A Classification Model Based on an Adaptive Neuro-fuzzy Inference System for Disease Prediction

摘要: Disease prediction is now prevalent in the health industry due to need increase life expectancy of any human being. Diseases are different kinds like physical, mental, environmental, human-made. Recently, machine learning paving its path toward perfection field industry. Machine (ML) with artificial neural network (ANN) a useful tool for solving aspects complex real-time situation analysis that includes both biomedical and healthcare applications. The system can help eradicating problems faced by medical practitioners delivering unbiased results. Patients suffering unavailability experienced as well expensive be benefitted from this system. has been recently one most active research areas development computing environment hardware software many application highly problem definition. care sector them; it capable automation process saving time-consuming subjective nature. So, ML ANN-based processes provide unbiased, repeatable broader dimensionality nature data medicine reduces sample pathological cases made advanced ANN techniques clinical interpretation analysis. understanding disease detection mostly depend on number experts their expertise area problem, which not enough. requires expert highest level knowledge high degree correctness. It prone error, ML, method improve accuracy standard computer-based decision-making models tools behavior. traditional methods Bayesian network, Gaussian mixture model, hidden Markov model implemented recognition humans, animals, birds, etc., applied researchers have failed reach optimum competence. Many intelligent systems introduced identification diseases probabilistic decision tree, linear discriminant analysis, support vector machine. learning-based adaptive neuro-fuzzy inference next step evolution an network. In chapter, usefulness along ANFIS utility medico issue discussed.