Predicting Type 2 Diabetes Using an Electronic Nose-based Artificial Neural Network Analysis
Title | Predicting Type 2 Diabetes Using an Electronic Nose-based Artificial Neural Network Analysis |
Publication Type | Journal Article |
Year of Publication | 2002 |
Authors | Mohamed E.I., Linder R., Perriello G., Di Daniele N., Pöppl S.J., De Lorenzo A. |
Journal | Diabetes, nutrition & metabolism |
Volume | 15 |
Issue | 4 |
Pages | 215-21 |
Date Published | 2002 Aug |
Publication Language | eng |
ISSN | 0394-3402 |
Keywords | Aged, Blood Glucose, Body Mass Index, Breath Tests, Diabetes Mellitus, Type 2, Fasting, Female, Glycosuria, Humans, Logistic Models, Male, Middle Aged, Neural Networks (Computer), Nose, Odors, Proteinuria, Sensitivity and Specificity |
Abstract | Diabetes is a major health problem in both industrial and developing countries, and its incidence is rising. Although detection of diabetes is improving, about half of the patients with Type 2 diabetes are undiagnosed and the delay from disease onset to diagnosis may exceed 10 yr. Thus, earlier detection of Type 2 diabetes and treatment of hyperglycaemia and related metabolic abnormalities is of vital importance. The objectives of the present study were to examine urine samples from Type 2 diabetic patients and healthy volunteers using the electronic nose technology and to evaluate possible application of data classification methods such as self-learning artificial neural networks (ANN) and logistic regression (LR) in comparison with principal components analysis (PCA). Urine samples from Type 2 diabetic patients and healthy controls were processed randomly using a simple 8-sensors electronic nose and individual electronic nose patterns were qualitatively classified using the "Approximation and Classification of Medical Data" (ACMD) network based on 2 output neurons, binary LR analysis and PCA. Distinct classes were found for Type 2 diabetic subjects and controls using PCA, which had a 96.0% successful classification percentage mean while qualitative ANN analysis and LR analysis had successful classification percentages of 92.0% and 88.0%, respectively. Therefore, the ACMD network is suitable for classifying medical and clinical data. |
PubMed Link | |
Alternate Journal | Diabetes Nutr. Metab. |