{"doi":"10.1016/j.xops.2025.100785","title":"Predicting Imminent Conversion to Exudative Age-Related Macular Degeneration Using Multimodal Data and Ensemble Machine Learning","abstract":"Objective: Exudative age-related macular degeneration (eAMD) is a major cause of central vision loss. Identifying patients at high risk of imminent eAMD could enable timely treatment and improve outcomes. Our goal was to develop and compare classical machine learning (ML) and deep learning (DL) models to predict imminent eAMD conversion within 6 months and integrate OCT with clinical data into a single predictive model. Design: Retrospective cohort study. Participants: Patients seen at the Wilmer Eye Institute between 2013 and 2021 with eAMD in ≥1 eye. Methods: < 0.05 was considered statistically significant. Main Outcome Measures: Area under the operating characteristic curve. Results: < 0.001). Conclusions: The 3-dimensional DL models, trained with OCT volumes, are capable of predicting both first-eye and fellow-eye imminent conversion to eAMD. The addition of clinical data further improved the model performance. These models, if validated prospectively, could serve as screening tools and allow retinal specialists to prioritize patients with more acute retinal issues. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.","journal":"Ophthalmology Science","year":2025,"id":523036,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":4,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9578,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":796118,"name":"Yuxuan Liu","orcid":"0000-0003-4426-9290","position":1,"is_corresponding":false},{"id":811383,"name":"Madeleine S. Gastonguay","orcid":"0000-0002-5700-8543","position":2,"is_corresponding":false},{"id":330907,"name":"Dan Midgett","orcid":"0000-0003-1173-0917","position":3,"is_corresponding":false},{"id":1167855,"name":"Nathanael Kuo","orcid":"0000-0002-0477-9299","position":4,"is_corresponding":false},{"id":1369170,"name":"Yujie Zhao","orcid":"0000-0003-1683-3528","position":5,"is_corresponding":false},{"id":1395498,"name":"Kareef Ullah","orcid":null,"position":6,"is_corresponding":false},{"id":1395499,"name":"G. Fletcher Alexander","orcid":null,"position":7,"is_corresponding":false},{"id":1395500,"name":"Todd Hartman","orcid":null,"position":8,"is_corresponding":false},{"id":488814,"name":"Neslihan Dilruba Köseoğlu","orcid":"0000-0001-9268-1461","position":9,"is_corresponding":false},{"id":655437,"name":"Craig Jones","orcid":"0000-0002-0629-3006","position":10,"is_corresponding":false},{"id":873874,"name":"T. Y. Alvin Liu","orcid":"0000-0003-2957-0755","position":0,"is_corresponding":true}],"reference_count":27,"raw_metadata":null,"created_at":"2026-07-19T02:49:58.707747Z","pmid":"40502295","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}