{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T11:25:21Z","timestamp":1787916321276,"version":"build-2784847793"},"reference-count":52,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82501368"],"award-info":[{"award-number":["82501368"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372047"],"award-info":[{"award-number":["62372047"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Age-related macular degeneration (AMD) is a leading cause of irreversible blindness, yet current tools for forecasting treatment outcomes remain limited by either the opacity of deep learning or the rigidity of rule-based systems. To address this gap, we propose a hybrid neuro-symbolic and large language model (LLM) framework that combines mechanistic disease knowledge with multimodal ophthalmic data for explainable AMD treatment prognosis. In a pilot cohort of ten surgically managed AMD patients (six men, four women; mean age 67.8 \u00b1 6.3 years), we collected 30 structured clinical documents and 100 paired imaging series (optical coherence tomography, fundus fluorescein angiography, scanning laser ophthalmoscopy, and ocular\/superficial B-scan ultrasonography). Texts were semantically annotated and mapped to standardized ontologies, while images underwent rigorous DICOM-based quality control, lesion segmentation, and quantitative biomarker extraction. A domain-specific ophthalmic knowledge graph encoded causal disease and treatment relationships, enabling neuro-symbolic reasoning to constrain and guide neural feature learning. An LLM fine-tuned on ophthalmology literature and electronic health records ingested structured biomarkers and longitudinal clinical narratives through multimodal clinical-profile prompts, producing natural-language risk explanations with explicit evidence citations. On an independent test set, the hybrid model achieved AUROC 0.94 \u00b1 0.03, AUPRC 0.92 \u00b1 0.04, and a Brier score of 0.07, significantly outperforming purely neural and classical Cox regression baselines (p \u2264 0.01). Explainability metrics showed that &gt;85% of predictions were supported by high-confidence knowledge-graph rules, and &gt;90% of generated narratives accurately cited key biomarkers. A detailed case study demonstrated real-time, individualized risk stratification\u2014for example, predicting an &gt;70% probability of requiring three or more anti-VEGF injections within 12 months and a ~45% risk of chronic macular edema if therapy lapsed\u2014with predictions matching the observed clinical course. These results highlight the framework\u2019s ability to integrate multimodal evidence, provide transparent causal reasoning, and support personalized treatment planning. While limited by single-center scope and short-term follow-up, this work establishes a scalable, privacy-aware, and regulator-ready template for explainable, next-generation decision support in AMD management, with potential for expansion to larger, device-diverse cohorts and other complex retinal diseases.<\/jats:p>","DOI":"10.3390\/s25226879","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T12:44:55Z","timestamp":1762865095000},"page":"6879","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Explainable Artificial Intelligence Framework for Predicting Treatment Outcomes in Age-Related Macular Degeneration"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5002-3708","authenticated-orcid":false,"given":"Mini Han","family":"Wang","sequence":"first","affiliation":[{"name":"Zhuhai People\u2019s Hospital (The Affiliated Hospital of Beijing Institute of Technology, Zhuhai Clinical Medical College of Jinan University), Zhuhai 519000, China"},{"name":"The Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong 999077, China"},{"name":"Zhuhai Institute of Advanced Technology Chinese Academy of Sciences, Zhuhai 519000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, M.H. (2025). Integrating Artificial Intelligence and Precision Therapeutics for Advancing the Diagnosis and Treatment of Age-Related Macular Degeneration. Bioengineering, 12.","DOI":"10.3390\/bioengineering12050548"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1001\/jamaophthalmol.2023.4659","article-title":"A Deep-Learning Algorithm to Predict Short-Term Progression to Geographic Atrophy on Spectral-Domain Optical Coherence Tomography","volume":"141","author":"Dow","year":"2023","journal-title":"JAMA Ophthalmol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Shor, R., Popovic, M.M., and Muni, R.H. (JAMA Ophthalmol., 2025). Neovascular Age-Related Macular Degeneration and GLP-1 RAs\u2014Reply, JAMA Ophthalmol., early access.","DOI":"10.1001\/jamaophthalmol.2025.3723"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.jare.2024.10.001","article-title":"Serum metabolite biomarkers for the early diagnosis and monitoring of age-related macular degeneration","volume":"74","author":"Li","year":"2025","journal-title":"J. Adv. