mlsanityData to 14 Oct 2026

Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification

arXiv 2405.19363 ↗First posted 24 May 2024eess.SP cs.AI cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

Medical time series (MedTS) data, such as Electroencephalography (EEG) and Electrocardiography (ECG), play a crucial role in healthcare, such as diagnosing brain and heart diseases. Existing methods for MedTS classification primarily rely on handcrafted biomarkers extraction and CNN-based models, with limited exploration of transformer-based models. In this paper, we introduce Medformer, a multi-granularity patching transformer tailored specifically for MedTS classification. Our method incorporates three novel mechanisms to leverage the unique characteristics of MedTS: cross-channel patching to leverage inter-channel correlations, multi-granularity embedding for capturing features at different scales, and two-stage (intra- and inter-granularity) multi-granularity self-attention for learning features and correlations within and among granularities. We conduct extensive experiments on five public datasets under both subject-dependent and challenging subject-independent setups. Results demonstrate Medformer's superiority over 10 baselines, achieving top averaged ranking across five datasets on all six evaluation metrics. These findings underscore the significant impact of our method on healthcare applications, such as diagnosing Myocardial Infarction, Alzheimer's, and Parkinson's disease. We release the source code at https://github.com/DL4mHealth/Medformer.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 38 of its 79 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

38 of 79 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  8. 2020Reformer: The Efficient Transformercited by 1,668
  9. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  10. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  11. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  12. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
26 more
  1. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
  2. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 471
  3. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  4. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
  5. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  6. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 250
  7. 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 171
  8. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 148
  9. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 104
  10. 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Seriescited by 79
  11. 2020Subject-Aware Contrastive Learning for Biosignalscited by 76
  12. 2021Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysiscited by 76
  13. 2023Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Seriescited by 59
  14. 2021Gated Transformer Networks for Multivariate Time Series Classificationcited by 58
  15. 2023CARD: Channel Aligned Robust Blend Transformer for Time Series Forecastingcited by 55
  16. 2022Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecastingcited by 54
  17. 2022A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmarkcited by 45
  18. 2023Multi-resolution Time-Series Transformer for Long-term Forecastingcited by 41
  19. 2023MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformercited by 29
  20. 2023MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detectioncited by 26
  21. 2024CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variablescited by 25
  22. 2023ManyDG: Many-domain Generalization for Healthcare Applicationscited by 23
  23. 2022Hierarchical Deep Learning with Generative Adversarial Network for Automatic Cardiac Diagnosis from ECG Signalscited by 15
  24. 2023Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease using EEG Datacited by 9
  25. 2023Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction:A Multi-Dataset Studycited by 6
  26. 2019Cross-Subject Statistical Shift Estimation for Generalized Electroencephalography-based Mental Workload Assessmentcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 29; 2026: 22.

53 papers.

Sort:

By area:

  1. 2025CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decodingcited by 53
  2. 2025FeDaL: Federated Dataset Learning for General Time Series Foundation Modelscited by 10
  3. 2025LEAD: An EEG Foundation Model for Alzheimer's Disease Detectioncited by 9
  4. 2026EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysiscited by 9
  5. 2025TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generationcited by 8
  6. 2026Towards a Medical AI Scientistcited by 7
  7. 2024Repurposing Foundation Model for Generalizable Medical Time Series Classificationcited by 6
  8. 2025Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?cited by 6
  9. 2025MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysiscited by 5
  10. 2026Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Seriescited by 5
  11. 2025UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentationcited by 4
  12. 2025Training-Free Time Series Classification via In-Context Reasoning with LLM Agentscited by 4
38 more
  1. 2026LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modelingcited by 4
  2. 2026MambaSL: Exploring Single-Layer Mamba for Time Series Classificationcited by 4
  3. 2025BioMamba: Leveraging Spectro-Temporal Embedding in Bidirectional Mamba for Enhanced Biosignal Classificationcited by 3
  4. 2026Cross-Subject Generalization for EEG Decoding: A Survey of Deep Learning Methodscited by 3
  5. 2025DynaGraph: Interpretable Multi-Label Prediction from EHRs via Dynamic Graph Learning and Contrastive Augmentationcited by 2
  6. 2025Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analyticscited by 2
  7. 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraintcited by 2
  8. 2025DE3S: Dual-Enhanced Soft-Sparse-Shape Learning for Medical Early Time-Series Classificationcited by 2
  9. 2026Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysiscited by 2
  10. 2026Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approachcited by 2
  11. 2024ADformer: A Multi-Granularity Spatial-Temporal Transformer for EEG-Based Alzheimer Detectioncited by 1
  12. 2025Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspectioncited by 1
  13. 2025Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNetcited by 1
  14. 2025CoSupFormer : A Contrastive Supervised learning approach for EEG signal Classificationcited by 1
  15. 2026HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signalscited by 1
  16. 2025Transformer representation learning is necessary for dynamic multi-modal physiological data on small-cohort patientscited by 0
  17. 2025FHBench: Towards Efficient and Personalized Federated Learning for Multimodal Healthcarecited by 0
  18. 2025Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classificationcited by 0
  19. 2025NeuroHD-RA: Neural-distilled Hyperdimensional Model with Rhythm Alignmentcited by 0
  20. 2025Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Networkcited by 0
  21. 2025Masked Training for Robust Arrhythmia Detection from Digitalized Multiple Layout ECG Imagescited by 0
  22. 2025A Unified Contrastive-Generative Framework for Time Series Classificationcited by 0
  23. 2025TS-P2CL: Plug-and-Play Dual Contrastive Learning for Vision-Guided Medical Time Series Classificationcited by 0
  24. 2025Cortical-SSM: A Deep State Space Model for Motor Imagery Decoding from EEG Signalscited by 0
  25. 2025Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenizationcited by 0
  26. 2025MedM2T: A MultiModal Framework for Time-Aware Modeling with Electronic Health Record and Electrocardiogram Datacited by 0
  27. 2025Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentationcited by 0
  28. 2025NeuroSketch: A Practical Design Recipe for Neural Decodingcited by 0
  29. 2026Benchmarking Artificial Intelligence Models for Daily Coastal Hypoxia Forecastingcited by 0
  30. 2026Towards unified brain-to-text decoding across speech production and perceptioncited by 0
  31. 2026On What We Can Learn from Low-Resolution Datacited by 0
  32. 2026Spectral Priors vs. Attention: Investigating the Utility of Attention Mechanisms in EEG-Based Diagnosiscited by 0
  33. 2026BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Seriescited by 0
  34. 2026NeuroShield: A Device-Agnostic Foundation Model for EEG Authenticationcited by 0
  35. 2026MedTS-TTT: Test-Time Training for Medical Time Series Classificationcited by 0
  36. 2026MedTVL: Harnessing Vision and Language for Medical Time Series Classificationcited by 0
  37. 2026Behavioral Latency as Weak Event-Time Supervision for EEG Reaction-Time Decodingcited by 0
  38. 2026A Multi-Resolution Multi-Domain Pre-Training Framework for Universal Traffic Forecastingcited by 0

50 most cited of 53 All 53 (JSON)