Reduced lead system selection methodology for reliable standard 12-lead reconstruction targeting personalised remote health monitoring applications

摘要

Advanced wireless technology, high speed internet facility and availability of other communication systems can be used to provide the accessibility of state-of-the-art healthcare facilities to the patients in remote and rural areas for monitoring and diagnosis of cardiovascular diseases, one of the prime causes of human mortality today. Telemonitoring applications encounter technological constraints viz. bandwidth, storage and data transmission time due to which reduced lead (RL) ECG systems (containing three to four leads) are used. From the medical science perspective, cardiologists are accustomed to the standard 12-lead (S12) ECG system owing to its wide-spread acceptability and decades-long usage and these RL systems may prove to be insufficient for diagnosis. In this paper, we attempt to provide for the first time, to the best of our knowledge, a technical methodology to the medical practitioners for selection of such RL systems suitable for personalised remote health monitoring applications. Subsequently, a novel S12-lead ECG reconstruction methodology is also proposed which is shown to be more reliable than the state-of-the art lead reconstruction methodologies. In this study, along with Frank's vectorcardiographic system, reduced 3-lead systems consisting of leads Ⅰ, Ⅱ and one of the six precordial leads (V_1-V_6) leading to a total of six such reduced lead sub-systems are considered. Based on the proposed lead reconstruction methodology, these aforementioned reduced lead systems' performance are evaluated and compared comprehensively using R2 statistics, correlation and regression coefficients. Furthermore, comparison of ECG features extracted from the original and reconstructed standard leads from each of these reduced lead systems by our recently proposed time domain morphology and gradient algorithm using root mean square error has been reported and discussed. The advantages and disadvantages of using a particular RL system have been discussed in the context of remote health monitoring applications.