{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T18:23:42Z","timestamp":1787250222887,"version":"build-2736575974"},"reference-count":68,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Higher Education Commission","award":["20-17042\/NRPU\/R&D\/HEC\/2021-2020"],"award-info":[{"award-number":["20-17042\/NRPU\/R&D\/HEC\/2021-2020"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Automated diabetic retinopathy (DR) screening has seen extensive research progress, yet its clinical adoption remains limited, largely due to insufficient attention to model generalizability across diverse populations and imaging conditions. Existing studies often overlook the role of dataset biases, arising from demographic, acquisition, and preprocessing variations that undermine robustness in real-world settings. To address this critical gap, we propose a comprehensive generalizability analysis framework that systematically categorizes dataset biases, evaluates their impact on performance, and introduces robust inter-dataset comparison metrics. The framework is metric-agnostic and extensible to multi-class severity grading, with stage-wise BAG formulations introduced to support more detailed clinical evaluation. Using one primary (EyePACS) and nine secondary datasets, we assessed the generalizability of two distinct architectures: a convolutional neural network (MobileNetV2) and a transformer-based model (CvT). Performance was evaluated through intra-group measures (accuracy, sensitivity, specificity, and AUC) and a newly proposed Bias-Adjusted Generalization (BAG) index designed to quantify resilience to bias-induced domain shifts. Results demonstrate that CvT consistently outperformed MobileNetV2, achieving an average accuracy of 87% and a BAG index of 0.94, compared to MobileNetV2\u2019s 78% accuracy and BAG index of 0.91. Gradient-based explainability visualizations further confirm that both models attend to clinically relevant retinal regions, with architectural differences in activation patterns consistent with their respective generalizability profiles. These findings highlight the inherent bias resilience of transformer architectures, while highlighting their computational demands as a barrier to deployment in low-resource environments. Importantly, the study suggests that integrating transformer-inspired mechanisms into lightweight CNNs could yield clinically scalable models with both efficiency and robustness. Our framework offers a standardized approach for bias-aware evaluation, providing actionable insights for developing equitable, generalizable, and resource-adaptable AI solutions for DR screening.<\/jats:p>","DOI":"10.1371\/journal.pone.0351225","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T17:26:38Z","timestamp":1787246798000},"page":"e0351225","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["A generalizability analysis framework for bias resilience in convolution neural network and transformer models for diabetic retinopathy screening"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2767-3139","authenticated-orcid":true,"given":"Majida","family":"Kazmi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3697-4010","authenticated-orcid":true,"given":"Bisma","family":"Imran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saad A.","family":"Qazi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5100-3189","authenticated-orcid":true,"given":"M. A. Rehman","family":"Siddiqui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"pone.0351225.ref001","volume-title":"IDF Diabetes Atlas","author":"International Diabetes Federation","year":"2025"},{"issue":"11","key":"pone.0351225.ref002","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1016\/j.ophtha.2021.04.027","article-title":"Global Prevalence of Diabetic Retinopathy and Projection of Burden through 2045: Systematic Review and Meta-analysis","volume":"128","author":"ZL Teo","year":"2021","journal-title":"Ophthalmology"},{"issue":"4","key":"pone.0351225.ref003","first-page":"044503","article-title":"Explainable end-to-end deep learning for diabetic retinopathy detection across multiple datasets","volume":"7","author":"M Chetoui","year":"2020","journal-title":"J Med Imaging (Bellingham)"},{"key":"pone.0351225.ref004","unstructured":"Science Media Centre Malaysia. Diabetic Retinopathy: A Complication of Diabetes Uncommonly Known. 