{"id":"W4387710580","doi":"10.1016/j.jacc.2023.09.204","title":"TCT-198 Does Artificial Intelligence Enhance Physician Interpretation of Optical Coherence Tomography: Insights From Eye Tracking","year":2023,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hamilton Health Sciences; McMaster University","funders":"","keywords":"Medicine; Optical coherence tomography; Interpretation (philosophy); Artificial intelligence; Coherence (philosophical gambling strategy); Tracking (education); Optometry; Medical physics; Computer vision; Ophthalmology; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001635726,0.0002677778,0.0002138953,0.0005811576,0.000251773,0.001567082,0.0003022815,0.0008084378,0.004846051],"category_scores_gemma":[0.02297863,0.0001409415,0.0003474248,0.0004148687,0.0002954457,0.0008621317,0.0003854072,0.0004906114,0.0007135872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006149084,"about_ca_system_score_gemma":0.0008176145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005423619,"about_ca_topic_score_gemma":0.00742767,"domain_scores_codex":[0.9992662,0.0002798676,0.00005396685,0.0001095281,0.0002321547,0.00005830301],"domain_scores_gemma":[0.9856779,0.009988934,0.001604178,0.0006043314,0.001805818,0.0003189079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004587136,0.001242424,0.6112074,0.0005660288,0.0007619017,0.0007673711,0.0008995053,0.005630094,0.03399632,0.002698681,0.0110156,0.3266276],"study_design_scores_gemma":[0.0002030802,0.0009354997,0.9493139,0.0001062016,0.0003342225,0.0008200424,0.000316693,0.03233934,0.00675517,0.002745279,0.006077541,0.00005307519],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9647508,0.001300026,0.004166733,0.001991215,0.0001123308,0.0001246411,0.001003103,0.0001343858,0.02641678],"genre_scores_gemma":[0.9944536,0.0003499463,0.002813529,0.0003983268,0.0001017394,0.00003228607,0.0004014328,0.00004555111,0.001403596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005423619,"threshold_uncertainty_score":0.01621169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04938753880597112,"score_gpt":0.3807086617400264,"score_spread":0.3313211229340553,"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."}}