Professor, Department of Electronics and Communication Engineering, Biluru Gurubasava Mahaswamiji Institute of Technology, Mudhol, India
Received: 14th Sep, 2025; Revised: 25th Oct, 2025; Accepted: 16th Nov, 2025; Available Online: 1st December, 2025
The increasing prevalence of cardiovascular diseases necessitates continuous monitoring systems that can support effective cardiac drug therapy with minimal latency and power consumption. Conventional cloud-based health monitoring solutions suffer from limitations such as high energy usage, communication delays, and privacy concerns. To address these challenges, this research proposes an edge-based Tiny Machine Learning (TinyML) framework for real-time cardiac drug response monitoring using embedded hardware software co-design. The proposed system integrates physiological signal acquisition, particularly electrocardiogram (ECG) and heart rate variability (HRV), with lightweight machine learning models deployed on resource-constrained microcontroller platforms. TinyML models are trained to analyze cardiac patterns and assess physiological responses associated with commonly prescribed cardiac drugs such as beta-blockers and anti-arrhythmic agents. Model optimization techniques, including quantization, pruning, and feature reduction, are employed to ensure a low memory footprint and energy efficiency suitable for wearable and implantable devices. The research emphasizes on-device inference, eliminating dependency on continuous cloud connectivity while preserving data privacy and enabling real-time decision support. Performance evaluation is conducted in terms of accuracy, latency, power consumption, and robustness under constrained hardware conditions. The outcome of this work aims to establish a scalable and energy-efficient TinyML architecture that can assist clinicians in personalized cardiac drug management and early detection of adverse cardiac events.
Keywords: TinyML, Cardiac Drug Monitoring, Embedded Systems, Edge AI, ECG Signal Processing, Low-Power Machine Learning, Wearable Healthcare Devices, Hardware Software Co-Design.
How to cite this article: Patil AP. Edge-Based TinyML Framework for Intelligent Cardiac Drug Response Monitoring Using Embedded Hardware Software Co-Design. Int J Drug Deliv Technol. 2026;16(1): 719-726; DOI: 10.25258/ijddt.16.1.75
Source of support: Nil.
Conflict of interest: None