2020. Accessed: 2024-10-07. Available from: https:\/\/sciencemediacentremalaysia.com\/opinion\/2020\/11\/feature-article-diabetic-retinopathy-a-complication-of-diabetes-uncommonly-known\/"},{"key":"pone.0351225.ref005","doi-asserted-by":"crossref","DOI":"10.37349\/emed.2026.1001382","article-title":"Comparative evaluation of vision transformers and convolutional networks for breast ultrasound image classification","volume":"7","author":"S Naral","year":"2026","journal-title":"Explor Med"},{"key":"pone.0351225.ref006","doi-asserted-by":"crossref","unstructured":"Emon MU, Zannat R, Khatun T, Rahman M, Keya MS, Ohidujjaman. Performance Analysis of Diabetic Retinopathy Prediction using Machine Learning Models. In: 2021 6th International Conference on Inventive Computation Technologies (ICICT). 2021. p. 1048\u201352.","DOI":"10.1109\/ICICT50816.2021.9358612"},{"issue":"2","key":"pone.0351225.ref007","first-page":"583","article-title":"Automated detection of diabetic retinopathy using machine learning classifiers","volume":"25","author":"KM Alabdulwahhab","year":"2021","journal-title":"Eur Rev Med Pharmacol Sci"},{"key":"pone.0351225.ref008","doi-asserted-by":"crossref","unstructured":"Reddy GT, Bhattacharya S, Ramakrishnan SS, Chowdhary CL, Hakak S, Kaluri R, et al. An ensemble based machine learning model for diabetic retinopathy classification. In: 2020 International Conference on Emerging Trends in Information Technology and Engineering (IC-ETITE). IEEE; 2020. p. 1\u20136.","DOI":"10.1109\/ic-ETITE47903.2020.235"},{"issue":"7","key":"pone.0351225.ref009","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.3390\/sym14071427","article-title":"AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning","volume":"14","author":"A Bilal","year":"2022","journal-title":"Symmetry"},{"issue":"11","key":"pone.0351225.ref010","doi-asserted-by":"crossref","first-page":"3865","DOI":"10.3390\/s21113865","article-title":"Hemorrhage Detection Based on 3D CNN Deep Learning Framework and Feature Fusion for Evaluating Retinal Abnormality in Diabetic Patients","volume":"21","author":"S Maqsood","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"33","key":"pone.0351225.ref011","doi-asserted-by":"crossref","first-page":"79559","DOI":"10.1007\/s11042-023-18036-4","article-title":"Deep learning based diabetic retinopathy screening for resource constraint applications","volume":"83","author":"M Kazmi","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"pone.0351225.ref012","doi-asserted-by":"crossref","first-page":"1305583","DOI":"10.1155\/2023\/1305583","article-title":"Classification of Diabetic Retinopathy Severity in Fundus Images Using the Vision Transformer and Residual Attention","volume":"2023","author":"Z Gu","year":"2023","journal-title":"Comput Intell Neurosci"},{"issue":"12","key":"pone.0351225.ref013","doi-asserted-by":"crossref","first-page":"7850","DOI":"10.1002\/mp.15312","article-title":"Vision Transformer-based recognition of diabetic retinopathy grade","volume":"48","author":"J Wu","year":"2021","journal-title":"Med Phys"},{"key":"pone.0351225.ref014","doi-asserted-by":"crossref","first-page":"127991","DOI":"10.1016\/j.neucom.2024.127991","article-title":"Detecting severity of Diabetic Retinopathy from fundus images: A transformer network-based review","volume":"597","author":"T Karkera","year":"2024","journal-title":"Neurocomputing"},{"key":"pone.0351225.ref015","doi-asserted-by":"crossref","unstructured":"Mohan NJ, Murugan R, Goel T, Roy P. ViT-DR: Vision Transformers in Diabetic Retinopathy Grading Using Fundus Images. In: 2022 IEEE 10th Region 10 Humanitarian Technology Conference (R10-HTC). IEEE; 2022. p. 167\u201372.","DOI":"10.1109\/R10-HTC54060.2022.9930027"},{"issue":"6","key":"pone.0351225.ref016","doi-asserted-by":"crossref","first-page":"100552","DOI":"10.1016\/j.xops.2024.100552","article-title":"Comparative Analysis of Vision Transformers and Conventional Convolutional Neural Networks in Detecting Referable Diabetic Retinopathy","volume":"4","author":"JHL Goh","year":"2024","journal-title":"Ophthalmol Sci"},{"key":"pone.0351225.ref017","doi-asserted-by":"crossref","unstructured":"Kumar NS, Ramaswamy Karthikeyan B. Diabetic Retinopathy Detection using CNN, Transformer and MLP based Architectures. In: 2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS). 