{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:44:26Z","timestamp":1792791866005,"version":"4.5.0"},"reference-count":30,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>This study introduces an explainable neuro-symbolic and large language model (LLM)-driven framework for intelligent interpretation of corneal topography and precision surgical decision support. In a prospective cohort of 20 eyes, comprehensive IOLMaster 700 reports were analyzed through a four-stage pipeline: (1) automated extraction of key parameters\u2014including corneal curvature, pachymetry, and axial biometry; (2) mapping of these quantitative features onto a curated corneal disease and refractive-surgery knowledge graph; (3) Bayesian probabilistic inference to evaluate early keratoconus and surgical eligibility; and (4) explainable multi-model LLM reporting, employing DeepSeek and GPT-4.0, to generate bilingual physician- and patient-facing narratives. By transforming complex imaging data into transparent reasoning chains, the pipeline delivered case-level outputs within ~95 \u00b1 12 s. When benchmarked against independent evaluations by two senior corneal specialists, the framework achieved 92 \u00b1 4% sensitivity, 94 \u00b1 5% specificity, 93 \u00b1 4% accuracy, and an AUC of 0.95 \u00b1 0.03 for early keratoconus detection, alongside an F1 score of 0.90 \u00b1 0.04 for refractive surgery eligibility. The generated bilingual reports were rated \u22654.8\/5 for logical clarity, clinical usefulness, and comprehensibility, with representative cases fully concordant with expert judgment. Comparative benchmarking against baseline CNN and ViT models demonstrated superior diagnostic accuracy (AUC = 0.95 \u00b1 0.03 vs. 0.88 and 0.90, p &lt; 0.05), confirming the added value of the neuro-symbolic reasoning layer. All analyses were executed on a workstation equipped with an NVIDIA RTX 4090 GPU and implemented in Python 3.10\/PyTorch 2.2.1 for full reproducibility. By explicitly coupling symbolic medical knowledge with advanced language models and embedding explainable artificial intelligence (XAI) principles throughout data processing, reasoning, and reporting, this framework provides a transparent, rapid, and clinically actionable AI solution. The approach holds significant promise for improving early ectatic disease detection and supporting individualized refractive surgery planning in routine ophthalmic practice.<\/jats:p>","DOI":"10.3390\/bioengineering12111174","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T17:02:01Z","timestamp":1761670921000},"page":"1174","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["An Explainable AI Framework for Corneal Imaging Interpretation and Refractive Surgery Decision Support"],"prefix":"10.3390","volume":"12","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 Department of Ophthalmology and Visual Sciences, 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":[[2025,10,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, M. (2024). Corneal Topography: A Guide for Clinical Application in Wavefront Era. CRC Press.","DOI":"10.1201\/9781003523321"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102292","DOI":"10.1016\/j.asej.2023.102292","article-title":"Corneal elevation topographic maps assessing different diseases detection: A review","volume":"15","author":"Ahmed","year":"2023","journal-title":"Ain Shams Eng. J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/s40662-024-00418-w","article-title":"Association between axial elongation and corneal topography in children undergoing orthokeratology with different back optic zone diameters","volume":"12","author":"Tan","year":"2025","journal-title":"Eye Vis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"19642","DOI":"10.1038\/s41598-024-70084-4","article-title":"Longitudinal assessment of the progression of severe keratoconus based on corneal topography","volume":"14","author":"Yang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"27987","DOI":"10.1038\/s41598-024-78759-8","article-title":"Analysis of intraocular lens tilt and decentration after cataract surgery in eyes with high myopia using the anterior segment optical coherence tomography","volume":"14","author":"Jeon","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_6","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_7","doi-asserted-by":"crossref","first-page":"24399","DOI":"10.1038\/s41598-025-09694-5","article-title":"Machine learning-assisted early detection of keratoconus: A comparative analysis of corneal topography and biomechanical data","volume":"15","author":"Syta","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1264659","DOI":"10.3389\/fmed.2023.1264659","article-title":"Evaluation of the corneal topography based on deep learning","volume":"10","author":"Xu","year":"2024","journal-title":"Front. Med."