Diagnosis of Parkinson’s Disease Using a Neural Network Based on QPSO

Abstract

Disease diagnosis and analysis can be a strenuous task as there are a number of reports and test results that need to be considered and analyzed to detect the patterns of the said disease. The presented paper offers an effective solution for the same with the help of a neural network trained using the concepts of quantum computing and evolutionary algorithms. To the best of our knowledge, neural networks trained using a combination of quantum and evolutionary principles are introduced for the first time for the diagnosis of any disease. The proposed neural network is a three-layered network that outputs the probability of disease presence which is then used to classify the patient as diseased or healthy. The resulting solution is an amalgam of the said technologies and inherits their positives such as robustness, time and space efficiency, and noise immunity. The performance of the model is tested against a voice defect analysis dataset which is often used for the diagnosis of Parkinson’s disease. The results show that QPSO is a powerful model with an accuracy of 93.75% and can be used for early detection of a variety of diseases.