<![CDATA[Cardiovascular disease (CVD) is currently the top global cause of death, and is caused by complex interactions between physiological, behavioral, and environmental factors. Although wearable health technologies used in conjunction with artificial intelligence (AI) have made it possible to monitor cardiovascular functions continuously, most current systems only monitor physiological signals, while neglecting environmental factors that play important roles in cardiovascular risk. This study is a proposal for the integrated process of an Artificial Intelligence-driven framework to combine with wearable health data and environmental management analytics for real-time cardiovascular disease prevention measures. Building on established deep learning methodologies for wearable-based monitoring - in this case, Long Short Term Memory (LSTM) and Convolution neural network (CNN) models - the approach also includes environmental variables as air quality indices, ambient temperature, humidity, and urban stress indicators (Miah, M. A., et al., 2019). Multimodal time series data are preprocessed, synchronized, and analyzed by a hybrid convergent CNN & one-dimensional long short-term memory network to obtain personalized cardiovascular risk prediction. Experimental results have shown that combining environmental analytics predicts more accurately and with fewer false alarms (Dominique, Dyvand & Mote, 2019), particularly in poor environmental conditions. The proposed framework proposes to further develop preventive cardiology by facilitating context-aware, personalized, and scalable cardiovascular risk management that offers significant implications in precision public health, smart city, and sustainable healthcare systems.]]>
Copyrights © 2024