2021. p. 1\u20132.","DOI":"10.1109\/ISPACS51563.2021.9651024"},{"issue":"11","key":"pone.0351225.ref018","doi-asserted-by":"crossref","first-page":"1266","DOI":"10.3390\/bioengineering10111266","article-title":"Multi-Dataset Comparison of Vision Transformers and Convolutional Neural Networks for Detecting Glaucomatous Optic Neuropathy from Fundus Photographs","volume":"10","author":"EE Hwang","year":"2023","journal-title":"Bioengineering (Basel)"},{"issue":"3","key":"pone.0351225.ref019","doi-asserted-by":"crossref","first-page":"195","DOI":"10.3390\/info16030195","article-title":"Deep Convolutional Neural Networks in Medical Image Analysis: A Review","volume":"16","author":"ID Mienye","year":"2025","journal-title":"Information"},{"issue":"5","key":"pone.0351225.ref020","doi-asserted-by":"crossref","first-page":"3650","DOI":"10.1167\/iovs.12-11126","article-title":"Racial differences in retinal vessel geometric characteristics: a multiethnic study in healthy Asians","volume":"54","author":"X Li","year":"2013","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"pone.0351225.ref021","unstructured":"Banerjee I, et al. Reading race: AI recognises patient\u2019s racial identity in medical images. ArXiv preprint. arXiv:2107.10356. 2021."},{"issue":"9","key":"pone.0351225.ref022","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from Imbalanced Data","volume":"21","author":"He Haibo","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"pone.0351225.ref023","unstructured":"Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Confounding variables can degrade generalization performance of radiological deep learning models. ArXiv preprint arXiv:1807.00431. 2018."},{"key":"pone.0351225.ref024","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/j.patrec.2020.04.009","article-title":"Deep Learning Frameworks for Diabetic Retinopathy Detection with Smartphone-based Retinal Imaging Systems","volume":"135","author":"RE Hacisoftaoglu","year":"2020","journal-title":"Pattern Recognit Lett"},{"key":"pone.0351225.ref025","doi-asserted-by":"crossref","unstructured":"Balakrishnan R, Rawat R, Kannan S, Pate W, Pati H, Rajkumar S. Image Recognition in Low-Light Conditions with Deep Learning Model. In: 2024 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT). 2024. p. 1479\u201385.","DOI":"10.1109\/IDCIoT59759.2024.10467387"},{"key":"pone.0351225.ref026","unstructured":"V\u0103dineanu \u00c5, Pelt DM, Dzyubachyk O, Batenburg KJ. An analysis of the impact of annotation errors on the accuracy of deep learning for cell segmentation. In: Proc. Int. Conf. Med. Imaging Deep Learn. 2022. p. 1251\u201367."},{"issue":"4","key":"pone.0351225.ref027","doi-asserted-by":"crossref","first-page":"81","DOI":"10.3390\/jimaging9040081","article-title":"Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review","volume":"9","author":"A Kebaili","year":"2023","journal-title":"J Imaging"},{"key":"pone.0351225.ref028","unstructured":"Dugas E, Jared, Jorge, Cukierski W. Diabetic Retinopathy Detection. 2015. Kaggle. https:\/\/www.kaggle.com\/competitions\/diabetic-retinopathy-detection"},{"key":"pone.0351225.ref029","unstructured":"Karthik, Maggie, Dane S. APTOS 2019 Blindness Detection. 2019. Accessed: 2025-08-25. Available from: https:\/\/kaggle.com\/competitions\/aptos2019-blindness-detection"},{"key":"pone.0351225.ref030","unstructured":"Decenci\u00c3\u00a8re E, et al. Feedback on a publicly distributed image database: The Messidor database. 2014. Accessed: 2025-08-25. Available from: https:\/\/www.adcis.net\/en\/third-party\/messidor2\/"},{"key":"pone.0351225.ref031","doi-asserted-by":"crossref","unstructured":"Porwal P, et al. Indian diabetic retinopathy image dataset (IDRiD): A database for diabetic retinopathy screening research. 2018. Accessed: 2025-08-25. Available from: https:\/\/ieee-dataport.org\/open-access\/indian-diabetic-retinopathy-image-dataset-idrid","DOI":"10.3390\/data3030025"},{"issue":"1","key":"pone.0351225.ref032","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TMI.2009.2033909","article-title":"Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs","volume":"29","author":"M Niemeijer","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"pone.0351225.ref033","doi-asserted-by":"crossref","first-page":"4828","DOI":"10.1038\/s41467-021-25138-w","article-title":"Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks","volume":"12","author":"L-P Cen","year":"2021","journal-title":"Nat Commun"},{"key":"pone.0351225.ref034","doi-asserted-by":"crossref","first-page":"154860","DOI":"10.1155\/2013\/154860","article-title":"Robust vessel segmentation in fundus images","volume":"2013","author":"A Budai","year":"2013","journal-title":"Int J Biomed Imaging"},{"key":"pone.0351225.ref035","doi-asserted-by":"crossref","first-page":"107068","DOI":"10.1016\/j.dib.2021.107068","article-title":"Dataset from fundus images for the study of diabetic retinopathy","volume":"36","author":"VE Castillo Ben\u00edtez","year":"2021","journal-title":"Data Brief"},{"key":"pone.0351225.ref036","doi-asserted-by":"crossref","unstructured":"Nakayama LF, Goncalves M, Zago Ribeiro L, Santos H, Ferraz D, Malerbi F, et al. A Brazilian Multilabel Ophthalmological Dataset (BRSET). PhysioNet. 