article
Early detection of diabetic retinopathy is essential to prevent severe complications, yet clinical adoption of artificial intelligence tools is often hindered by a lack of explainability. To address this, an ensemble deep learning model was developed combining Convolutional Neural Networks, Long Short-Term Memory networks, Simple Recurrent Neural Networks, and XGBoost. The model was evaluated using the APTOS 2019 eye pack dataset. Shapley Additive exPlanations, an explainable artificial intelligence method, was incorporated to identify specific image regions influencing the decision-making process. The ensemble architecture achieved 95.63 percent accuracy, 97.79 percent precision, 93.64 percent recall, an F1-score of 98.79 percent, and an area under the curve of 97.75 percent, outperforming the standalone models. The integration of interpretability tools demonstrates which image features drive predictions, helping build trust in automated diagnostic screening and aiding personalised treatment planning.
Diabetic retinopathy can cause severe vision complications if not detected early. While artificial intelligence offers high diagnostic accuracy, clinicians often hesitate to adopt complex black-box systems. By pairing high-performing ensemble machine learning with explainability tools that highlight relevant features on retinal scans, this approach helps bridge the gap between algorithmic performance and clinical trust, potentially improving screening efficiency and personalised patient care.
This technology could be applied in clinical decision-support and screening software for eye care professionals and healthcare providers. It represents applied research tested on an open dataset rather than within an operational clinical workflow, placing it at an early development stage. Further validation across broader patient populations and real-world health systems would be necessary before integration into commercial diagnostic platforms.
AI-generated from the published abstract. Always read the original work before citing.
Detection of diabetic retinopathy (DR) as early as possible is vital in mitigating the complicated issues associated with the disease. Recent advances in artificial intelligence (AI), particularly deep learning (DL) techniques, have led to appreciable increase in the accuracy of predicting various disease classes. However, the challenge of AI models is the difficulty in providing insights into how and why a model arrives in attaining decision-making to facilitate trust and adoption in clinical settings. Therefore, this study aimed to enhance the detection rate of DR and explain the significant regions on the image for the model's overall performance. This study utilised Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, Simple Recurrent Neural Networks (SRNN), and XGBoost in an ensemble model (EM). Specifically, Shapley Additive exPlanations (SHAP), a popular Explainable Artificial Intelligence (XAI) technique was utilised to identify and provide insights to which parts of the images features that contribute to the model's overall performance. After a series of experiments using the APTOS 2019 eye pack dataset collected from the Kaggle repository to evaluate the performance of CNN, LSTM, SRNN, and XGBoost. The EM outperformed all the other models with 95.63% accuracy, 97.79% precision, 93.64% recall rate, 98.79% F1-score and 97.75% AUC score. Also, SHAP analysis revealed significant regions on the image that influenced predictions, thus showing how important interpretability was for the model. The results imply that the ensemble DL, particularly with XGBoost, enhances the detection of DR, thereby improving the efficiency of screening tests and supporting personalised treatment plans in clinical practice through integrating these advanced models with XAI tools, creating trust towards automated diagnostic systems.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.36108/laujet/5202.91.0110
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
