Cardio AI Lab

We run two complementary spaces — a Computer Lab and a Bioscience Lab — to build interpretable, clinically useful models for cardiovascular health. Our flagship project is CardioFlowFormer, a spatiotemporal framework for motion phenotyping and early risk detection.

Cardio AI Lab overview

Our Labs

Computer Lab

  • Transformer pipelines for imaging, EHR, and genomics
  • Survival analysis, calibration, and uncertainty
  • Bias audits, domain adaptation, fairness metrics
  • GPU training, MLOps, and reproducible evaluation

Bioscience Lab

  • iPSC-derived cardiomyocyte imaging and annotations
  • Optical flow capture and motion signatures
  • Quality control, lab protocols, dataset curation
  • Bench-to-model feedback for clinically relevant labels

CardioFlowFormer

Transformer-based spatiotemporal model that fuses motion fields, morphology, and temporal contraction metrics to detect ageing- and damage-related cardiomyocyte dysfunction early.

  • Optical flow tokens + temporal attention
  • Explainability with attention maps, IG, SHAP
  • Time-to-event extensions for prognosis
  • External validation on UK Biobank / CPRD cohorts
Frame-to-frame cardiomyocyte motion patterns (fuzzy, dense, bulb)

frame-to-frame motion entropy changes

Active Projects

Clinical Validation Toolkit

Fair-CVD Benchmark

Motion Phenotyping Suite

People

Md Abu Sufian

Founder, Cardio AI Lab. Research: spatiotemporal modelling, survival analysis, fair & interpretable AI for CVD.

Email: m.sufian@uel.ac.uk

Collaborators & Students

Bioscience Lab (UEL), clinical partners, and external collaborators across imaging and biostatistics.

Join / Collaborate

We welcome collaboration on datasets, clinical validation, and tooling. Email m.sufian@uel.ac.uk.