All Competitors

Every biological foundation model, evaluated and ranked by the bio.rodeo team

Showing 17 of 7 filtered models

  • University of Oxford +5 othersJuly 1, 2025clinical_outcome_predictioncross_modality_generationdiagnosis+8

    Multimodal foundation model for cardiac biosignals, pretrained by masked modeling on ECG, PPG, and clinical text from ~1.7 million individuals.

    BiosignalsLanguage model
    26Openness
  • PhysioWave

    18914
    ETH Zurich +2 othersJune 12, 2025arrhythmia_detectionecgeeg+9

    Physiological signal foundation model for ECG, EMG, and EEG pairing learnable multi-scale wavelet decomposition with masked transformer pretraining.

    Biosignals
    80Openness
  • QoQ-Med

    5238465
    MITMay 31, 2025ecgfoundation_modelhistology+7

    Multimodal clinical foundation model reasoning jointly over 2D and 3D medical images, ECG time-series, and text reports across nine clinical domains.

    ImagingBiosignalsLanguage model
    74Openness
  • PULSE

    67301.9K
    The Ohio State University +1 otherOctober 21, 2024cardiologyecgecg_interpretation+6

    Multimodal large language model that interprets 12-lead electrocardiogram images, answering open-ended clinical questions and generating ECG reports.

    BiosignalsImaging
    84Openness
  • Eko HealthOctober 11, 2024disease_detectionecgfoundation_model+5

    Masked-autoencoder foundation model pretrained on digital-stethoscope heart sounds and single-lead ECG for cardiovascular disease detection.

    Biosignals
    22Openness
  • ECG-Chat

    8248
    China University of Geosciences +2 othersAugust 16, 2024cardiologycontrastive_learningdisease_classification+6

    Multimodal ECG-language model aligning 12-lead waveforms with clinical report text for conversational cardiac diagnosis and report generation.

    BiosignalsLanguage model
    27Openness
  • Rice UniversityMay 26, 2024arrhythmia_detectioncontrastive_learningconvnext+6

    ECG foundation model that learns 12-lead waveform representations by contrastively aligning each recording with machine-generated cardiological text.

    Biosignals
    63Openness