Skip to content

SCAI-Lab/delta-sbp-prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 

Repository files navigation

delta-sbp-prediction

This repository contains the official implementation of our multimodal deep learning framework for real-time beat-to-beat ΔSBP (delta Systolic Blood Pressure) estimation using physiological signals and demographic data.


Summary

We propose a hybrid CNN–BiLSTM–attention model that fuses:

  • Photoplethysmogram (PPG)
  • Electrocardiogram (ECG)
  • Demographic features (e.g., age, gender, BMI)

The model is pretrained on the Aurora BP dataset and fine-tuned on a clinical SCI (Spinal Cord Injury) cohort using SCAI-BP dataset via transfer learning. It satisfies international standards for BP monitoring systems (AAMI, BHS).


Citation

If you use this codebase, please cite our paper (coming soon).


Repository Structure

├── src/                
├── Supplementary_material/
├── README.md
├── LICENSE
└── requirements.txt     # Python dependencies



About

Codebase for multimodal CNN–BiLSTM–attention model for ΔSBP estimation using Aurora and SCI datasets.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors