{"id":"W4390571530","doi":"10.1007/s00246-023-03385-6","title":"Progression of an Artificial Intelligence Chatbot (ChatGPT) for Pediatric Cardiology Educational Knowledge Assessment","year":2024,"lang":"en","type":"article","venue":"Pediatric Cardiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; SickKids Foundation; Hospital for Sick Children; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Subspecialty; Medicine; Test (biology); Modalities; Chatbot; Stethoscope; Cardiology; Internal medicine; Medical education; Pediatrics; Medical physics; Artificial intelligence; Family medicine; Radiology; Computer 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":[],"consensus_categories":[],"category_scores_codex":[0.001187416,0.0002477915,0.0007011052,0.0006195556,0.0001468324,0.0000241125,0.000179847,0.0003881522,0.00008561862],"category_scores_gemma":[0.0004655237,0.000221028,0.0003367435,0.0007356429,0.0001372127,0.0001274388,0.0000574706,0.000376577,0.00009039643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002287318,"about_ca_system_score_gemma":0.00228743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005585756,"about_ca_topic_score_gemma":0.00001359231,"domain_scores_codex":[0.9973728,0.0002256582,0.0009607488,0.000689753,0.0002319453,0.0005190986],"domain_scores_gemma":[0.99742,0.001177293,0.0001621839,0.0004142857,0.0005790037,0.0002472066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007140579,0.0009447362,0.2538103,0.004160829,0.0004125739,0.00007458703,0.00374915,0.0008795277,0.001428238,0.05139747,0.01166131,0.6707672],"study_design_scores_gemma":[0.0009046728,0.03438214,0.3613525,0.0005978985,0.01651981,0.005075996,0.01548328,0.07705043,0.01850086,0.4034794,0.06110692,0.005546055],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9200921,0.01469703,0.04667534,0.003481923,0.01078768,0.002104087,0.00009818618,0.0001840243,0.001879629],"genre_scores_gemma":[0.9716859,0.001894075,0.003494964,0.0000517846,0.02185035,0.0005573569,0.0003232556,0.00004225794,0.0001000703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6652212,"threshold_uncertainty_score":0.9013261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1389619495919286,"score_gpt":0.4954971808345658,"score_spread":0.3565352312426371,"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."}}