{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:08:08Z","timestamp":1791392888895,"version":"4.3.3"},"reference-count":25,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Ines Hilali Jaghdam","award":["Princess Nourah bint Abdulrahman University Resear"],"award-info":[{"award-number":["Princess Nourah bint Abdulrahman University Resear"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To systematically evaluate transfer learning (TL) models for multiclass ocular disease diagnosis and assess their reliability using explainable artificial intelligence (AI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Eight pretrained convolutional neural network (CNN) models were evaluated on a public dataset covering cataract, diabetic retinopathy, glaucoma, and normal classes under a unified protocol. Performance was measured using accuracy, precision, recall, and F1-score. Grad-CAM, LIME, and SHAP were used for interpretability, and the Friedman test assessed performance consistency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Several models achieved near-perfect performance for diabetic retinopathy. DenseNet121 and XceptionNet performed best for cataract detection, while glaucoma showed consistently weaker results, indicating the need for segmentation-based approaches. Despite similar accuracy, explainability revealed substantial differences in model attention. EfficientNetB3 produced the most clinically meaningful visual explanations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Accuracy alone is insufficient for trustworthy medical AI. Explainable AI is essential for model selection. EfficientNetB3 offers the best balance between performance and interpretability, and glaucoma diagnosis requires more advanced, segmentation-aware pipelines.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261423994","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:27:49Z","timestamp":1770834469000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Unveiling the black box: Explainable transfer learning for ocular disorder diagnosis"],"prefix":"10.1177","volume":"12","author":[{"given":"Zaib","family":"un Nisa","sequence":"first","affiliation":[{"name":"The Superior University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arfan","family":"Jaffar","sequence":"additional","affiliation":[{"name":"The Superior University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sohail Masood","family":"Bhatti","sequence":"additional","affiliation":[{"name":"The Superior University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ines Hilali","family":"Jaghdam","sequence":"additional","affiliation":[{"name":"Princess Nourah Bint Abdulrahman University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4649-2376","authenticated-orcid":false,"given":"Tehseen","family":"Mazhar","sequence":"additional","affiliation":[{"name":"National College of Business Administration and Economics"},{"name":"Department of Computer Science and Information Technology, School Education Department, Government of Punjab, Layyah, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Amir Khan","sequence":"additional","affiliation":[{"name":"Universiti Teknologi MARA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Habib","family":"Hamam","sequence":"additional","affiliation":[{"name":"Uni de Moncton"},{"name":"School of Electrical Engineering, University of Johannesburg, Johannesburg, South Africa"},{"name":"International Institute of Technology and Management (IITG), Libreville, Gabon"},{"name":"College of Computer Science and Eng. (Invited Prof.), University of Ha'il, Ha'il, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"World Health Organization. Blindness and vision impairment https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/blindness-and-visual-impairment (2023)."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/app9142789"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2017.080606"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e36759"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-024-09137-9"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12886-024-03532-4"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/app14177795"},{"key":"e_1_3_2_9_2","article-title":"Combined optic disc and optic cup segmentation network based on adversarial learning","author":"Liu Y","year":"2024","unstructured":"Liu Y, Wu J, Zhu Y, et al. Combined optic disc and optic cup segmentation network based on adversarial learning. IEEE Access 2024.","journal-title":"IEEE Access"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics9100637"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.48084\/etasr.7294"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18149-4"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3101142"},{"key":"e_1_3_2_14_2","first-page":"721","article-title":"Automated detection of Alzheimer\u2019s via hybrid classical quantum neural networks","volume":"11","author":"Shahwar T","year":"2022","unstructured":"Shahwar T, Zafar J, Almogren A, et al. Automated detection of Alzheimer\u2019s via hybrid classical quantum neural networks. Electronics (Basel) 2022; 11: 721.","journal-title":"Electronics (Basel)"},{"key":"e_1_3_2_15_2","first-page":"1","article-title":"A comprehensive study on deep learning models for the detection of diabetic retinopathy using pathological images","author":"Singh DP","year":"2025","unstructured":"Singh DP, Banerjee T, Mahajan S, et al. A comprehensive study on deep learning models for the detection of diabetic retinopathy using pathological images. Arch Comput Methods Eng 2025: 1\u201330.","journal-title":"Arch Comput Methods Eng"},{"key":"e_1_3_2_16_2","volume-title":"Retinal eye disease detection using deep learning2018 14th International conference on information processing (ICINPRO)","author":"Jain L","unstructured":"Jain L, Murthy HS, Patel C, et al., eds. Retinal eye disease detection using deep learning. In: 2018 14th International conference on information processing (ICINPRO), 2018: IEEE."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3476412"},{"key":"e_1_3_2_18_2","volume-title":"Leveraging EfficientNetB3 for accurate breast cancer classification: insights and innovations2024 9th International conference on communication and electronics systems (ICCES)","author":"Nasra P","unstructured":"Nasra P, Gupta S, Kumar GR, eds. Leveraging EfficientNetB3 for accurate breast cancer classification: insights and innovations. In: 2024 9th International conference on communication and electronics systems (ICCES), 2024: IEEE."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2025.105414"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16882-w"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2025.100680"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-03752-8"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.35882\/jeeemi.v8i1.941"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.3390\/s24237710"},{"key":"e_1_3_2_25_2","volume-title":"A comparative study of DenseNet121 and InceptionResNetV2 model for deepfake image detection2024 3rd International conference on applied artificial intelligence and computing (ICAAIC)","author":"Manoranjitham R","unstructured":"Manoranjitham R, Swaroop SS, (eds). A comparative study of DenseNet121 and InceptionResNetV2 model for deepfake image detection. In: 2024 3rd International conference on applied artificial intelligence and computing (ICAAIC), 2024: IEEE."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2025.104802"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261423994","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261423994","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261423994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:06Z","timestamp":1777398966000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261423994"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":25,"alternative-id":["10.1177\/20552076261423994"],"URL":"https:\/\/doi.org\/10.1177\/20552076261423994","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261423994"}}