{"id":"W4411295747","doi":"10.1097/wno.0000000000002372","title":"Comment: Diagnosing Neuro-Ophthalmology Diseases Based on Case Reports: DeepSeek vs ChatGPT","year":2025,"lang":"en","type":"article","venue":"Journal of Neuro-Ophthalmology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Neuro-ophthalmology; Optometry; Ophthalmology; Medicine; Computer science; Medical physics; Glaucoma","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"],"consensus_categories":[],"category_scores_codex":[0.000637088,0.0003470207,0.0008772964,0.000881425,0.0003016528,0.0000410128,0.0001762194,0.0002726119,0.0005912345],"category_scores_gemma":[0.005344297,0.0003110876,0.0003607874,0.0005620354,0.0002437019,0.0001542433,0.00006606276,0.0009881752,0.00002362318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002175929,"about_ca_system_score_gemma":0.0007208816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002107795,"about_ca_topic_score_gemma":0.000001798744,"domain_scores_codex":[0.9963298,0.0005000717,0.001693309,0.0005071412,0.0003745521,0.0005951067],"domain_scores_gemma":[0.9932402,0.004088689,0.0009659729,0.000683453,0.0005811576,0.0004404934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"case_report","study_design_gemma":"case_report","study_design_scores_codex":[0.001982008,0.00188647,0.3726378,0.0002931158,0.00009193439,0.6051881,0.0002159525,0.0004527062,0.0007689407,0.000142278,0.01332412,0.003016594],"study_design_scores_gemma":[0.000532296,0.006471026,0.07325286,0.0005200792,0.0004370692,0.9034265,0.0004666453,0.00139143,0.002886973,0.00309594,0.007210687,0.0003085433],"study_design_candidate":"case_report","study_design_consensus":"case_report","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9322179,0.0005806935,0.0001262931,0.05994883,0.005187252,0.000458746,0.000008827578,0.00003014252,0.001441295],"genre_scores_gemma":[0.9823249,0.00005501658,0.0002326035,0.01649672,0.0006735822,0.00003000906,0.00001445747,0.00004456205,0.0001281272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.299385,"threshold_uncertainty_score":0.9999341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09185055630844646,"score_gpt":0.4144553078256665,"score_spread":0.3226047515172201,"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."}}