2023.","DOI":"10.1101\/2024.01.23.24301660"},{"key":"pone.0351225.ref037","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1016\/j.ins.2019.06.011","article-title":"Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening","volume":"501","author":"T Li","year":"2019","journal-title":"Inform Sci"},{"issue":"8","key":"pone.0351225.ref038","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1109\/TNNLS.2012.2199516","article-title":"Study on the impact of partition-induced dataset shift on k-fold cross-validation","volume":"23","author":"JG Moreno-Torres","year":"2012","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"pone.0351225.ref039","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2018. p. 4510\u201320.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"pone.0351225.ref040","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chen B, Wang W, Chen L-C, Tan M, et al. Searching for MobileNetV3. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). 2019. p. 1314\u201324.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"pone.0351225.ref041","doi-asserted-by":"crossref","unstructured":"Zoph B, Vasudevan V, Shlens J, Le QV. Learning Transferable Architectures for Scalable Image Recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2018. p. 8697\u2013710.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"pone.0351225.ref042","unstructured":"Tan M, Le Q. EfficientNetV2: Smaller models and faster training. In: Proc Int Conf Mach Learn (ICML). 2021. p. 10096\u2013106."},{"key":"pone.0351225.ref043","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. p. 2818\u201326.","DOI":"10.1109\/CVPR.2016.308"},{"key":"pone.0351225.ref044","unstructured":"Dosovitskiy A, et al. An image is worth 16x16 words: Transformers for image recognition at scale; 2020. ArXiv preprint arXiv. 2010. 11929 p."},{"key":"pone.0351225.ref045","doi-asserted-by":"crossref","unstructured":"Wu H, et al. CvT: Introducing convolutions to vision transformers. In: Proc. IEEE\/CVF Int Conf Comput Vis. 2021. p. 22\u201331.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"pone.0351225.ref046","doi-asserted-by":"crossref","unstructured":"Liu Z, et al. Swin Transformer: Hierarchical vision transformer using shifted windows. In: Proc. IEEE\/CVF Int Conf Comput Vis. 2021. p. 10012\u201322.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0351225.ref047","unstructured":"Bao H, Dong L, Piao S, Wei F. BEiT: BERT pre-training of image transformers. ArXiv preprint arXiv:2106.08254. 2021."},{"key":"pone.0351225.ref048","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, J\u00e9gou H. Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning. 2021. p. 10347\u201357."},{"issue":"5","key":"pone.0351225.ref049","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","article-title":"Convolutional neural networks for medical image analysis: full training or fine tuning?","volume":"35","author":"N Tajbakhsh","year":"2016","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0351225.ref050","volume-title":"An MLHOps-driven vision transformer approach for pneumonia classification in chest X-rays","author":"DTV Nagothi","year":"2025"},{"key":"pone.0351225.ref051","doi-asserted-by":"crossref","unstructured":"Zhai X, Kolesnikov A, Houlsby N, Beyer L. Scaling Vision Transformers. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. p. 1204\u201313.","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"pone.0351225.ref052","unstructured":"Steiner A, Kolesnikov A, Zhai X, Wightman R, Uszkoreit J, Beyer L. How to train your vit? data, augmentation, and regularization in vision transformers. arXiv:210610270. 2021."},{"key":"pone.0351225.ref053","doi-asserted-by":"crossref","unstructured":"Bhojanapalli S, Chakrabarti A, Glasner D, Li D, Unterthiner T, Veit A. Understanding Robustness of Transformers for Image Classification. