{"id":"W4400653428","doi":"10.1016/j.jfo.2024.104242","title":"Role of artificial intelligence, machine learning and deep learning models in corneal disorders – A narrative review","year":2024,"lang":"ca","type":"review","venue":"Journal Français d Ophtalmologie","topic":"Corneal surgery and disorders","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Optical coherence tomography; Keratoconus; Artificial intelligence; Medicine; Ophthalmology; Ultrasound biomicroscopy; Glaucoma; Convolutional neural network; Fungal keratitis; Deep learning; Corneal topography; Optometry; Keratitis; Computer science; Visual acuity; Cornea","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003495804,0.001210601,0.004705769,0.001148885,0.0004355188,0.0001311988,0.0004376425,0.0008428232,0.001215864],"category_scores_gemma":[0.003087685,0.0009395317,0.001464197,0.002016559,0.0005825851,0.0003560453,0.0004101506,0.007724206,0.0001327415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002602694,"about_ca_system_score_gemma":0.0007492131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003366207,"about_ca_topic_score_gemma":0.000185403,"domain_scores_codex":[0.9919459,0.001596731,0.003493833,0.001048388,0.0008288405,0.001086308],"domain_scores_gemma":[0.9959514,0.001398376,0.001554948,0.0003220109,0.0002677416,0.0005055049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0003435696,0.0003624267,0.001864209,0.03274704,0.0005515506,0.0009062584,0.003645599,0.0009804944,0.000008150369,0.0002209883,0.00006131674,0.9583084],"study_design_scores_gemma":[0.001369861,0.007447946,0.0004828494,0.4412248,0.01272961,0.01134852,0.02837309,0.08659597,0.000009071081,0.04677272,0.3593121,0.00433345],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00279503,0.9908488,0.0003698375,0.000426185,0.0008344793,0.001419489,0.00002089387,0.00005981948,0.003225407],"genre_scores_gemma":[0.110124,0.888798,0.0001312762,0.00007703736,0.0002668572,0.00006666726,0.00008140478,0.0001209684,0.0003338059],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.953975,"threshold_uncertainty_score":0.9996971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05717470250102955,"score_gpt":0.3441297164516333,"score_spread":0.2869550139506037,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}