Real-Time Detection of Myocardial Infarction Onset Using Communication Network-Enabled Recursive Bayesian Updating

Myocardial infarction (MI) is one of the leading cardiovascular pathologies that often result in mortality. One of the methods to improve patient outcomes and lower mortality in MI occurrence is early detection. This requires access to individuals' real-time vital cardiac signs to detect the onset of MI. However, most known vital cardiac signs and biomarkers of MI are either not always present in MI episodes or are not unique to MI. Hence, there is a need to develop a framework that can uniquely determine the onset of MI. This work proposes a framework for early detection of the MI onset that leverages the MI biomarker sensing capability of the Graphene-field effect transistor (G-FET), the remote vital cardiac indicators transmission ability of a communication network, and the real-time adaptive potential of recursive Bayesian updating based on an individual's changing condition. The resultant posterior probability associated with the Bayesian updating, which is dynamically modified as new data is received in real-time, indicates the MI onset. This ensures early detection of MI. Considering an MI onset detection window of 30 to 60 minutes as a critical time to ensure that MI effects are salvageable, numerical results are provided. The numerical results demonstrate that the proposed framework provides early detection of MI onset, crucial to salvaging its effects and lowering mortality. The influence of some of the design parameters on the system performance is also evaluated.