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 2021. p. 10211\u201321.","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"pone.0351225.ref054","doi-asserted-by":"crossref","unstructured":"Fan H, Xiong B, Mangalam K, Li Y, Yan Z, Malik J, et al. Multiscale Vision Transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 2021. p. 6804\u201315.","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"pone.0351225.ref055","doi-asserted-by":"crossref","first-page":"1100697","DOI":"10.3389\/fnbot.2022.1100697","article-title":"DRFnet: Dynamic receptive field network for object detection and image recognition","volume":"16","author":"M Tan","year":"2023","journal-title":"Front Neurorobot"},{"key":"pone.0351225.ref056","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1038\/s41746-018-0040-6","article-title":"Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices","volume":"1","author":"MD Abr\u00e0moff","year":"2018","journal-title":"NPJ Digit Med"},{"issue":"22","key":"pone.0351225.ref057","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs","volume":"316","author":"V Gulshan","year":"2016","journal-title":"JAMA"},{"issue":"22","key":"pone.0351225.ref058","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1001\/jama.2017.18152","article-title":"Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes","volume":"318","author":"DSW Ting","year":"2017","journal-title":"JAMA"},{"issue":"3","key":"pone.0351225.ref059","doi-asserted-by":"crossref","first-page":"485","DOI":"10.3390\/diagnostics16030485","article-title":"Addressing Class Imbalance in Fetal Health Classification: Rigorous Benchmarking of Multi-Class Resampling Methods on Cardiotocography Data","volume":"16","author":"ZSM Hawrami","year":"2026","journal-title":"Diagnostics (Basel)"},{"key":"pone.0351225.ref060","doi-asserted-by":"crossref","unstructured":"Chefer H, Gur S, Wolf L. Transformer Interpretability Beyond Attention Visualization. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021. p. 782\u201391.","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"pone.0351225.ref061","doi-asserted-by":"crossref","first-page":"103000","DOI":"10.1016\/j.media.2023.103000","article-title":"Advances in medical image analysis with vision Transformers: A comprehensive review","volume":"91","author":"R Azad","year":"2024","journal-title":"Med Image Anal"},{"key":"pone.0351225.ref062","article-title":"Retinopathy, neuropathy, and foot care: standards of care in diabetes\u20142025","volume":"48","year":"2025","journal-title":"Diabetes Care"},{"issue":"11","key":"pone.0351225.ref063","doi-asserted-by":"crossref","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI","volume":"32","author":"E Tjoa","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"1","key":"pone.0351225.ref064","article-title":"Tackling algorithmic bias and promoting transparency in health datasets: the STANDING Together consensus recommendations","volume":"7","author":"JE Alderman","year":"2025","journal-title":"Lancet Digit Health"},{"issue":"1","key":"pone.0351225.ref065","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1186\/s12910-021-00687-3","article-title":"Privacy and artificial intelligence: challenges for protecting health information in a new era","volume":"22","author":"B Murdoch","year":"2021","journal-title":"BMC Med Ethics"},{"issue":"3","key":"pone.0351225.ref066","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1056\/NEJMc2104626","article-title":"The Clinician and Dataset Shift in Artificial Intelligence","volume":"385","author":"SG Finlayson","year":"2021","journal-title":"N Engl J Med"},{"issue":"3","key":"pone.0351225.ref067","article-title":"Sources of bias in artificial intelligence that perpetuate healthcare disparities-A global review","volume":"1","author":"LA Celi","year":"2022","journal-title":"PLOS Digit Health"},{"issue":"5","key":"pone.0351225.ref068","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000864","article-title":"AI-driven healthcare: A review on ensuring fairness and mitigating bias","volume":"4","author":"SV Chinta","year":"2025","journal-title":"PLOS Digital Health"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0351225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T17:26:57Z","timestamp":1787246817000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0351225"}},"subtitle":[],"editor":[{"given":"Ali Mohammad","family":"Alqudah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":68,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0351225","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]}}}