CARDIAC ADVANCED ARRYTHMIA PREDICTION SYSTEMS- CAAPS

Abstract

There is a constant search for novel methods of classi\uf001cation and predicting cardiac rhythm disorders or arrhythmias. We prefer to classify them as\nwide complex tachyarrhythmia s or ventricular arrhythmias inclusive of malignant ventricular arrhythmias which with hemodynamic compromise\nis usually life threatening. Long term and fatality predictions warranting AICD implantation are already available. We have a novel method and\nrobust algorithm with preprocessing and optimal feature selection from ECG signal analysis for such rhythm disorders. Variability of ECG\nrecording makes predictability analysis challenging especially when execution time is of prime importance in tackling resuscitative attempts for\nMVA. Noisy data needs \uf001ltering and preprocessing for effective analysis. Portable devices need more of this \uf001ltering prior to data input.\nDeterministic probabilistic \uf001nite state automata (DPFA) which generates a probability strings from the broad morphologic patterns of an ECG can\ngenerate a classi\uf001er data for the algorithm without preprocessing for atrial high rate episodes (AHRE). DPFA can be effectively used for atrial\ntachyarrhythmias for predictive analysis. The method we suggest is use of optimal classi\uf001er set for prediction of malignant ventricular arrhythmias\nand use of DFPA for atrial arrhythmias. Here traditional practices of heart rate variability based support vector machine (SVM), discrete wavelet\ntransform (DWT), principal component analysis (PCA), deep neural network (DNN), convoutional neural network (CNN) or CNN with long term\nmemory (LSTM) can be outperformed.\nAICD - automatic implantable cardiac de\uf001brillator, MVA - Malignant Ventricular Arrhythmias, VT - ventricular tachycardia, VF - ventricular\n\uf001brillation,DFPA deterministic probabilistic \uf001nite state automata, SVM -Support Vector Machine, DWT discrete wavelet transform, PCA\nprincipal component analysis, DNN deep neural network, CNN convoutional neural network, Convoutional LSTM Long short term\nmemory,RNN recurrent neural network