/paper-ecg

OSU Capstone Project 2020-21 - Natalie & Julian

Primary LanguagePythonOtherNOASSERTION

Paper ECG

An application for digitizing ECG scans. (OSU Capstone Project 2020-21)

See ecgdigitize for the library implementing the grid and signal digitization. Cite published manuscript: J. D. Fortune, N. E. Coppa, K. T. Haq, H. Patel and L. G. Tereshchenko. Digitizing ECG image: a new method and open-source software code. Computer Methods and Programs in Biomedicine 2022 Pages 106890. DOI: https://doi.org/10.1016/j.cmpb.2022.106890 https://www.sciencedirect.com/science/article/pii/S0169260722002723

Authors

  • Natalie Coppa
  • Julian Fortune
  • Larisa Tereschenko (tereshch at ohsu.edu)

With help from:

  • Kazi Haq
  • Hetal Patel

Overview

This application allows digitizing paper ECG image scans, such as this one:

fullscan

To produce digital signals, like these:

fullscan-output

Installation

Download the latest release here.

User Guide

Read the user guide here

Contributing

Follow the set-up instructions:

You should now have:

  • Python 3.6.7
  • Virtual environment
  • All required packages

Reminder: Make sure your virtual environment is running! (this will happen automatically if you are using pyenv)

You can now run:

fbs run

Or, on Windows, you may need to run:

py -3.6 -m fbs run

This will start the interpreted version of the project.

Build

In order to create an executable that can be distributed, run:

fbs build

Or, on Windows, you may need to run:

py -3.6 -m fbs build

This only builds an executable targeting the current OS (i.e., virtualization or multiple machines is necessary to produce builds for each OS).

Contributing

View the issues list to see what tasks are available to work on.

Dependencies

The project currently requires Python 3.6.7 to work with fbs (see 3.7 support issue).

Build Notes

Capstone

See our sprint documents here.

Preprint to cite

Julian Fortune, Natalie Coppa, Kazi T Haq, Hetal Patel, Larisa G Tereshchenko. Digitizing ECG image: new fully automated method and open-source software code. medRxiv 2021.07.13.21260461; doi: https://doi.org/10.1101/2021.07.13.21260461

Statistical validation code

see file digitizing_validation Stata code.do. See manuscript(peprint above) for the detailed description of statistical methods.