{"id":"W4400930166","doi":"10.1111/odi.15082","title":"Innovating dental diagnostics: ChatGPT's accuracy on diagnostic challenges","year":2024,"lang":"en","type":"article","venue":"Oral Diseases","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Western University","funders":"","keywords":"Medical diagnosis; Diagnostic accuracy; Diagnostic test; Medicine; Medical physics; Test (biology); Differential diagnosis; Pediatrics; Radiology; Pathology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008816156,0.0001448371,0.0001662046,0.0001508806,0.0001011771,0.00007141547,0.00006585252,0.00006280383,0.000361666],"category_scores_gemma":[0.005832047,0.0001213753,0.00007673111,0.0002596661,0.00005898828,0.0001594465,0.00002611342,0.0001775016,0.0009842383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000101238,"about_ca_system_score_gemma":0.0001965505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001246215,"about_ca_topic_score_gemma":0.00003014215,"domain_scores_codex":[0.9988893,0.00003275868,0.000268648,0.0003039077,0.0002397933,0.0002655365],"domain_scores_gemma":[0.9971278,0.002334005,0.00003413091,0.0002098811,0.00009248469,0.0002017483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000475474,0.0003177285,0.04157693,0.0005266467,0.0000320242,0.0002327184,0.0006739005,0.000004128111,0.00002926773,0.006328604,0.007886698,0.9423438],"study_design_scores_gemma":[0.0003003242,0.003415428,0.8077536,0.01144656,0.0008805895,0.0001634101,0.009883554,0.003786346,0.009078207,0.02366056,0.1282732,0.001358184],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9484549,0.03682947,0.0000366412,0.01080821,0.001689316,0.00044039,0.00004170851,0.0003031246,0.00139621],"genre_scores_gemma":[0.9900546,0.007174112,0.00007116795,0.001088093,0.00122839,0.0001074327,0.0001019936,0.00003010253,0.0001440957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9409856,"threshold_uncertainty_score":0.9997936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1667445600766599,"score_gpt":0.4452014181101006,"score_spread":0.2784568580334406,"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."}}