{"id":"W7117892033","doi":"10.1109/icicnis66685.2025.11315830","title":"Optical Coherence Tomography for Efficient Diagnosis of Ophthalmological Optical Pathway Disease using Machine Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Optical coherence tomography; Medical imaging; Surgical planning; Multidisciplinary approach; Computer technology; Imaging science","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":[0.0009623446,0.0005168819,0.00129563,0.0005656886,0.0003318337,0.00009221453,0.000324634,0.0002243054,0.0007277515],"category_scores_gemma":[0.003421163,0.0004008895,0.001233353,0.00148741,0.0009351172,0.000051122,0.0002854166,0.0006617301,0.00000935605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009597706,"about_ca_system_score_gemma":0.0003563416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001080239,"about_ca_topic_score_gemma":8.681923e-7,"domain_scores_codex":[0.9960913,0.0002311592,0.001179644,0.001001774,0.0006404322,0.0008556687],"domain_scores_gemma":[0.9960613,0.001911789,0.000230314,0.0005335548,0.0005249116,0.0007380868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002055948,0.004435479,0.9482109,0.001927795,0.001001104,0.0004384674,0.00007792799,0.01306918,0.007648542,0.009193109,0.0000595264,0.01188205],"study_design_scores_gemma":[0.002905791,0.001439727,0.03898839,0.002913385,0.005247888,0.00003760782,0.000473887,0.9202838,0.02635686,0.0003409705,0.0003867721,0.0006249403],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9262736,0.00650243,0.06038015,0.002115642,0.0002822205,0.0009196033,0.00005623705,0.00007383189,0.003396216],"genre_scores_gemma":[0.9835525,0.0001513922,0.0145795,0.0001933064,0.0001181978,0.00009980158,0.0000419786,0.00003030855,0.00123298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9092225,"threshold_uncertainty_score":0.9998443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0299972663911496,"score_gpt":0.3244274502167593,"score_spread":0.2944301838256097,"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."}}