Design of an electrocardiographic lead reconstruction algorithm using machine learning in the context of ambulatory monitoring

Abstract

This PhD Thesis presents an algorithm for reconstructing the standard 12-lead system electrocardiographic (ECG) register using a reduced system of independent leads supported by machine learning models, with a focus on its integration into an ambulatory monitoring system. Traditional ECG lead reconstruction methods have relied on linear combination based approaches, with limited exploration of evaluation methods and electrode positions. This thesis evaluates the effectiveness of new artificial neural networks and fuzzy c-means based algorithms compared to classical linear regression methods, highlighting superior performance and emphasizing the importance of model explainability. Further enhancements, including expert committees and fuzzy models, are explored to improve accuracy and efficiency. Clinical validation at the Hospital Clínico Universitario de València and Hospital General Universitario de València demonstrates the algorithm's effectiveness in an accurate lead reconstruction, paving the way for ambulatory monitoring applications. The study also addresses challenges posed by implantable devices such as pacemakers and defibrillators; a subsequent study proposes a strategy to eliminate distorted pulses during reconstruction, improving signal quality under any condition. Overall, the thesis contributes to advancing ECG lead reconstruction methodologies for improved patient care.