自适应人工智能用于心血管事件判定:ODYSSEY OUTCOMES与EUCLID试验中跨定义的心血管事件判定
该研究开发并验证了自适应AI算法ADAPT-CEC,用于判定临床试验中的心血管终点事件。算法在ODYSSEY OUTCOMES试验中开发,经20例EUCLID疑似事件适应后,在EUCLID试验中外部验证。结果显示,混合策略(人类判定AI置信度最低的30%事件)的F1分数最高,且各策略对EUCLID主要终点治疗效果估计与人类判定相似。
要点
- ADAPT-CEC经短暂适应后可在第二项试验中判定相似和新终点事件。
- 混合策略在F1分数上优于单独使用ADAPT-CEC或GPT-4o。
- 各种AI判定策略均能复制EUCLID主要终点的治疗效果。
核心结论
- 经短暂适应后,单一试验衍生的AI算法可判定第二项试验中相似(心梗和卒中)及新终点(心血管死亡和出血),并复制EUCLID主要终点治疗效果。
- 人类判定AI置信度最低30%的疑似事件的混合策略优于单独ADAPT-CEC或单独GPT-4o,且复制了EUCLID主要终点治疗效果。
研究设计与样本
- 研究基于ODYSSEY OUTCOMES试验(急性冠脉综合征后使用阿利西尤单抗的心血管结局评估)衍生ADAPT-CEC。
- 在EUCLID试验(外周动脉疾病使用替格瑞洛研究)中外部验证,每个终点用20例疑似事件进行适应。
- 比较了ADAPT-CEC、直接GPT-4o判定和混合策略(AI置信度最低30%疑似事件由人类判定)的F1分数。
主要发现
- 三种策略对非终点事件的正确分类率分别为99.4%、99.6%和99.8%。
- 混合判定的F1分数最高:心血管死亡0.94(95%CI,0.92-0.96);心梗0.80(95%CI,0.77-0.82);卒中0.82(95%CI,0.78-0.86);出血0.83(95%CI,0.82-0.85)。
- ADAPT-CEC的出血F1分数(0.78,95%CI,0.77-0.79)优于GPT-4o。
关键数值与推荐
- EUCLID主要终点(心血管死亡、心梗或卒中)治疗效果:人类判定HR=1.02(95%CI,0.93-1.13);混合判定HR=1.04(95%CI,0.94-1.15);ADAPT-CEC判定HR=0.98(95%CI,0.88-1.09);GPT-4o判定HR=1.06(95%CI,0.95-1.19)。
临床怎么用
- 该AI算法可减少临床试验终点判定中的人工工作量。
- 混合策略(AI初筛+人类复核低置信度事件)可提高判定准确性和效率。
- 自适应AI判定在应用前需针对新试验进行短期适应调整。
局限性
- 需要前瞻性研究来确定自适应AI判定在临床试验中的实际应用。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Clinical end point classification (CEC) is the gold standard for cardiovascular end point measurement in clinical trials but adds time and cost. We developed and validated an artificial intelligence (AI) algorithm (adaptive AI for CEC [ADAPT-CEC]) that adjudicates multiple cardiovascular end points and adapts to new definitions. METHODS: ADAPT-CEC was derived from myocardial infarction (MI), stroke, and heart failure from the ODYSSEY OUTCOMES (Evaluation of Cardiovascular Outcomes After an Acute Coronary Syndrome During Treatment With Alirocumab) trial and externally validated on MI, stroke, bleeding and cardiovascular (CV) death from the EUCLID (Examining Use of Ticagrelor in Peripheral Artery Disease) trial after adaptation with 20 EUCLID suspected events per end point. ADAPT-CEC was compared via F1 score with direct Generative Pretrained Transformer (GPT) 4o adjudication and a hybrid approach where the 30% of suspected events with the lowest AI prediction certainty used human adjudication. The EUCLID primary end point of CV death, MI, or stroke was re-estimated for all 3 adjudication strategies. RESULTS: Among 13 885 suspected EUCLID primary end point events, ADAPT-CEC, hybrid, and GPT 4o strategies correctly classified 86.4%, 95.6%, and 76.3% of all end points and 99.4%, 99.6%, and 99.8% of all non-end points compared with human adjudication, respectively. Hybrid adjudication F1 metrics were the highest (CV death, 0.94 [95% CI, 0.92-0.96]; MI, 0.80 [95% CI, 0.77-0.82]; stroke, 0.82 [95% CI, 0.78-0.86]; bleeding, 0.83 [95% CI, 0.82-0.85]). ADAPT-CEC F1 metrics were lower for CV death, MI, and stroke but similar to GPT 4o, while bleeding (0.78 [95% CI, 0.77-0.79]) was superior to GPT 4o. The EUCLID primary treatment effect was similar by human adjudication (hazard ratio [HR], 1.02 [95% CI, 0.93-1.13]); hybrid (HR, 1.04 [95% CI, 0.94-1.15]); ADAPT-CEC (HR, 0.98 [95% CI, 0.88-1.09]), and GPT 4.0 (HR, 1.06 [95% CI, 0.95-1.19]) adjudication. CONCLUSIONS: After brief adaptation, a single trial-derived AI algorithm can adjudicate similar (MI and stroke) and new end points (CV death and bleeding) in a second trial and replicate the EUCLID primary outcome treatment effect. A hybrid approach with humans adjudicating those suspected events with the lowest 30% of ADAPT-CEC prediction certainty was superior to ADAPT-CEC alone or GPT 4o alone and replicated the EUCLID primary outcome treatment effect. Prospective studies of adaptive AI adjudication are needed to determine future trial implementation.
引用
- Vemulapalli, Peña Guerra, Wojdyla, et al. Adaptive AI for Cardiovascular Event Adjudication: Cardiovascular Event Adjudication Across Different Definitions in the ODYSSEY OUTCOMES and EUCLID Trials. Circulation. 2026. PMID: 41911340. doi:10.1161/CIRCULATIONAHA.126.080072
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。