Integrated wearable PPG: a multi-vital sign monitoring based on group sparse mode decomposition framework in remote health care using PPG signal.

Monitoring vital signs using a photoplethysmogram (PPG) signal has gained considerable attention, allowing users to monitor anyone, anywhere, and anytime with an objective. In recent years, advances in wearable technology and signal processing techniques have paved the way for accurate and reliable vital sign monitoring using PPG signals. Early detection of cardiovascular diseases can help the physician treat the disease promptly; thus, realtime monitoring of vital signs has emerged. Any deviation in the threshold value of vital signs can indicate potential threats to the cardiovascular system. The need to monitor vital signs in realtime using wearable devices has attracted the interest of the healthcare industry in developing simple and efficient vital sign estimation algorithms. This research introduces a framework to estimate the following important vital signs: heart rate (HR), respiratory rate (RR), blood pressure (BP), and blood oxygen saturation (SpO2), concurrently by overcoming the limitations posed by state-of-the-art techniques that primarily focus on individual or two vital sign estimations. Our proposed approach leverages signal processing techniques to determine the above-mentioned vital signs seamlessly and accurately. This innovation enhances the efficiency of vital sign monitoring and presents a unified solution for comprehensive health assessment. The widespread use of wearable devices for monitoring realtime health status in everyday life manifests in using PPG sensor-enabled wearable devices to perform more complex computational tasks. To date, the algorithms proposed to process an input PPG signal often use multiple processing steps to estimate any vital signs. This can increase the computational complexity of these algorithms, making it challenging to deploy devices with limited computational resources. The proposed work introduces a computationally efficient framework to estimate all four vital signs using the signal framework. The experimental results obtained with the proposed framework demonstrate that the proposed work outperforms the state-of-the-art estimation accuracy and computational complexity.