Toward Affordable and Non-Invasive Detection of Hypoglycemia: A Machine Learning Approach

2025-09-22

AI Summary

Current hypoglycemia monitoring for type 1 diabetes mellitus (T1DM) is costly and invasive. Method: This study proposes a non-invasive, low-cost classification framework leveraging galvanic skin response (GSR) time-series signals—readily acquired via wearable devices—to distinguish hypoglycemic from euglycemic states. Seven machine learning models—including LSTM and XGBoost—were trained and evaluated on the OhioT1DM dataset. Contribution/Results: The LSTM model achieved perfect hypoglycemia recall (1.00) with an F1-score confidence interval of [0.611, 0.745]; XGBoost attained a robust 0.54 recall despite severe class imbalance. Rigorous confidence interval estimation and cross-model comparison confirm GSR’s significant discriminative power for glycemic state classification. This work establishes a novel, feasible paradigm for resource-constrained, non-invasive glucose monitoring.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Diabetes mellitus is a growing global health issue, with Type 1 Diabetes (T1D) requiring constant monitoring to avoid hypoglycemia. Although Continuous Glucose Monitors (CGMs) are effective, their cost and invasiveness limit access, particularly in low-resource settings. This paper proposes a non-invasive method to classify glycemic states using Galvanic Skin Response (GSR), a biosignal commonly captured by wearable sensors. We use the merged OhioT1DM 2018 and 2020 datasets to build a machine learning pipeline that detects hypoglycemia (glucose < 70 mg/dl) and normoglycemia (glucose > 70 mg/dl) with GSR alone. Seven models are trained and evaluated: Random Forest, XGBoost, MLP, CNN, LSTM, Logistic Regression, and K-Nearest Neighbors. Validation sets and 95% confidence intervals are reported to increase reliability and assess robustness. Results show that the LSTM model achieves a perfect hypoglycemia recall (1.00) with an F1-score confidence interval of [0.611-0.745], while XGBoost offers strong performance with a recall of 0.54 even under class imbalance. This approach highlights the potential for affordable, wearable-compatible glucose monitoring tools suitable for settings with limited CGM availability using GSR data. Index Terms: Hypoglycemia Detection, Galvanic Skin Response, Non Invasive Monitoring, Wearables, Machine Learning, Confidence Intervals.

Problem

• Detecting hypoglycemia non-invasively using Galvanic Skin Response data
• Developing affordable glucose monitoring alternatives to expensive CGMs
• Creating wearable-compatible tools for low-resource healthcare settings

Innovation

• Non-invasive hypoglycemia detection using Galvanic Skin Response
• Machine learning pipeline with seven models including LSTM and XGBoost
• Achieves high recall for hypoglycemia classification using GSR alone