deterioration, defined as a transfer from ward to intensive care unit or death within 24 hours of an observation.
RESULTS: Of the 362 926 patient encounters (median patient age, 64 [IQR, 47-77] years; 200 642 [55.3%] female), 16 693 (4.6%) experienced a clinical deterioration event. eCART had the highest area under the receiver operating characteristic curve at 0.895 (95% CI, 0.891-0.900), followed by NEWS2 at 0.831 (95% CI, 0.826-0.836), NEWS at 0.829 (95% CI, 0.824-0.835), RI at 0.828 (95% CI, 0.823-0.834), EDI at 0.808 (95% CI, 0.802-0.812), and MEWS at 0.757 (95% CI, 0.750-0.764). After matching scores at the moderate-risk sensitivity level for a NEWS score of 5, overall positive predictive values (PPVs) ranged from a low of 6.3% (95% CI, 6.1%-6.4%) for an EDI score of 41 to a high of 17.3% (95% CI, 16.9%-17.8%) for an eCART score of 94. Matching scores at the high-risk specificity of a NEWS score of 7 yielded overall PPVs ranging from a low of 14.5% (95% CI, 14.0%-15.2%) for an EDI score of 54 to a high of 23.3% (95% CI, 22.7%-24.2%) for an eCART score of 97. The moderate-risk thresholds provided a median of at least 20 hours of lead time for all the scores. Median lead time at the high-risk threshold was 11 (IQR, 0-69) hours for eCART, 8 (IQR, 0-63) hours for NEWS, 6 (IQR, 0-62) hours for NEWS2, 5 (IQR, 0-56) hours for MEWS, 1 (IQR, 0-39) hour for EDI, and 0 (IQR, 0-42) hours for RI.
CONCLUSIONS AND RELEVANCE: In this cohort study of inpatient encounters, eCART outperformed the other AI and non-AI scores, identifying more deteriorating patients with fewer false alarms and sufficient time to intervene. NEWS, a non-AI, publicly available early warning score, significantly outperformed EDI. Given the wide variation in accuracy, additional transparency and oversight of early warning tools may be warranted.
参考来源
- Edelson DP, Churpek MM, Carey KA, et al. Early Warning Scores With and Without Artificial Intelligence. JAMA Netw Open. 2024. PMID: 39405061. doi:10.1001/jamanetworkopen.2024.38986
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。