Documentation & Resources

This page provides access to all project documentation and resources.

Project Documents

• Atrial Insights

  This is our minimum viable product, Atrial Insights, your personal dashboard designed to help you better understand your atrial fibrillation episodes using real data from your monitoring devices.

• 📊 Presentation Slides

  Final presentation

• 💻 Source Code Repository

  Browse our project's source code and documentation.

Additional Resources

• 📚 Source for training data collection

  This database is the MIT-Beth Israel Hospital Afib database. The data was collected from patients in Boston in 1983 and we used about 130 hours of data for model training and development.

• 📚 Source for training data collection

  This database is the Long Term AF database. The data came from patients in Warsaw Poland, collected in 2007 and we used about 72 hours of this data for model evaluation.

References

George Moody & Steven Swiryn. 2008. Long Term AF Database, Version: 1.0.0. PhysioNet. https://doi.org/10.13026/C2QG6Q George Moody & Roger Mark. 2000. MIT-BIH Atrial Fibrillation Database, Version 1.0.0. PhysiNet. https://doi.org/10.13026/C2MW2D Mousavi S, Afghah F, Acharya UR. HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks. Comput Biol Med. 2020 Dec;127:104057. doi: 10.1016/j.compbiomed.2020.104057. Epub 2020 Oct 15. PMID: 33126126; PMCID: PMC7875017.