机器学习算法联合生物标志物鉴别1型与2型心肌梗死
本研究为CMR-IMPACT多中心前瞻性试验的二次分析,纳入123例经专家裁定为心肌梗死且初始高敏肌钙蛋白I(hs-cTnI)可测的成人急性冠脉综合征症状患者。基于初始hs-cTnI的MI3机器学习算法鉴别1型与2型心肌梗死的AUC为0.704(95%CI 0.611-0.797),联合NT-proBNP和Gal-3后AUC提升至0.789(95%CI 0.709-0.869,p=0.0165)。在86例有连续hs-cTnI的患者中,AUC由0.721(95%CI 0.614-0.829)升至0.797(95%CI 0.700-0.894,p=0.09)。作者认为联合生物标志物模型在鉴别1型与2型心肌梗死方面显示出前景。
要点
- 在123例裁定为心肌梗死的患者中,1型占58.5%(72/123),2型占41.5%(51/123)。
- 基于初始hs-cTnI的MI3算法鉴别1型与2型心肌梗死的AUC为0.704(95%CI 0.611-0.797)。
- MI3联合NT-proBNP和Gal-3后AUC提升至0.789(95%CI 0.709-0.869,p=0.0165)。
- 在86例有连续hs-cTnI的患者中,联合生物标志物后AUC由0.721升至0.797(p=0.09),未达统计学显著。
- 作者认为联合NT-proBNP和Gal-3的MI3算法在鉴别1型与2型心肌梗死方面显示出前景。
适用人群与场景
- CMR-IMPACT试验中因急性冠脉综合征症状就诊、初始肌钙蛋白不确定的成人患者。
- 纳入标准为经裁定诊断为心肌梗死且初始高敏肌钙蛋白I(hs-cTnI;Abbott Laboratories)可测。
研究设计与关键结果
- 研究类型为多中心前瞻性CMR-IMPACT试验的二次分析;123例裁定心肌梗死患者,平均年龄60±12岁,女性37.4%(46/123)。
- 1型心肌梗死占58.5%(72/123),2型占41.5%(51/123)。
- 基于初始hs-cTnI的MI3算法鉴别心肌梗死类型的AUC为0.704(95%CI 0.611-0.797)。
- MI3联合NT-proBNP和Gal-3后AUC提升至0.789(95%CI 0.709-0.869,p=0.0165)。
- 在86例有连续hs-cTnI的患者中,MI3的AUC为0.721(95%CI 0.614-0.829),联合NT-proBNP和Gal-3后升至0.797(95%CI 0.700-0.894,p=0.09)。
证据类型、等级与局限
- 证据类型:多中心前瞻性试验的二次分析。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,将NT-proBNP和Gal-3加入MI3机器学习算法在鉴别1型与2型心肌梗死方面显示出前景。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「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
BACKGROUND: Treatment of myocardial infarction (MI) differs based on MI type, which can be difficult to determine in the emergency department. This study sought to evaluate whether a machine learning algorithm (MI3) in combination with N-Terminal pro B-type natriuretic peptide (NT-proBNP) and galectin-3 (Gal-3) can accurately differentiate MI type.
METHODS: We conducted a secondary analysis of the multisite CMR-IMPACT trial, which prospectively enrolled adults with symptoms of acute coronary syndrome and an initial indeterminate troponin. Patients with an adjudicated diagnosis of MI and an initial high-sensitivity cardiac troponin I (hs-cTnI; Abbott Laboratories) measure were included. Incidence of MI and MI type were adjudicated by expert reviewers. Receiver operator characteristic curves for MI-type were created and area under the curve (AUC) calculated for MI3 and MI3 with NT-proBNP and Gal-3. AUCs were compared using DeLong's method.
RESULTS: Among 123 patients with adjudicated MI, the mean age was 60±12 years and 37.4% (46/123) were female. Type 1 MI occurred in 58.5% (72/123) and type 2 MI in 41.5% (51/123). MI3 based on an initial hs-cTnI yielded an AUC of 0.704 (95% CI 0.611-0.797) for MI type. When combined with NT-proBNP and Gal-3, AUC improved to 0.789 (95% CI 0.709-0.869, p=0.0165). In patients with serial hs-cTnIs (n = 86), the AUC of MI3 for MI type was 0.721 (95% CI 0.614-0.829) and increased to 0.797 (95% CI 0.700-0.894, p=0.09) with the addition of NT-proBNP and Gal-3.
CONCLUSION: Adding NT-proBNP and Gal-3 to the MI3 machine learning algorithm shows promise in differentiating type 1 from type 2 MI.
参考来源
- Snavely A, Jackson L, Hunter CJ, et al. Differentiating Type 1 and Type 2 myocardial infarction using a machine learning algorithm and biomarkers. Am J Emerg Med. 2025. PMID: 40834835. doi:10.1016/j.ajem.2025.08.019
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。