Supplementary material: Evaluating the robustness of an AI pathfinder application on eligibility criteria in multiple myeloma trials using real-worlddata and historical trials

These are peer-reviewed supplementary materials for the article 'Evaluating the robustness of an AI pathfinder application on eligibility criteria in multiple myeloma trials using real-world data and historical trials' published in the Journal of Comparative Effectiveness Research.Supplementary Table 1: Computable eligibility criteria of RRMM clinical trials derived from Flatiron Health and Optum’s EHR.Supplementary Table 2: Descriptive statistics of RRMM baseline characteristics in Optum’s EHR and Flatiron Health.Supplementary Figure 1: Percentage of patients excluded versus Shapley values by each eligibility criterion for NIMBUS, ENDEAVOR, ELOQUENT2, CASTOR, CANDOR, and TOURMALINE trials using Optum’s EHR and Flatiron Health real-world databases.Supplementary Table 3: The number of eligibility criteria (# EC), the number of eligible patients (# Pat.) and the hazard ratio (HR) of the progression-free survival of the original clinical trials and emulated RRMM trials with eligibility criteria under three scenarios using Optum’s EHR database: the original criteria used in the trial, fully relaxed criteria, and robust data-driven criteria.Background: Eligibility criteria are pivotal in achieving clinical trial success, enabling targeted patient enrollment while ensuring the trial safety. However, overly restrictive criteria hinder enrollment and study result generalizability. Broadening eligibility criteria enhances the trial inclusivity, diversity and enrollment pace. Liu et al. proposed an AI pathfinder method leveraging real-world data to broaden criteria without compromising efficacy and safety outcomes, demonstrating promise in non-small cell lung cancer trials. Aim: To assess the robustness of the methodology, considering diverse qualities of real world data and to promote its application. Materials/Methods: We revised the AI pathfinder method, applied it to relapsed and refractory multiple myeloma trials and compared it using two real-world data sources. We modified the assessment and considered a bootstrap confidence interval of the AI pathfinder to enhance the decision robustness. Results & conclusion: Our findings confirmed the AI pathfinder’s potential in identifying certain eligibility criteria, in other words, prior complications and laboratory tests for relaxation or removal. However, a robust quantitative assessment, accounting for trial variability and real-world data quality, is crucial for confident decision-making and prioritizing safety alongside efficacy.

本数据集为发表于《比较疗效研究杂志》的论文《基于真实世界数据和历史试验评估人工智能路径探索应用在多发性骨髓瘤临床试验中适用标准的鲁棒性》的同行评审补充材料。补充表1：源自Flatiron Health和Optum电子健康记录的可计算适用标准；补充表2：Optum电子健康记录和Flatiron Health中多发性骨髓瘤基线特征的描述性统计；补充图1：使用Optum电子健康记录和Flatiron Health的真实世界数据库，针对NIMBUS、ENDEAVOR、ELOQUENT2、CASTOR、CANDOR和TOURMALINE试验中每个适用标准排除的病人比例与Shapley值之间的比较；补充表3：在Optum电子健康记录数据库的三个场景下，原始临床试验和模拟的多发性骨髓瘤临床试验的适用标准数量（# EC）、适用病人数量（# Pat.）以及无进展生存期（PFS）的危度比（HR）：试验中使用的原始标准、完全放宽的标准和鲁棒的基于数据驱动的标准。背景：适用标准在实现临床试验成功中扮演关键角色，它既能够实现目标病人的招募，又确保试验的安全性。然而，过于严格的适用标准会阻碍招募并影响研究结果的普适性。放宽适用标准能够提升试验的包容性、多样性和招募速度。Liu等研究者提出了一种利用真实世界数据进行标准放宽的人工智能路径探索方法，在不损害疗效和安全性结果的前提下展示了其在非小细胞肺癌临床试验中的潜力。目的：为了评估该方法的鲁棒性，考虑到真实世界数据的多样性，并促进其应用。材料/方法：我们对人工智能路径探索方法进行了修订，并将其应用于复发和难治性多发性骨髓瘤试验，同时使用两个真实世界数据源进行比较。我们对评估方法进行了改进，并考虑了人工智能路径探索的置信区间以增强决策的鲁棒性。结果与结论：我们的研究结果证实了人工智能路径探索在识别某些适用标准（即放宽或删除的前并发症和实验室检测）方面的潜力。然而，考虑到试验的变异性以及真实世界数据质量，进行稳健的定量评估对于自信的决策和优先考虑安全性以及疗效至关重要。