{"id":"W4405316841","doi":"10.1016/j.jisako.2024.100376","title":"ChatGPT-3.5 and -4 provide mostly accurate information when answering patients’ questions relating to femoroacetabular impingement syndrome and arthroscopic hip surgery","year":2024,"lang":"en","type":"article","venue":"Journal of ISAKOS Joint Disorders & Orthopaedic Sports Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; McGill University; McMaster University","funders":"","keywords":"Femoroacetabular impingement; Medicine; Physical therapy","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":[0.001665452,0.000247055,0.0006112924,0.0008811817,0.0001688637,0.00006148629,0.00004582948,0.0001099842,0.0001205502],"category_scores_gemma":[0.001282635,0.0001924541,0.0001047773,0.0004090467,0.0001337975,0.000891135,0.00004042519,0.0004799562,0.000005007542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001495218,"about_ca_system_score_gemma":0.0003764797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002276075,"about_ca_topic_score_gemma":0.00003161479,"domain_scores_codex":[0.9969946,0.00004921641,0.001660642,0.000240462,0.0007122857,0.0003428568],"domain_scores_gemma":[0.9982737,0.000206491,0.0004926691,0.000186538,0.0003627633,0.0004778125],"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":[0.0001576128,0.0001174639,0.4245581,0.001644308,0.0001256609,0.0001599065,0.01807121,0.00006819245,0.0001193262,0.0002031948,0.003900983,0.5508741],"study_design_scores_gemma":[0.001052167,0.004134799,0.8780586,0.02416573,0.001110676,0.002375552,0.02088965,0.003069314,0.0001671575,0.004147672,0.06005038,0.0007783883],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9587795,0.005621959,0.002110649,0.03065116,0.001894785,0.0007921766,0.000002407522,0.00005385332,0.00009346252],"genre_scores_gemma":[0.9938769,0.003570626,0.0007387238,0.001333237,0.0003440626,0.00002092961,0.00002864316,0.00002766327,0.00005924634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5500957,"threshold_uncertainty_score":0.7848052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0419467865413583,"score_gpt":0.3246136134742312,"score_spread":0.2826668269328729,"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."}}