Related Experiment Video
Updated: Dec 31, 2025
05:03
Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
Published on: December 11, 2019
9.0K
Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection
Mihaela Porumb1, Saverio Stranges2,3,4, Antonio Pescapè5
1School of Engineering, University of Warwick, Coventry, CV4 7AL, UK.
Scientific Reports
|January 15, 2020
Summary
This study introduces an AI-powered system to detect nocturnal hypoglycemia using electrocardiogram (ECG) signals from wearable devices. Personalized analysis of ECG data enables real-time, non-invasive detection of low blood glucose events.
Area of Science:
- Biomedical Engineering
- Cardiology
- Artificial Intelligence in Medicine
Background:
- Monitoring blood glucose is vital for managing diabetes and preventing complications.
- Hypoglycemia, or low blood glucose, can cause serious health issues and affects heart electrophysiology.
- Previous ECG-based hypoglycemia detection systems struggled with individual variations.
Purpose of the Study:
- To develop an AI-driven, personalized approach for detecting nocturnal hypoglycemia using non-invasive ECG data.
- To overcome inter-subject heterogeneity in ECG signals for reliable hypoglycemia detection.
- To create a visualization tool for understanding AI's detection process in ECG.
Main Methods:
- Utilized a personalized medicine approach combined with Artificial Intelligence (AI).
- Analyzed raw ECG signals from wearable devices in healthy individuals over 14 days.
- Developed a visualization method to identify ECG components linked to hypoglycemia.
Main Results:
- Successfully detected nocturnal hypoglycemia using short ECG signal excerpts.
- Demonstrated the effectiveness of AI in personalized hypoglycemia detection.
- Provided a visualization tool to explain AI's analysis of ECG signals during hypoglycemic events.
Conclusions:
- AI and personalized medicine enable reliable, real-time, non-invasive detection of hypoglycemia via ECG.
- The developed visualization method enhances the interpretability of AI-based diagnostic tools.
- This approach paves the way for advanced wearable systems for continuous glucose monitoring and alerting.
Related Concept Videos
01:15Hypoglycemia and Glucagon
735
Without prolonged fasting, healthy individuals maintain blood glucose levels above 3.5 mM due to a well-adapted neuroendocrine counterregulatory system that effectively prevents acute hypoglycemia, a potentially life-threatening condition. The primary clinical scenarios for hypoglycemia encompass diabetes treatment, inappropriate production of endogenous insulin or insulin-like substances by tumors, and the use of glucose-lowering agents in non-diabetic individuals. Notably, hypoglycemia in the...
735
01:30Pulse rhythm
1.3K
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
1.3K
01:30Hypertension III: Clinical Manifestations and Diagnostic Studies
385
Hypertension is asymptomatic and also referred to as the "silent killer" until it progresses to a severe stage or causes target organ disease. Patients may experience symptoms stemming from the strain on blood vessels and tissues in various organs or the heart's increased workload.Physical exams might show no abnormalities other than high blood pressure. Signs of vascular damage, when present, correspond to the organs supplied by the affected vessels, leading to target organ damage. For...
385