Analysis of computational techniques for diabetes diagnosis using the combination of iris-based features and physiological parameters

摘要: Digital image processing and advanced machine vision techniques are popular for the diagnosis of disease(s) in biomedical science. This paper presents a detailed comparative analysis learning-based classification to diagnose type 2 diabetes using combination iris-based features physiological parameters. A set 334 subjects investigated which divided into diabetic non-diabetic groups. Moreover, group is classified three different subgroups according duration state. Statistical features, gray-level co-occurrence matrix, run length matrix-based extracted from specific areas iris. Nine classifiers application selected, subsequently, six parameters (accuracy, precision, sensitivity, specificity, F-score, area under curve) each classifier analyzed. The provided promising results with more than 95% accuracy. proposed technique can be used as noninvasive non-contact tool help find out patients prevalence diabetes.