Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data set
BackgroundDiabetic retinopathy (DR) screening faces critical challenges in early detection due to its asymptomatic onset and the limitations of conventional prediction models. While existing studies predominantly focus on image-based AI diagnosis, there is a pressing need for accurate risk predictio...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-06-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2025.1591832/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849334435711811584 |
|---|---|
| author | Weijun Gong You Pu Tiao Ning Yan Zhu Gui Mu Jing Li |
| author_facet | Weijun Gong You Pu Tiao Ning Yan Zhu Gui Mu Jing Li |
| author_sort | Weijun Gong |
| collection | DOAJ |
| description | BackgroundDiabetic retinopathy (DR) screening faces critical challenges in early detection due to its asymptomatic onset and the limitations of conventional prediction models. While existing studies predominantly focus on image-based AI diagnosis, there is a pressing need for accurate risk prediction using structured clinical data. The purpose of this study was to develop, compare, and validate models for predicting retinopathy in diabetic patients via five traditional statistical models and deep learning models.MethodsOn the basis of 3,000 data points from the Diabetes Complications Data Set of the National Center for Population Health Sciences Data, the differences in the characteristics of patients with diabetes mellitus and diabetes combined with retinopathy were statistically analyzed using SPSS software. Five traditional machine learning models and a model based on deep neural networks (DNNs) were used to train models to assess retinopathy in diabetic patients.ResultsDeep learning-based prediction models outperformed traditional machine learning models, namely logistic regression, decision tree, naive Bayes, random forest, and support vector machine, on all the datasets and performed better in predicting retinopathy in diabetic patients (accuracy, 0.778 vs. 0.753, 0.630, 0.718, 0.758, 0.776, respectively; F1 score, 0.776 vs. 0.751, 0.602, 0.724, 0.755, 0.776, respectively; AUC, 0.833 vs. 0.822, 0.631, 0.769, 0.829, 0.831, respectively). To enhance the interpretability of the deep learning model, SHAP analysis was employed to assess feature importance and provide insights into the key drivers of retinopathy prediction.ConclusionDeep learning models can accurately predict retinopathy in diabetic patients. The findings of this study can be used for prevention and monitoring by allocating resources to high-risk patients. |
| format | Article |
| id | doaj-art-f8dd6735d68b44e3bed79b27879f8f6c |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-f8dd6735d68b44e3bed79b27879f8f6c2025-08-20T03:45:34ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-06-011210.3389/fmed.2025.15918321591832Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data setWeijun Gong0You Pu1Tiao Ning2Yan Zhu3Gui Mu4Jing Li5School of Mathematics Kunming University, Kunming University, Kunming, Yunnan, ChinaDepartment of Rehabilitation, Baoshan People’s Hospital, Baoshan, Yunnan, ChinaEngineering Research Center for Urban Modern Agriculture of Higher Education in Yunnan Province, School of Agriculture and Life Sciences, Kunming University, Kunming, Yunnan, ChinaSchool of Mathematics Kunming University, Kunming University, Kunming, Yunnan, ChinaSchool of Mathematics Kunming University, Kunming University, Kunming, Yunnan, ChinaEngineering Research Center for Urban Modern Agriculture of Higher Education in Yunnan Province, School of Agriculture and Life Sciences, Kunming University, Kunming, Yunnan, ChinaBackgroundDiabetic retinopathy (DR) screening faces critical challenges in early detection due to its asymptomatic onset and the limitations of conventional prediction models. While existing studies predominantly focus on image-based AI diagnosis, there is a pressing need for accurate risk prediction using structured clinical data. The purpose of this study was to develop, compare, and validate models for predicting retinopathy in diabetic patients via five traditional statistical models and deep learning models.MethodsOn the basis of 3,000 data points from the Diabetes Complications Data Set of the National Center for Population Health Sciences Data, the differences in the characteristics of patients with diabetes mellitus and diabetes combined with retinopathy were statistically analyzed using SPSS software. Five traditional machine learning models and a model based on deep neural networks (DNNs) were used to train models to assess retinopathy in diabetic patients.ResultsDeep learning-based prediction models outperformed traditional machine learning models, namely logistic regression, decision tree, naive Bayes, random forest, and support vector machine, on all the datasets and performed better in predicting retinopathy in diabetic patients (accuracy, 0.778 vs. 0.753, 0.630, 0.718, 0.758, 0.776, respectively; F1 score, 0.776 vs. 0.751, 0.602, 0.724, 0.755, 0.776, respectively; AUC, 0.833 vs. 0.822, 0.631, 0.769, 0.829, 0.831, respectively). To enhance the interpretability of the deep learning model, SHAP analysis was employed to assess feature importance and provide insights into the key drivers of retinopathy prediction.ConclusionDeep learning models can accurately predict retinopathy in diabetic patients. The findings of this study can be used for prevention and monitoring by allocating resources to high-risk patients.https://www.frontiersin.org/articles/10.3389/fmed.2025.1591832/fulldiabetic retinopathydeep learning modelprediction modelsmodel comparisonmachine learning |
| spellingShingle | Weijun Gong You Pu Tiao Ning Yan Zhu Gui Mu Jing Li Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data set Frontiers in Medicine diabetic retinopathy deep learning model prediction models model comparison machine learning |
| title | Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data set |
| title_full | Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data set |
| title_fullStr | Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data set |
| title_full_unstemmed | Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data set |
| title_short | Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data set |
| title_sort | deep learning for enhanced prediction of diabetic retinopathy a comparative study on the diabetes complications data set |
| topic | diabetic retinopathy deep learning model prediction models model comparison machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2025.1591832/full |
| work_keys_str_mv | AT weijungong deeplearningforenhancedpredictionofdiabeticretinopathyacomparativestudyonthediabetescomplicationsdataset AT youpu deeplearningforenhancedpredictionofdiabeticretinopathyacomparativestudyonthediabetescomplicationsdataset AT tiaoning deeplearningforenhancedpredictionofdiabeticretinopathyacomparativestudyonthediabetescomplicationsdataset AT yanzhu deeplearningforenhancedpredictionofdiabeticretinopathyacomparativestudyonthediabetescomplicationsdataset AT guimu deeplearningforenhancedpredictionofdiabeticretinopathyacomparativestudyonthediabetescomplicationsdataset AT jingli deeplearningforenhancedpredictionofdiabeticretinopathyacomparativestudyonthediabetescomplicationsdataset |