Open source QRS detectors achieved sensitivities and positive predictivities close to 99.8% on the MIT/BIH and AHA arrhythmia databases, with beat classifier sensitivity >93%.
Open-source ECG analysis software provides highly accurate QRS detection and beat classification, reducing duplication of effort for researchers and developers.
Each year companies and researchers expend significant resources developing basic beat detection and classification software. In an effort to reduce this duplication of effort we are developing and making available open source ECG analysis software. Our open source QRS detectors have sensitivities and positive predictivities that are close to 99.8% on the MIT/BIH and AHA arrhythmia databases. Our beat classifier has a sensitivity of 93.91% and a positive predictivity of 96.48% on the MIT/BIH arrhythmia database and a sensitivity of 93.2% and a positive predictivity of 97.83% on the AHA arrhythmia database. Since we have posted our source code, over 350 users have downloaded our ECG analysis software. Downloads have been nearly equally divided between students, researchers, and commercial developers.
P.S. Hamilton (Wed,) conducted a other in Arrhythmia. Open source ECG analysis software was evaluated on Sensitivity and positive predictivity of QRS detectors and beat classifier. Open source QRS detectors achieved sensitivities and positive predictivities close to 99.8% on the MIT/BIH and AHA arrhythmia databases, with beat classifier sensitivity >93%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: