arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.07089cs.LG
收藏

TrialSynth:合成序列临床试验数据的生成

TrialSynth: Generation of Synthetic Sequential Clinical Trial Data

University of Illinois Urbana Champaign(伊利诺伊大学厄巴纳-香槟分校);Medidata Solutions(美迪赛塔解决方案公司);Carle Illinois College of Medicine(卡尔伊利诺伊医学院)

Chufan Gao, Mandis Beigi, Afrah Shafquat, Jacob Aptekar, Jimeng Sun

AI总结:

针对细粒度时间序列合成临床试验数据生成难的问题,提出基于霍克斯过程的变分自编码器TrialSynth,在小样本真实数据集上实现了更优的生成保真度与数据效用,同时兼顾患者隐私。

摘要:

分析过往临床试验数据是优化新临床试验的设计、落地与执行,更高效地将救命干预措施推向市场的持续工作的一部分。尽管近年来静态上下文合成临床试验数据的生成取得了进展,但由于患者样本量有限,加之患者隐私需求带来的约束,生成细粒度的时间序列合成临床试验数据一直颇具挑战。鉴于患者在整个临床试验中的轨迹对优化试验设计、防范有害不良事件至关重要,目前亟需生成高保真的时间序列临床试验数据。本文提出TrialSynth,这是一种变分自编码器(Variational Autoencoder, VAE),旨在应对生成合成时间序列临床试验数据的特定挑战。与相关临床数据VAE方法不同,我们方法的核心利用了霍克斯过程(Hawkes Processes, HP),该方法尤其适合建模事件类型与时间间隔预测,而这正是捕捉序列临床试验数据结构所必需的。我们的实验表明,在不同保真度/隐私权衡水平下,TrialSynth的表现均优于其他可生成序列临床试验数据的同类方法,能够在患者源群体规模较小的多个真实世界序列事件数据集上生成高度准确的事件序列。值得注意的是,我们的实证研究结果凸显,TrialSynth不仅优于现有的临床序列生成方法,还能生成效用更优的数据,同时在实证层面保护了患者隐私。

英文摘要:

Analyzing data from past clinical trials is part of the ongoing effort to optimize the design, implementation, and execution of new clinical trials and more efficiently bring life-saving interventions to market. While there have been recent advances in the generation of static context synthetic clinical trial data, due to both limited patient availability and constraints imposed by patient privacy needs, the generation of fine-grained synthetic time-sequential clinical trial data has been challenging. Given that patient trajectories over an entire clinical trial are of high importance for optimizing trial design and efforts to prevent harmful adverse events, there is a significant need for the generation of high-fidelity time-sequence clinical trial data. Here we introduce TrialSynth, a Variational Autoencoder (VAE) designed to address the specific challenges of generating synthetic time-sequence clinical trial data. Distinct from related clinical data VAE methods, the core of our method leverages Hawkes Processes (HP), which are particularly well-suited for modeling event-type and time gap prediction needed to capture the structure of sequential clinical trial data. Our experiments demonstrate that TrialSynth surpasses the performance of other comparable methods that can generate sequential clinical trial data at varying levels of fidelity / privacy tradeoff, enabling the generation of highly accurate event sequences across multiple real-world sequential event datasets with small patient source populations. Notably, our empirical findings highlight that TrialSynth not only outperforms existing clinical sequence-generating methods but also produces data with superior utility while empirically preserving patient privacy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