面向真实世界餐次血糖控制的可解释机制表征
Interpretable Mechanistic Representations for Meal-level Glycemic Control in the Wild
AI总结：
提出混合变分自编码器，将潜在表征与血糖机制微分方程绑定，从真实 CGM 和餐食数据中学习可解释生理嵌入，并显著提升按疾病严重程度聚类的效果。
摘要：
糖尿病涉及复杂的血糖控制状况，且个体间差异很大。然而，现有方法无法在餐次级真实捕捉这种差异。一方面，专家设计的特征缺乏数据驱动方法的灵活性；另一方面，学习得到的表征往往不可解释，这阻碍了临床应用。本文提出一种混合变分自编码器，用于学习 CGM 和餐食数据的可解释表征。我们的方法将潜在空间锚定到机制微分方程的输入上，生成能够反映胰岛素敏感性、葡萄糖效能和基础葡萄糖水平等生理量的嵌入。此外，我们提出一种推断葡萄糖出现速率的新方法，使机制模型对不可靠的餐食记录具有鲁棒性。在一个包含 2 型糖尿病及糖尿病前期个体 CGM 和自我报告餐食的数据集上，我们的无监督表征发现了与疾病严重程度成比例的个体分离。我们的嵌入所产生的聚类，其效果最高可达朴素特征、专家特征、黑箱特征和纯机制特征的 4 倍。该方法提供了一个细致且可解释的嵌入空间，可用于比较个体内部及个体之间的血糖控制，并能直接从真实世界数据中学习。
英文摘要：
Diabetes encompasses a complex landscape of glycemic control that varies widely among individuals. However, current methods do not faithfully capture this variability at the meal level. On the one hand, expert-crafted features lack the flexibility of data-driven methods; on the other hand, learned representations tend to be uninterpretable which hampers clinical adoption. In this paper, we propose a hybrid variational autoencoder to learn interpretable representations of CGM and meal data. Our method grounds the latent space to the inputs of a mechanistic differential equation, producing embeddings that reflect physiological quantities, such as insulin sensitivity, glucose effectiveness, and basal glucose levels. Moreover, we introduce a novel method to infer the glucose appearance rate, making the mechanistic model robust to unreliable meal logs. On a dataset of CGM and self-reported meals from individuals with type-2 diabetes and pre-diabetes, our unsupervised representation discovers a separation between individuals proportional to their disease severity. Our embeddings produce clusters that are up to 4x better than naive, expert, black-box, and pure mechanistic features. Our method provides a nuanced, yet interpretable, embedding space to compare glycemic control within and across individuals, directly learnable from in-the-wild data.
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。
