Workflow for Medical Data Classification and Analysis

An approach for automated knowledge extraction and decision-making from medical images through a workflow for preprocessing of incoming X-ray images, analysis, classification and evaluation of the results is presented in this paper. The designed algorithm for analysis of medical X-rays images is based on machine learning and consists of three main phases: preprocessing of training and validation datasets, medical images classification utilizing Logistic Regression, Naive Bayes, SVM methods, evaluation of the model. A workflow was developed to process and analyze datasets of lung X-ray images containing four classes, and determine classification accuracy by examining performance evaluation parameters.