A low cost IOT based wearable stroke prediction device for stroke risk groups
Kalonde, Florence Peace
MetadataShow full item record
Stroke is a prevalent and devastating condition that requires urgent medical attention. Detecting stroke risk in high-risk individuals is crucial for early intervention and prevention. This research aims to develop a low-cost IoT-based wearable device that can predict stroke occurrence. The significance of this work lies in the potential to provide an accessible and affordable solution for identifying individuals at risk of stroke, thereby improving their chances of receiving timely medical assistance. The primary problem addressed in this research is the challenge of predicting stroke in high-risk individuals. Stroke has a substantial impact on individuals and society, leading to disabilities, increased healthcare costs, and reduced quality of life. Current methods for stroke prediction often require expensive and specialized equipment, limiting their accessibility and widespread implementation. The main argument of this study is that an IOT-based wearable device utilizing photoplethysmography (PPG) can offer a cost-effective solution to detect stroke risk. The research methodology involved utilizing an Arduino Nano RP2040 and a MAX30102 sensor to collect physiological parameters indicative of stroke risk, such as pulse pressure and mean arterial pressure. The collected data were processed to assess the likelihood of stroke occurrence. The device transmitted the measured parameters via Wi-Fi connectivity to an email address, enabling further analysis and monitoring. The key results of this research demonstrate the successful development of a low-cost IoT based wearable device for stroke prediction. The device effectively extracted relevant parameters using PPG technology, enabling assessment of stroke risk. Its affordability makes it accessible for wider implementation, while the ability to transmit data remotely enhances usability and convenience. These findings highlight the potential of IoT technology in revolutionizing stroke prediction and prevention. This study presents a cost-effective, low-cost IoT-based wearable device for stroke prediction, aiding high-risk patients without specialist facilities. This leads to improved preventive measures, healthcare outcomes, and reduced costs. Future research should prioritize clinical studies and collaboration with experts to validate the device's accuracy and reliability.