Frank vectorcardiographic system from standard 12 lead ECG. an effort to enhance cardiovascular diagnosis

Background: Vectorcardiogram (VCG) has been repeatedly found useful for clinical investigations. It may not substitute but complement Standard 12-Lead (S12) ECG. There was tremendous research between 1950s to mid-1980s on VCG in general and Frank's System in particular, however, in last three decades it has been dropped as a routine cardiac test, the major reasons being unconventional electrode placements which required training of the physicians, greater number of electrodes involved when used to supplement S12 system and additional hardware complexity involved, at least in the early days. Although it lost the interest of cardiologists, the engineering community has adopted the VCG as a tool for interdisciplinary research. We envisage that, if accurate Frank's VCG system is made available avoiding the aforementioned limitations, VCG will complement S12 system in diagnosis of cardiovascular diseases (CVDs). Methods and results: In this paper, we propose a methodology to construct Frank VCG from S12 system using Principal Component Analysis (PCA). We have compared our work with state-of-the-art Inverse Dower Transform (IDT) and Kors Transform (KT). Mean R(2) statistics and correlation coefficient values, obtained upon comparison of reconstructed and originally measured Frank's leads, for CSE multilead (CSEDB) and PhysioNet's PTBDB databases using our proposed method, IDT and KT were found to be (73.7%,0.869), (57.6%,0.788) and (56.2%,0.781) respectively. From remote healthcare perspective, a reduced 2-3 lead system is desired and Frank lead system seems to be promising as shown by previous works. However, cardiologists are accustomed to S12 system due to its widespread usage and derived Frank lead system might not be sufficient. Hence, to bridge the gap, we have presented the results of personalized reconstruction of S12 system from derived VCG, obtained using proposed PCA-based method and compared it with results obtained when originally measured Frank leads were used. Conclusions: The proposed methodology, without any modification in the current acquisition system, can be used to obtain Frank VCG from S12 system to complement it in CVD diagnosis. Omnipresent computerized machines can readily apply the proposed methodology and thus, can find widespread clinical application.