Skip to content

nathanohara/ecg

Repository files navigation

ECG Feature Modeling

An implementation of the algorithm from "Characterising an ECG signal using statistical modelling: a feasibility study" by Bodisco, et al.

The primary MCMC script where the Metropolis-Hastings algorithm is implemented is ecg_MCMC.R. MCMC samples were saved into the folder "MCMC_Samples". arrhythmia.rmd and healthy.rmd show the results of posterior sampling on five heartbeats from a healthy patient and five heartbeats from a patient with an arrhythmia, taken from the MIT-BIH Arrhythmia Database. interpretation.rmd contains scripts generating density plots and two-sample t-tests to compare parameter distributions across healthy and unhealthy patients. Each of these markdown files has been knit to HTML and is located in the "rendered_markdown" folder. "data_prc" contains our preprocessed data, whereas "heartbeat_data" contains that same data segmented into individual heartbeats. This data was processed using code from this repository: Python Online and Offline ECG QRS Detector based on the Pan-Tomkins algorithm. Figures generated are held in the "Results" folder, and a PDF of a final report detailing the process is in final_report.pdf.

About

Computing ECG features using MCMC modeling

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published