BioSignal Copilot: Leveraging the power of LLMs in drafting reports for biomedical signals
Files and descriptions
-
ECG_delineation.py This is a feasibility study code pack that aims to produce a Signal To Text for BioSignal Copilot system that we are developing. It contains the comprehensive code for our system.
-
model.hdf5 is our predictive model, which is the model trained in A. H. Ribeiro, M. H. Ribeiro, G. M. M. Paixão, et al., “Automatic diagnosis of the 12-lead ECG using a deep neural network,” Nature Communications, vol. 11, no. 1, p. 1760, 2020. Published DOI: https://doi.org/ 10.1038/s41467-020-15432-4
Pre-print version: https://arxiv.org/abs/1904.01949
Data link: https://zenodo.org/record/3765717
Model files: https://zenodo.org/record/3765717/files/model.zip
Test data: https://zenodo.org/record/3765780 ("Contain 827 ECG tracings from different patients, annotated by several cardiologists, residents and medical students. It is used as test set on the paper: "Automatic diagnosis of the 12-lead ECG using a deep neural network". https://www.nature.com/articles/s41467-020-15432-4.")
TNMG7_N1.dat and TNMG7_N1.hea are one of our case study test data.
TNMG7_N1_normal.png is the ECG picture corresponding to the test data.