Oikonomou Evangelos K, Thangaraj Phyllis M, Bhatt Deepak L, Ross Joseph S, Young Lawrence H, Krumholz Harlan M, Suchard Marc A, Khera Rohan
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
Mount Sinai Heart, Icahn School of Medicine at Mount Sinai Health System, New York, NY, USA.
NPJ Digit Med. 2023 Nov 25;6(1):217. doi: 10.1038/s41746-023-00963-z.
Randomized clinical trials (RCT) represent the cornerstone of evidence-based medicine but are resource-intensive. We propose and evaluate a machine learning (ML) strategy of adaptive predictive enrichment through computational trial phenomaps to optimize RCT enrollment. In simulated group sequential analyses of two large cardiovascular outcomes RCTs of (1) a therapeutic drug (pioglitazone versus placebo; Insulin Resistance Intervention after Stroke (IRIS) trial), and (2) a disease management strategy (intensive versus standard systolic blood pressure reduction in the Systolic Blood Pressure Intervention Trial (SPRINT)), we constructed dynamic phenotypic representations to infer response profiles during interim analyses and examined their association with study outcomes. Across three interim timepoints, our strategy learned dynamic phenotypic signatures predictive of individualized cardiovascular benefit. By conditioning a prospective candidate's probability of enrollment on their predicted benefit, we estimate that our approach would have enabled a reduction in the final trial size across ten simulations (IRIS: -14.8% ± 3.1%, p = 0.001; SPRINT: -17.6% ± 3.6%, p < 0.001), while preserving the original average treatment effect (IRIS: hazard ratio of 0.73 ± 0.01 for pioglitazone vs placebo, vs 0.76 in the original trial; SPRINT: hazard ratio of 0.72 ± 0.01 for intensive vs standard systolic blood pressure, vs 0.75 in the original trial; all simulations with Cox regression-derived p value of < 0.01 for the effect of the intervention on the respective primary outcome). This adaptive framework has the potential to maximize RCT enrollment efficiency.
随机临床试验（RCT）是循证医学的基石，但资源消耗大。我们提出并评估一种通过计算试验表型图进行适应性预测富集的机器学习（ML）策略，以优化RCT入组。在两项大型心血管结局RCT的模拟序贯分析中，（1）一种治疗药物（吡格列酮与安慰剂；中风后胰岛素抵抗干预（IRIS）试验），以及（2）一种疾病管理策略（强化与标准收缩压降低在收缩压干预试验（SPRINT）中），我们构建了动态表型表征，以推断中期分析期间的反应概况，并检查它们与研究结局的关联。在三个中期时间点，我们的策略学习到了预测个体心血管获益的动态表型特征。通过以前瞻性候选者的预测获益为条件来确定其入组概率，我们估计我们的方法在十次模拟中能够减少最终试验规模（IRIS：-14.8%±3.1%，p = 0.001；SPRINT：-17.6%±3.6%，p < 0.001），同时保持原始平均治疗效果（IRIS：吡格列酮与安慰剂的风险比为0.73±0.01，而原始试验中为0.76；SPRINT：强化与标准收缩压的风险比为0.72±0.01，而原始试验中为0.75；所有模拟中干预对各自主要结局的影响经Cox回归得出的p值<0.01）。这种适应性框架有可能使RCT入组效率最大化。
