Booth Id:
ROBO028
Category:
Robotics and Intelligent Machines
Year:
2024
Finalist Names:
Thomas, Ethan (School: Ransom Everglades School)
Abstract:
In the contemporary landscape of medical technology, the integration of machine learning (ML) with wearable electrocardiograms (ECGs) presents a groundbreaking approach to cardiovascular disease detection. This study expands the abilities of ML algorithms in interpreting ECG data from wearable devices for early and accurate identification of cardiovascular anomalies. Traditional methods of cardiovascular monitoring often require invasive procedures or stationary equipment, limiting their accessibility and viability for early diagnosis. In contrast, wearable ECGs offer continuous, non-invasive monitoring. The application of ML models such as convolutional neural networks (CNNs) enables clinically viable interpretation of these datasets without a clinician, overcoming the severe scaleability limitations that currently plague the wearable ECG market. By targeting the early detection of cardiovascular irregularities, potentially reducing the incidence of late-diagnosis related complications. Moreover, the predictive capabilities of ML models facilitate proactive healthcare interventions, improving patient outcomes and reducing healthcare costs. Our analysis further discusses the potential of these models in personalizing patient care, considering individual health profiles and historical data for tailored treatment strategies. The amalgamation of wearable ECG technology with advanced ML models thus marks a significant stride towards innovative, efficient, and patient-centric approaches in cardiovascular healthcare.