{"id":"W4389480302","doi":"10.3389/fcvm.2023.1283338","title":"Does artificial intelligence enhance physician interpretation of optical coherence tomography: insights from eye tracking","year":2023,"lang":"en","type":"article","venue":"Frontiers in Cardiovascular Medicine","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Hamilton Health Sciences; Hamilton General Hospital","funders":"Abbott Vascular","keywords":"Optical coherence tomography; Dwell time; Eye tracking; Artificial intelligence; Medicine; Fixation (population genetics); Software; Computer science; Medical physics; Computer vision; Ophthalmology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003293283,0.0002437972,0.0007162112,0.0005248988,0.00004137986,0.00001608318,0.0003687522,0.0001396557,0.00001539853],"category_scores_gemma":[0.0001182608,0.0001877238,0.0003479642,0.00226166,0.0004166069,0.000186042,0.00003702249,0.000343673,0.00001711406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005680279,"about_ca_system_score_gemma":0.00001569072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006471029,"about_ca_topic_score_gemma":0.00002892835,"domain_scores_codex":[0.9980134,0.00007347647,0.0005992819,0.0004271496,0.0005653652,0.0003213603],"domain_scores_gemma":[0.9989473,0.0001467142,0.00005262475,0.0006471712,0.000100812,0.0001053856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005861747,0.00008219324,0.004646347,0.0002632549,0.001559306,0.00004606869,0.004857034,0.08617986,0.01823461,0.001663761,0.0005167393,0.8818922],"study_design_scores_gemma":[0.0006848417,0.0002628211,0.1050569,0.002251538,0.001007873,0.000001259808,0.01258052,0.542623,0.1785353,0.1536738,0.001827068,0.001495098],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1805692,0.009379,0.8049747,0.0001382185,0.001964918,0.0006056494,0.00001843409,0.0004534603,0.001896343],"genre_scores_gemma":[0.9924267,0.0002712717,0.006813067,0.00002043127,0.0002432703,0.0001322264,0.00005388983,0.00003554148,0.000003633378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8803971,"threshold_uncertainty_score":0.7655153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01094642547748292,"score_gpt":0.2504306689717604,"score_spread":0.2394842434942775,"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."}}