},{"key":"ref_9","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_10","doi-asserted-by":"crossref","first-page":"1517918","DOI":"10.3389\/frai.2025.1517918","article-title":"Balancing accuracy and user satisfaction: The role of prompt engineering in AI-driven healthcare solutions","volume":"8","author":"Wang","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1527010","DOI":"10.3389\/frai.2025.1527010","article-title":"Applied machine learning in intelligent systems: Knowledge graph-enhanced ophthalmic contrastive learning with \u201cclinical profile\u201d prompts","volume":"8","author":"Wang","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"ref_12","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":"2023","journal-title":"Br. J. Ophthalmol."},{"key":"ref_13","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_14","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_15","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_16","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_17","doi-asserted-by":"crossref","unstructured":"Hoehndorf, R., Pesquita, C., and Zhapa-Camacho, F. (2025). Neuro-Symbolic AI in Life Sciences. IOS Press.","DOI":"10.3233\/FAIA250239"},{"key":"ref_18","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_19","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_20","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1038\/s41746-025-01706-y","article-title":"Advanced and interpretable corneal staining assessment through fine grained knowledge distillation","volume":"8","author":"Deng","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1398","DOI":"10.1136\/bjo-2023-325053","article-title":"Assessing the medical reasoning skills of GPT-4 in complex ophthalmology cases","volume":"108","author":"Milad","year":"2024","journal-title":"Br. J. Ophthalmol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"4999","DOI":"10.1038\/s41598-025-88948-8","article-title":"Integrated visual and text-based analysis of ophthalmology clinical cases using a large language model","volume":"15","author":"Sorin","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_23","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_24","doi-asserted-by":"crossref","first-page":"e50842","DOI":"10.2196\/50842","article-title":"Performance of ChatGPT on ophthalmology-related questions across various examination levels: Observational study","volume":"10","author":"Haddad","year":"2024","journal-title":"JMIR Med. Educ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3694","DOI":"10.1038\/s41433-023-02564-2","article-title":"Comparison of GPT-3.5, GPT-4, and human user performance on a practice ophthalmology written examination","volume":"37","author":"Lin","year":"2023","journal-title":"Eye"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mahadi, M.K., Rahad, R., Noman, A., Ishrat, S., and Faisal, F. (2024, January 24\u201326). Understanding machine learning & its application in obesity estimation by explainable AI. Proceedings of the 2024 International Conference on Inventive Computation Technologies (ICICT), Kathmandu, Nepal.","DOI":"10.1109\/ICICT60155.2024.10544438"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1561","DOI":"10.1007\/s40519-019-00793-7","article-title":"Factors associated with overweight and obesity in adults using structural equation model: Mediation effect of physical activity and dietary pattern","volume":"25","author":"Darbandi","year":"2019","journal-title":"Eat. Weight. Disord. Stud. Anorex. Bulim. Obes."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"22607","DOI":"10.1038\/s41598-021-01964-2","article-title":"A weighted patient network-based framework for predicting chronic diseases using graph neural networks","volume":"11","author":"Lu","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_29","first-page":"48","article-title":"Improving the Accuracy of Artificial Intelligence Models in Nutrition and Health Research Through High-Quality Data Processing. SAMRIDDHI: A Journal of Physical Sciences","volume":"16","author":"Kovalchuk","year":"2024","journal-title":"Eng. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Peng, K., Peng, Z., and Zhang, R. (2025). Enhancing Neighborhood Food Availability for Safer and Healthier Urban Environments: A Cross-Sectional Investigation in Changsha, China. Designing Healthy Buildings and Communities: Shaping a Climate-Resilient Future, Springer.","DOI":"10.1007\/978-981-96-3057-8_6"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/11\/1174\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T17:34:06Z","timestamp":1761672846000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/11\/1174"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":30,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["bioengineering12111174"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering12111174","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,28]]}}}