Cardiac Evidence Backtracking for Eating Behavior Monitoring using Collocative Electrocardiogram Imagining

2025-02-20

AI Summary

This study addresses the challenge of non-invasive, continuous dietary behavior monitoring in clinical settings by proposing an automatic eating detection method leveraging 24-hour wearable ECG signals. The approach constructs image-like representations via a 1D-to-2D tensor mapping, incorporates a novel periodicity-aware attention mechanism to model the physiological coupling between cardiac rhythm and ingestion, and introduces a pioneering cardiac evidence backtracking mechanism—integrating an enhanced Class Activation Mapping (CAM) with decision-tree-based decoding—to significantly improve model interpretability and clinical credibility. Evaluated on the largest publicly available eating-ECG dataset, the method outperforms state-of-the-art models in detection accuracy. Crucially, the physiologically grounded biomarkers retrospectively identified by the model exhibit strong alignment with established medical priors, empirically validating the feasibility of extracting latent dietary behavior information from routine ECG recordings.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Machine Learning: Time-Series/Data Streams

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance

Abstract

Eating monitoring has remained an open challenge in medical research for years due to the lack of non-invasive sensors for continuous monitoring and the reliable methods for automatic behavior detection. In this paper, we present a pilot study using the wearable 24-hour ECG for sensing and tailoring the sophisticated deep learning for ad-hoc and interpretable detection. This is accomplished using a collocative learning framework in which 1) we construct collocative tensors as pseudo-images from 1D ECG signals to improve the feasibility of 2D image-based deep models; 2) we formulate the cardiac logic of analyzing the ECG data in a comparative way as periodic attention regulators so as to guide the deep inference to collect evidence in a human comprehensible manner; and 3) we improve the interpretability of the framework by enabling the backtracking of evidence with a set of methods designed for Class Activation Mapping (CAM) decoding and decision tree/forest generation. The effectiveness of the proposed framework has been validated on the largest ECG dataset of eating behavior with superior performance over conventional models, and its capacity of cardiac evidence mining has also been verified through the consistency of the evidence it backtracked and that of the previous medical studies.

Problem

• Non-invasive eating behavior monitoring
• Deep learning for ECG analysis
• Interpretable cardiac evidence backtracking

Innovation

• Wearable ECG for continuous monitoring
• Deep learning for behavior detection
• Collocative learning with interpretable evidence backtracking