Deep learning for ECG analysis

ECG signals consist of different kinds of features which are very important to diagnosing disease and predicting future health issues. Applying deep learning to analyzing ECG signals is a well-known research path with exciting research problems to solve. The following sub-projects are available under this project category.

• ECG analysis using Deep Learning
• ECG feature extractions using limited leads
• Open-source ECG analyzer using DL

Goal

Applying deep-learning solutions to analyze ECGs in real-time and/or developing an open-source platform for ECG analysis.

Learning outcome

• Interdisciplinary research
• Machine learning / AI
• Performing research with advanced deep learning algorithms and real-world applications

Qualifications

• Hard-working
• Motivated
• Interested in learning (the rest can be learned during the thesis work)

Supervisors

• Pål Halvorsen
• Michael Riegler
• Vajira Thambawita

References

• Explaining deep neural networks for knowledge discovery in electrocardiogram analysis
• DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine