Edge-AI and Wearable Sensor Telemetry for Early Signal Detection of Cardiovascular Decompensation in Rural and Underserved U.S. Health Networks
- Authors
-
-
Sunday Sunday
Ladoke Akintola University of TechnologyAuthor
-
- Keywords:
- Edge Artificial Intelligence, Wearable Sensors, Cardiovascular Decompensation,Rural Health, Remote Patient Monitoring, Predictive Analytics
- Abstract
-
Cardiovascular disease remains the leading cause of mortality in the United States, with rural andunderserved populations experiencing disproportionately higher rates of adverse outcomes due tolimited access to continuous physiological monitoring and specialist care. Traditional approachesto detecting cardiovascular decompensation rely on episodic clinical assessments that fail tocapture the gradual physiological deterioration preceding acute events. This study addresses thecritical gap in early warning capabilities by developing and validating a hybrid Edge-AIframework for real-time detection of cardiovascular decompensation using wearable sensortelemetry. The proposed system integrates multimodal physiological data—including heart ratevariability, photoplethysmography waveforms, respiratory rate, and oxygen saturation—processed through a lightweight gradient-boosting machine learning pipeline optimized for edge deployment. Using retrospective data from 1,247 patients with heart failure across rural healthnetworks and prospective simulation validation, the framework achieved 89.4% accuracy (AUC= 0.93) in predicting decompensation events 4.2 hours before clinical recognition, with a falsealarm rate of 12.6%. The system demonstrated robust performance on resource-constrainedhardware (latency < 100ms, power consumption < 50mW), making it suitable for deployment inlow-infrastructure settings. These findings suggest that Edge-AI-enabled wearable telemetry canprovide clinically meaningful early warnings of cardiovascular deterioration, potentiallyreducing emergency admissions and improving outcomes in underserved communities. Theframework offers a scalable, privacy-preserving solution for extending advanced cardiacmonitoring capabilities to populations currently underserved by traditional healthcareinfrastructure.
- Cover Image
-
- Downloads
- Published
- 08/15/2026
- Section
- Articles
- License
-
Copyright (c) 2026 Sunday Sunday (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
Edge-AI and Wearable Sensor Telemetry for Early Signal Detection of Cardiovascular Decompensation in Rural and Underserved U.S. Health Networks. (2026). The Science Post, 2(3). https://www.thesciencepostjournal.com/index.php/tsp/article/view/227