Diabetes Mellitus Prediction and Severity Level Estimation Using OWDANN Algorithm

• Published in: Computational intelligence and neuroscience Vol. 2021; no. 1; p. 5573179
• Main Authors: R, Annamalai, R, Nedunchelian
• Format: Journal Article
• Language: English
• Published: United States Hindawi 2021; John Wiley & Sons, Inc
• Subjects: Algorithms; Carbohydrates; Datasets; Decision trees; Deep learning; Diabetes; Diabetes mellitus; Diabetes Mellitus - diagnosis; Diabetes Mellitus - epidemiology; Discriminant analysis; Disease prevention; Efficiency; Feature extraction; Fuzzy sets; Glucose; Humans; Insulin; Labeling; Machine learning; Neural networks; Outliers (statistics); Performance evaluation; Predictions; Risk analysis; Risk factors; Stroke; Support vector machines
• ISSN: 1687-5265; 1687-5273; 1687-5273
• DOI: 10.1155/2021/5573179

Today, diabetes is one of the most prevalent, chronic, and deadly diseases in the world owing to some complications. If accurate early diagnosis is feasible, the risk factor and incidence of diabetes may be greatly decreased. Diabetes prediction is stable and reliable, since there are only minimal labelling evidence and outliers found in the datasets of diabetes. Numerous works coped with diabetes disease prediction and provided the solution. But the existing methods proffered low accuracy detection and consumed more training time. So, this paper proposed an OWDANN algorithm for diabetes mellitus disease prediction and severity level estimation. The proposed system mainly consists of two phases, namely, disease prediction and severity level estimation phase. In the disease prediction phase, the preprocessing is performed for the Pima dataset. Then, the features are extracted from the preprocessed data, and finally, the classification step is performed by using OWDANN. In the severity level estimation phase, the diabetes positive dataset is preprocessed first. Then, the features are extracted, and lastly, the severity level is predicted using GDHC. The extensive experimental results showed that the proposed system outperforms with 98.97% accuracy, 94.98% sensitivity, 95.62% specificity, 97.02% precision, 93.84% recall, 9404% f-measure, 0.094% FDR, and 0.023% FPR compared with the state-of-the-art methods.