Automated detection of diabetic subject using pre-trained 2D-CNN models with frequency spectrum images extracted from heart rate signals

• Published in: Computers in biology and medicine Vol. 113; p. 103387
• Main Authors: Yildirim, Ozal, Talo, Muhammed, Ay, Betul, Baloglu, Ulas Baran, Aydin, Galip, Acharya, U. Rajendra
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.10.2019; Elsevier Limited
• Subjects: Accuracy; Annotations; Artificial intelligence; Automation; Classification; Conflicts of interest; Data processing; Datasets; Decision trees; Deep learning; Diabetes; Diabetes mellitus; Diabetic neuropathy; Diabetic retinopathy; EKG; Electrocardiography; Fourier transforms; Frequency spectrum; Heart rate; Heart rate signals; Image detection; Insulin; Machine learning; Medical imaging; Model accuracy; Model testing; Neural networks; Performance evaluation; Signal analysis; Signal processing; Transfer learning; Two dimensional models; Wavelet transforms; Weighting; Deep learning; Heart rate signals; Transfer learning; Diabetes mellitus

In this study, a deep-transfer learning approach is proposed for the automated diagnosis of diabetes mellitus (DM), using heart rate (HR) signals obtained from electrocardiogram (ECG) data. Recent progress in deep learning has contributed significantly to improvement in the quality of healthcare. In...