English(EN) Differentiable latent structure discovery for interpretable forecasting in clinical time series

新的高斯过程模型增强了临床时间序列可解释预测

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-30 14:59

研究人员开发了StructGP，一种新颖的高斯过程模型，用于临床时间序列的可解释预测。该模型将过程卷积与可微分结构学习相结合，以揭示变量间依赖关系的定向无环图，并保留原则性的不确定性。StructGP在模拟和真实临床数据上都表现出强大的性能，与现有方法相比，提高了预测准确性和校准性。 AI

影响引入了一种用于医疗保健领域可解释和校准预测的新方法，有可能改善临床决策支持。

排序理由学术论文，详细介绍了一种新的时间序列预测方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Ivan Lerner, Jean Feydy, Alexandre Kalimouttou, Anita Burgun, Francis Bach · 2026-05-01 04:00

Differentiable latent structure discovery for interpretable forecasting in clinical time series

arXiv:2604.27967v1 Announce Type: new Abstract: Background: Timely, uncertainty-aware forecasting from irregular electronic health records (EHR) can support critical-care decisions, yet most approaches either impute to a grid or sacrifice interpretability. We introduce StructGP, …
arXiv cs.LG TIER_1 English(EN) · Francis Bach · 2026-04-30 14:59

Differentiable latent structure discovery for interpretable forecasting in clinical time series

Background: Timely, uncertainty-aware forecasting from irregular electronic health records (EHR) can support critical-care decisions, yet most approaches either impute to a grid or sacrifice interpretability. We introduce StructGP, a continuous-time multi-task Gaussian process th…