大型语言模型作为合成临床专家用于纵向罕见病建模
Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling
- University of Freiburg（弗莱堡大学）
- Freiburg Center for Data Analysis, Modeling and AI（弗莱堡数据分析、建模与人工智能中心）
- University of Bonn（波恩大学）
- Bonn Center for Mathematical Life Sciences（波恩数学生命科学中心）
- Life and Medical Sciences (LIMES) Institute（生命与医学科学研究所）
- Centre for Integrative Biological Signalling Studies（整合生物信号研究中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究用LLMs作为合成临床专家，监督变分自编码器学习纵向罕见病数据的低维表示，降低了脊髓性肌萎缩症标签分歧，提升了运动功能里程碑预测效果。
AI中文摘要：
由于信息有限，对纵向罕见病数据进行建模需整合临床知识，但专家知识的获取及模型拟合的形式化颇具挑战，尤其受限于临床专家的时间。为在模型拟合过程中仍能利用领域知识，我们采用大型语言模型（LLMs）作为合成临床专家，对基于变分自编码器（variational autoencoder）的方法进行监督，该方法可学习就诊级观测的低维潜在摘要。具体而言，我们离线查询LLMs关于患者观测的文本描述以获取判断，例如疑似临床类别。为提升变分自编码器的拟合效果，我们在这些判断上训练可微替代模型，并扩充损失函数以鼓励保留对应输入特征临床标签分布的重构。在针对脊髓性肌萎缩症（spinal muscular atrophy）患儿的纵向运动功能评估应用中，我们将就诊级临床特征映射至由多元混合效应模型连接的低维表示。合成专家损失函数会阻止那些在数据空间中数值相近但改变了重构运动功能特征临床解释的重构，例如跨越疾病类型边界的情况。我们由此将原始与重构SMA类型标签间的分歧从约11%降至7%。此外，与无监督潜在表示及数据级基线相比，通过合成专家优化潜在表示提升了运动功能里程碑的预测效果。这些结果表明，将LLMs纳入模型拟合过程可使临床知识为表征学习所用，并提升纵向罕见病数据的临床忠实性。
英文摘要：
Due to the limited amount of information, modeling longitudinal rare-disease data can benefit from integrating clinical knowledge. Yet, elicitation of expert knowledge and formalization for model fitting is challenging, in particular due to limited time of clinical experts. To nevertheless make domain knowledge accessible during model fitting, we use large language models (LLMs) as synthetic clinical experts to supervise a variational-autoencoder-based approach that learns low-dimensional latent summaries of visit-level observations. Specifically, LLMs are queried offline on textual descriptions of patient observations to obtain judgments, e.g., the suspected clinical category. To improve the variational autoencoder fit, we train a differentiable surrogate model on these judgments and augment the loss function to encourage reconstructions that preserve the clinical-label distribution of their corresponding input profile. In an application to longitudinal motor-function assessments from children with spinal muscular atrophy, we map visit-level clinical profiles to low-dimensional representations that are linked by a multivariate mixed-effects model. The synthetic expert loss discourages reconstructions that remain numerically close in data space but alter the clinical interpretation of the reconstructed motor function profile, such as by crossing a disease-type boundary. We thus reduced disagreement between original and reconstructed SMA type labels from about 11 to 7 percent. Furthermore, informing the latent representation by the synthetic expert improved prediction of motor function milestones compared with unsupervised latent representations and a data-level baseline. These results suggest that incorporating LLMs into model fitting can make clinical knowledge available to representation learning and improve clinical faithfulness for longitudinal rare-disease data.
