arXiv cs.AI· Dahai Yu, Lin Jiang, Rongchao Xu, Guang Wang·· 13 小时前AI 评分22
HealthMamba：面向医疗设施就诊量预测的不确定性感知时空图状态空间模型
HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction
AI 导读
HealthMamba 是一个不确定性感知的时空框架，用于准确可靠地预测医疗设施就诊量，包含统一时空上下文编码器、图状态空间模型 GraphMamba 和集成三种机制的不确定性量化模块。在加州、纽约、得州和佛州四个大规模真实数据集上，其预测准确率较 SOTA 基线提升约 6.0%，不确定性量化提升 3.5%。该工作发表于 IJCAI 2026。
正文 · 原文
Abstract:Healthcare facility visit prediction is essential for optimizing healthcare resource allocation and informing public health policy. Despite advanced machine learning methods being employed for better prediction performance, existing works usually formulate this task as a time-series forecasting problem without considering the intrinsic spatial dependencies of different types of healthcare facilities, and they also fail to provide reliable predictions under abnormal situations such as public emergencies. To advance existing research, we propose HealthMamba, an uncertainty-aware spatiotemporal framework for accurate and reliable healthcare facility visit prediction. HealthMamba comprises three key components: (i) a Unified Spatiotemporal Context Encoder that fuses heterogeneous static and dynamic information, (ii) a novel Graph State Space Model called GraphMamba for hierarchical spatiotemporal modeling, and (iii) a comprehensive uncertainty quantification module integrating three uncertainty quantification mechanisms for reliable prediction. We evaluate HealthMamba on four large-scale real-world datasets from California, New York, Texas, and Florida. Results show HealthMamba achieves around 6.0% improvement in prediction accuracy and 3.5% improvement in uncertainty quantification over state-of-the-art baselines.
| Comments: | IJCAI 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.05286 [cs.LG] |
| (or arXiv:2602.05286v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.05286 arXiv-issued DOI via DataCite |
Submission history
From: Dahai Yu [view email]
[v1]
Thu, 5 Feb 2026 04:14:27 UTC (5,453 KB)
[v2]
Wed, 4 Mar 2026 05:10:59 UTC (5,449 KB)
[v3]
Thu, 21 May 2026 03:03:56 UTC (5,448 KB)
[v4]
Wed, 21 Oct 2026 03:40:22 UTC (345 KB)
来源：arXiv cs.AI · arxiv.org