Data-Driven Decision-Making for Classification of Diabetic Retinopathy Using Convolutional Neural Network (CNN) in a Clinical Decision Support System

DOI

10.2991/978-94-6463-589-8_33How to use a DOI?

Keywords

Diabetic Retinopathy; Convolutional Neural Network (CNN); Res Net-50; Clinical Decision Support System (CDSS)

Abstract

Data-driven decision-making is getting more attention since its modelling core depends on data availability, rather than long and costly processes of getting data and requirements from domain experts, patients, or decision-makers. The current practice for detecting diabetic retinopathy is conducted manually by ophthalmologists. Diabetes may cause a serious eye complication issue called diabetic retinopathy. The procedure is time-consuming in getting eye examinations where only a limited number of patients can be examined. Therefore, deep learning techniques such as convolutional neural networks (CNN) can be employed to help with faster detection of diabetic retinopathy. The architecture of CNN including ResNet-50 can classify the fundus images of diabetic retinopathy. ResNet50 leverages transfer learning, which helps with better generalisation. The APTOS 2019 dataset is acquired and undergoes preprocessing to increase the quality of fundus images such as cropping, contrast enhancement, performing oversampling and data augmentation. Training and testing are necessary to improve the accuracy of using ResNet-50 by different attributes. The model’s performance is then evaluated using evaluation metrics and has achieved a high accuracy of 87.0%. A clinical decision support system (CDSS) using the model is developed as the proof-of-concept for this research.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ahmad Faiz Ghazali
AU  - Nuriyah Mohamad Zakaria
AU  - Azliza Mohd Ali
PY  - 2024
DA  - 2024/12/01
TI  - Data-Driven Decision-Making for Classification of Diabetic Retinopathy Using Convolutional Neural Network (CNN) in a Clinical Decision Support System
BT  - Proceedings of the International Conference on Innovation & Entrepreneurship in Computing, Engineering & Science Education (InvENT 2024)
PB  - Atlantis Press
SP  - 360
EP  - 370
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-589-8_33
DO  - 10.2991/978-94-6463-589-8_33
ID  - Ghazali2024
ER  -