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e081398","DOI":"10.1136\/bmjopen-2023-081398","article-title":"Empowering Portable Age-Related Macular Degeneration Screening: Evaluation of a Deep Learning Algorithm for a Smartphone Fundus Camera","volume":"14","author":"Savoy","year":"2024","journal-title":"BMJ Open"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yeh, T.-C., Luo, A.-C., Deng, Y.-S., Lee, Y.-H., Chen, S.-J., Chang, P.-H., Lin, C.-J., Tai, M.-C., and Chou, Y.-B. (2022). Prediction of treatment outcome in neovascular age-related macular degeneration using a novel convolutional neural network. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-09642-7"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"169","DOI":"10.22270\/jddt.v15i7.7283","article-title":"Current Trends and Challenges in Clinical Trials for Wet Age-Related Macular Degeneration: A Review","volume":"15","author":"Mishra","year":"2025","journal-title":"J. Drug Deliv. Ther."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1038\/s41433-024-03460-z","article-title":"Artificial intelligence in assessing progression of age-related macular degeneration","volume":"39","author":"Birner","year":"2025","journal-title":"Eye"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"445","DOI":"10.26599\/BDMA.2023.9020024","article-title":"AI-based Advanced approaches and dry eye disease detection based on multi-source evidence: Cases, applications, issues, and future directions","volume":"7","author":"Wang","year":"2024","journal-title":"Big Data Min. Anal."},{"key":"ref_10","unstructured":"Wang, M.H., Zhou, J., Huang, C., Tang, Z., Yu, X., Hou, G., Yang, J., Yuan, Q., Chong, K.K., and Huang, L. (2023, January 2\u20134). Fusion learning methods for the age-related macular degeneration diagnosis based on multiple sources of ophthalmic digital images. Proceedings of the Second International Conference on Electrical, Electronics, and Information Engineering, Nanchang, China."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1001\/jamaophthalmol.2025.1608","article-title":"Dynamic Risk of Systemic Complement Activation With Time to Progression to Advanced Age-Related Macular Degeneration","volume":"143","author":"Lynch","year":"2025","journal-title":"JAMA Ophthalmol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102687","DOI":"10.1016\/j.tice.2024.102687","article-title":"Therapeutic potential of adult stem cells-derived mitochondria transfer combined with curcumin administration into ARPE-19 cells in age-related macular degeneration model","volume":"93","author":"Duruksu","year":"2025","journal-title":"Tissue Cell"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"104701","DOI":"10.1016\/j.pdpdt.2025.104701","article-title":"Efficacy and prognostic factors of anti-VEGF treatment for neovascular age-related macular degeneration: An OCTA imaging-based deep learning analysis","volume":"55","author":"Liu","year":"2025","journal-title":"Photodiagn. Photodyn. Ther."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Y., Xu, C., Peng, A., Qin, H., and Yao, K. (2025). Advancements in age-related macular degeneration treatment: From traditional anti-VEGF to emerging therapies in gene, stem cell, and nanotechnology. Biochem. Pharmacol., 236.","DOI":"10.1016\/j.bcp.2025.116902"},{"key":"ref_15","unstructured":"Han, J.M. (2025). Prediction of Anti-VEGF Treatment Outcome and Recurrence in Neovascular Age-Related Macular Degeneration Based on Optical Coherence Tomography Using Deep Neural Networks, Seoul National University."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Mondal, A., Nandi, A., Pramanik, S., and Mondal, L.K. (2025). Application of deep learning algorithm for judicious use of anti-VEGF in diabetic macular edema. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-87290-3"},{"key":"ref_17","unstructured":"Wang, M.H., Huang, L., Hou, G., Yang, J., Xing, L., Yuan, Q., Chong, K.K.-L., Lin, Z., Zeng, P., and Fang, X. (2023, January 2\u20134). Deep learning for macular fovea detection based on ultra-widefield fundus images. Proceedings of the Second International Conference on Electrical, Electronics, and Information Engineering, Nanchang, China."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1097\/IAE.0000000000004106","article-title":"Deep learning for automatic prediction of early activation of treatment-naive nonexudative macular neovascularizations in age-related macular degeneration","volume":"44","author":"Crincoli","year":"2024","journal-title":"Retina"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, M.H., Chong, K.K.