Automated diagnosis of cardiac state in healthcare systems using computational intelligence

A study is presented for the diagnosis of a patient's heart conditions using recorded heart sounds and Computational Intelligence (CI) techniques. The digitally recorded heart sound signals are processed through Continuous Wavelet Transform (CWT) to extract time?frequency features for normal and abnormal heart conditions. The wavelet energy distributions are used as inputs to classifiers based on soft computing techniques such as Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Genetic Algorithms (GAs) for diagnosis of heart conditions. The number and the parameters of Membership Functions (MFs) used in ANFIS along with the features from wavelet energy distribution are selected using GAs, maximising the diagnosis success. ANFIS with GAs (GA-ANFIS) are trained with a subset of data with known heart conditions. The trained GA-ANFIS are tested using the other set of data (testing data), not used in training. The results are compared with Artificial Neural Network (ANN) and GA (GA-ANN). The results show the effectiveness of the proposed approach in automated diagnosis of cardiac state in healthcare systems.