Shift-Invariant Feature Attribution in the Application of Wireless Electrocardiograms

2026-03-20

AI Summary

This study addresses the limitation of existing ECG feature attribution methods, which often neglect temporal translation invariance and thus struggle to accurately link ECG signals to underlying cardiac physiological phases. To overcome this, the authors propose a physiologically meaningful translation-invariant baseline integrated with a residual network architecture. Attribution scores are aggregated and mapped onto specific cardiac cycle phases—such as the P-wave and T-wave—to enable interpretable analysis of decisions in physical activity recognition. Experimental results demonstrate that the model’s key discriminative signals predominantly localize to the P-wave and T-wave regions, corroborating the physiological plausibility and effectiveness of the proposed approach.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Video Understanding & Activity Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Assigning relevance scores to the input features of a machine learning model enables to measure the contributions of the features in achieving a correct outcome. It is regarded as one of the approaches towards developing explainable models. For biomedical assignments, this is very useful for medical experts to comprehend machine-based decisions. In the analysis of electro cardiogram (ECG) signals, in particular, understanding which of the electrocardiogram samples or features contributed most for a given decision amounts to understanding the underlying cardiac phases or conditions the machine tries to explain. For the computation of relevance scores, determining the proper baseline is important. Moreover, the scores should have a distribution which is at once intuitive to interpret and easy to associate with the underline cardiac reality. The purpose of this work is to achieve these goals. Specifically, we propose a shift-invariant baseline which has a physical significance in the analysis as well as interpretation of electrocardiogram measurements. Moreover, we aggregate significance scores in such a way that they can be mapped to cardiac phases. We demonstrate our approach by inferring physical exertion from cardiac exertion using a residual network. We show that the ECG samples which achieved the highest relevance scores (and, therefore, which contributed most to the accurate recognition of the physical exertion) are those associated with the P and T waves. Index Terms Attribution, baseline, cardiovascular diseases, electrocardiogram, activity recognition, machine learning

Problem

• attribution
• electrocardiogram
• baseline
• explainable machine learning
• cardiac phases

Innovation

• shift-invariant baseline
• feature attribution
• electrocardiogram (ECG)
• explainable AI
• cardiac phase mapping