-L., Lin, Z., Yu, X., and Pan, Y. (2023). An Explainable Artificial Intelligence-Based Robustness Optimization Approach for Age-Related Macular Degeneration Detection Based on Medical IOT Systems. Electronics, 12.","DOI":"10.3390\/electronics12122697"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, M.H., Jiang, X., Zeng, P., Li, X., Chong, K.K.-L., Hou, G., Fang, X., Yu, Y., Yu, X., and Fang, J. (2025). Balancing accuracy and user satisfaction: The role of prompt engineering in AI-driven healthcare solutions. Front. Artif. Intell., 8.","DOI":"10.3389\/frai.2025.1517918"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, M.H., Cui, J., Lee, S.M.-Y., Lin, Z., Zeng, P., Li, X., Liu, H., Liu, Y., Xu, Y., and Wang, Y. (2025). Applied machine learning in intelligent systems: Knowledge graph-enhanced ophthalmic contrastive learning with clinical profile prompts. Front. Artif. Intell., 8.","DOI":"10.3389\/frai.2025.1527010"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, C., Wang, J., Wu, H., Fan, W., Li, S., Wei, D., Song, Z., and Tao, Y. (2024). Hydrogel-based therapy for age-related macular degeneration: Current innovations, impediments, and future perspectives. Gels, 10.","DOI":"10.3390\/gels10030158"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hitzler, P., and Sarker, M.K. (2022). Neuro-Symbolic Artificial Intelligence: The State of the Art, IOS Press.","DOI":"10.3233\/FAIA342"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s10462-023-10622-0","article-title":"Interpretable scientific discovery with symbolic regression: A review","volume":"57","author":"Makke","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"12809","DOI":"10.1007\/s00521-024-09960-z","article-title":"Neuro-symbolic artificial intelligence: A survey","volume":"36","author":"Bhuyan","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hoehndorf, R., Pesquita, C., and Camacho, F.Z. (2025). Neuro-Symbolic AI in Life Sciences, IOS Press.","DOI":"10.3233\/FAIA250239"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"nwac035","DOI":"10.1093\/nsr\/nwac035","article-title":"Neuro-symbolic approaches in artificial intelligence","volume":"9","author":"Hitzler","year":"2022","journal-title":"Natl. Sci. Rev."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/s40860-024-00231-1","article-title":"Surveying neuro-symbolic approaches for reliable artificial intelligence of things","volume":"10","author":"Lu","year":"2024","journal-title":"J. Reliab. Intell. Environ."},{"key":"ref_29","unstructured":"Abdallah, Q.M., Al-Daghistani, F., Mizher, H., Abdallah, M., and Abukhalil, A.A. (2025, January 27\u201330). The Role of Large Language Models in Personalized Obesity Management: Opportunities and Challenges. Proceedings of the 2025 12th International Conference on Information Technology (ICIT), Amman, Jordan."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sorin, V., Kapelushnik, N., Hecht, I., Zloto, O., Glicksberg, B.S., Bufman, H., Livne, A., Barash, Y., Nadkarni, G.N., and Klang, E. (2025). Integrated visual and text-based analysis of ophthalmology clinical cases using a large language model. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-88948-8"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1038\/s41433-023-02915-z","article-title":"ChatGPT and Beyond: An overview of the growing field of large language models and their use in ophthalmology","volume":"38","author":"Kedia","year":"2024","journal-title":"Eye"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Belle, V., Fisher, M., Russo, A., Komendantskaya, E., and Nottle, A. (2024). Neuro-Symbolic AI+ Agent Systems: A First Reflection on Trends, Opportunities and Challenges, Springer.","DOI":"10.1007\/978-3-031-56255-6_10"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"104454","DOI":"10.1016\/j.pdpdt.2024.104454","article-title":"A comprehensive review on early detection of drusen patterns in age-related macular degeneration using deep learning models","volume":"51","author":"Kiruthika","year":"2025","journal-title":"Photodiagn. Photodyn. Ther."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Leng, X., Shi, R., Wu, Y., Zhu, S., Cai, X., Lu, X., and Liu, R. (2023). Deep learning for detection of age-related macular degeneration: A systematic review and meta-analysis of diagnostic test accuracy studies. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0284060"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Finocchio, L., Zeppieri, M., Gabai, A., Toneatto, G., Spadea, L., and Salati, C. (2023). Recent developments in gene therapy for neovascular age-related macular degeneration: A review. Biomedicines, 11.","DOI":"10.3390\/biomedicines11123221"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1186\/s12964-025-02246-4","article-title":"Gene therapy for age-related macular degeneration: A promising frontier in vision preservation","volume":"23","author":"Hushmandi","year":"2025","journal-title":"Cell Commun. Signal."