# MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification

arXiv: https://arxiv.org/abs/2605.24961 · HTML: https://mlsanity.com/paper/2605.24961/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 52 references that are in the map.
- First posted on arXiv 24 May 2026.

## Builds on (most cited first, 3 of 3)

- [MedMamba: Vision Mamba for Medical Image Classification](https://mlsanity.com/paper/2403.03849/) (2024)
- [A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data](https://mlsanity.com/paper/2010.12493/) (2020)
- [EEGMamba: Bidirectional State Space Model with Mixture of Experts for EEG Multi-task Classification](https://mlsanity.com/paper/2407.20254/) (2024)

## Abstract (arXiv)

Medical time series are central to healthcare, enabling continuous monitoring and supporting timely clinical decisions. Despite recent progress, existing methods struggle to jointly model local-global dynamics and handle nonstationarities like baseline drift, while often failing to capture latent channel interactions. To address these challenges, we propose MedMamba, an end-to-end architecture that integrates state space models with domain-specific inductive biases. Specifically, MedMamba first employs multi-scale convolutional embeddings to capture discriminative local morphology. Second, to mitigate nonstationarity, we introduce a tri-branch differential state space encoder that processes raw, temporal-difference, and frequency-domain views, fusing them to emphasize informative patterns while suppressing drift. Furthermore, to uncover latent channel correlations, we design a spatial graph Mamba module that learns a directed dependency structure regularized toward sparsity and acyclicity, which obviates the need for predefined graphs. Extensive experiments on five real-world datasets demonstrate that MedMamba achieves state-of-the-art performance while maintaining linear computational complexity, and ablation studies validate each component's contribution.Code is available at https://github.com/zhangda1018/MedMamba.