A Novel Proposal for Deep Learning-Based Diabetes Prediction: Converting Clinical Data to Image Data

Diabetes, one of the most common diseases worldwide, has become an increasingly global threat to humans in recent years. However, early detection of diabetes greatly inhibits the progression of the disease. This study proposes a new method based on deep learning for the early detection of diabetes....

Full description

Saved in:
Bibliographic Details
Published inDiagnostics (Basel) Vol. 13; no. 4; p. 796
Main Authors Aslan, Muhammet Fatih, Sabanci, Kadir
Format Journal Article
LanguageEnglish
Published Switzerland MDPI AG 01.02.2023
MDPI
Subjects
Accuracy
Algorithms
Artificial intelligence
Big Data
Classification
convolutional neural network
Data mining
Datasets
Deep learning
Diabetes
diabetes prediction
Disease
Electronic data processing
Feature selection
Health aspects
Insulin resistance
Machine learning
Medical diagnosis
Medical records
Neural networks
numeric-to-image
Pancreas
PIMA dataset
Support vector machines
Technology application
Womens health
Turkey
PIMA dataset
diabetes prediction
support vector machines
numeric-to-image
convolutional neural network
Online AccessGet full text

Cover

More Information
Summary:Diabetes, one of the most common diseases worldwide, has become an increasingly global threat to humans in recent years. However, early detection of diabetes greatly inhibits the progression of the disease. This study proposes a new method based on deep learning for the early detection of diabetes. Like many other medical data, the PIMA dataset used in the study contains only numerical values. In this sense, the application of popular convolutional neural network (CNN) models to such data are limited. This study converts numerical data into images based on the feature importance to use the robust representation of CNN models in early diabetes diagnosis. Three different classification strategies are then applied to the resulting diabetes image data. In the first, diabetes images are fed into the ResNet18 and ResNet50 CNN models. In the second, deep features of the ResNet models are fused and classified with support vector machines (SVM). In the last approach, the selected fusion features are classified by SVM. The results demonstrate the robustness of diabetes images in the early diagnosis of diabetes.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2075-4418
2075-4418
DOI:10.3390/diagnostics13040796