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Deka, D., Medhi, J.P., and Nirmala, S. (2015, January 9\u201311). Detection of macula and fovea for disease analysis in color fundus images. Proceedings of the 2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS), Kolkata, India.","DOI":"10.1109\/ReTIS.2015.7232883"},{"key":"ref_38","first-page":"1265","article-title":"Is neuro-symbolic AI meeting its promises in natural language processing? A structured review","volume":"15","author":"Hamilton","year":"2024","journal-title":"Semant. Web"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Votsis, I. (2024). A Neuro-Symbolic Approach to the Logic of Scientific Discovery, Springer.","DOI":"10.1007\/978-3-031-69300-7_18"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1136\/bjo-2023-324734","article-title":"Review of emerging trends and projection of future developments in large language models research in ophthalmology","volume":"108","author":"Wong","year":"2024","journal-title":"Br. J. Ophthalmol."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Jiao, C., Rosas, E., Asadigandomani, H., Delsoz, M., Madadi, Y., Raja, H., Munir, W.M., Tamm, B., Mehravaran, S., and Djalilian, A.R. (2025). Diagnostic Performance of Publicly Available Large Language Models in Corneal Diseases: A Comparison with Human Specialists. Diagnostics, 15.","DOI":"10.3390\/diagnostics15101221"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"Ledsam","year":"2018","journal-title":"Nat. Med."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1016\/j.ophtha.2018.11.015","article-title":"DeepSeeNet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs","volume":"126","author":"Peng","year":"2019","journal-title":"Ophthalmology"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1136\/bjophthalmol-2020-316594","article-title":"Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30,000 patients","volume":"105","author":"Heydon","year":"2021","journal-title":"Br. J. Ophthalmol."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"73950","DOI":"10.1109\/ACCESS.2024.3405570","article-title":"Enhancing early detection of diabetic retinopathy through the integration of deep learning models and explainable artificial intelligence","volume":"12","author":"Alavee","year":"2024","journal-title":"IEEE Access"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"100402","DOI":"10.1016\/j.array.2025.100402","article-title":"Explainable deep learning-based meta-classifier approach for multi-label classification of retinal diseases","volume":"26","author":"Hemal","year":"2025","journal-title":"Array"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1007\/s12559-023-10224-6","article-title":"Classification of Developmental and Brain Disorders via Graph Convolutional Aggregation","volume":"16","author":"Salim","year":"2024","journal-title":"Cogn. Comput."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1136\/bjo-2025-327360","article-title":"Performance of DeepSeek-R1 in ophthalmology: An evaluation of clinical decision-making and cost-effectiveness","volume":"109","author":"Mikhail","year":"2025","journal-title":"Br. J. Ophthalmol."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"128598","DOI":"10.1016\/j.eswa.2025.128598","article-title":"Exploiting open data for CO2 estimation via artificial intelligence and eXplainable AI","volume":"291","author":"Bilotta","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Canti, E., Collini, E., Palesi, L.A.I., and Nesi, P. (2024, January 15\u201318). Comparing Techniques for Temporal Explainable Artificial Intelligence. Proceedings of the 2024 IEEE 10th International Conference on Big Data Computing Service and Machine Learning Applications (BigDataService), Shanghai, China.","DOI":"10.1109\/BigDataService62917.2024.00019"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"101678","DOI":"10.1109\/ACCESS.2023.3314660","article-title":"Predicting free parking slots via deep learning in short-mid terms explaining temporal impact of features","volume":"11","author":"Bilotta","year":"2023","journal-title":"IEEE Access"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1001\/jamaophthalmol.2025.2766","article-title":"Optic Nerve Atrophy Conditions Associated With 3D Unsegmented Optical Coherence Tomography Volumes Using Deep Learning","volume":"143","author":"Szanto","year":"2025","journal-title":"JAMA Ophthalmol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6879\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T12:46:30Z","timestamp":1762865190000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6879"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":52,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25226879"],"URL":"https:\/\/doi.org\/10.3390\/s25226879","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]}}}