Integrating Natural Language Processing and Exercise Monitoring for Early Diagnosis of Metabolic Syndrome: A Deep Learning Approach

2025-05-13

AI Summary

This study addresses the challenge of noninvasive, early screening for metabolic syndrome (MetS) to reduce reliance on conventional blood-based diagnostics. We propose a lightweight, end-to-end multimodal deep learning framework that jointly models wearable-derived heart rate time series and unstructured free-text exercise logs—both readily available in daily life. Specifically, we employ a BiLSTM-CNN architecture to extract semantic features from textual exercise descriptions and integrate them with temporal heart rate representations. The model incorporates SMOTE for class imbalance mitigation and SHAP for post-hoc interpretability. Under three-fold cross-validation, it achieves an AUROC of 0.806 and a recall of 76.3%. Interpretability analysis identifies the daily minimum heart rate and exercise-related semantic embeddings as the most discriminative features. Our approach establishes a novel, low-cost, and highly interpretable paradigm for MetS screening in resource-constrained settings.

Technology Category

• Machine Learning: Multimodal Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Metabolic syndrome (MetS) is a medication condition characterized by abdominal obesity, insulin resistance, hypertension and hyperlipidemia. It increases the risk of majority of chronic diseases, including type 2 diabetes mellitus, and affects about one quarter of the global population. Therefore, early detection and timely intervention for MetS are crucial. Standard diagnosis for MetS components requires blood tests conducted within medical institutions. However, it is frequently underestimated, leading to unmet need for care for MetS population. This study aims to use the least physiological data and free texts about exercises related activities, which are obtained easily in daily life, to diagnosis MetS. We collected the data from 40 volunteers in a nursing home and used data augmentation to reduce the imbalance. We propose a deep learning framework for classifying MetS that integrates natural language processing (NLP) and exercise monitoring. The results showed that the best model reported a high positive result (AUROC=0.806 and REC=76.3%) through 3-fold cross-validation. Feature importance analysis revealed that text and minimum heart rate on a daily basis contribute the most in the classification of MetS. This study demonstrates the potential application of data that are easily measurable in daily life for the early diagnosis of MetS, which could contribute to reducing the cost of screening and management for MetS population.

Problem

• Early diagnosis of Metabolic Syndrome using minimal data
• Integrating NLP and exercise monitoring for MetS detection
• Reducing screening costs with daily-life measurable data

Innovation

• Deep learning integrates NLP and exercise monitoring
• Uses minimal physiological data and free texts
• Data augmentation reduces imbalance in dataset