{"id":"W4389793507","doi":"10.4081/ejtm.2023.12114","title":"ChatGPT in the development of medical questionnaires. The example of the low back pain","year":2023,"lang":"en","type":"article","venue":"European Journal of Translational Myology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Oswestry Disability Index; Physical therapy; Low back pain; Medicine; Back pain; Physical medicine and rehabilitation; Rating scale; Psychology; Alternative medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008588837,0.00005488865,0.0001389166,0.00009313974,0.00006638248,0.000003068228,0.0003120385,0.00003467174,0.0001710089],"category_scores_gemma":[0.0007701159,0.00002623187,0.00007472271,0.0003300786,0.0001833254,0.00002665979,0.00001289292,0.0003029491,0.00002223615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001403068,"about_ca_system_score_gemma":0.0005583604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005340741,"about_ca_topic_score_gemma":0.0001456102,"domain_scores_codex":[0.9971514,0.001286261,0.000839788,0.00006447576,0.0005457582,0.0001123304],"domain_scores_gemma":[0.9983978,0.001022664,0.0002436092,0.0001272774,0.0001696768,0.0000390249],"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":[0.0006352146,0.0006904534,0.2040809,0.0005263056,0.0001953438,0.0000944155,0.1751598,0.001515805,0.002019155,0.01024819,0.01236783,0.5924665],"study_design_scores_gemma":[0.0002294664,0.0002378893,0.9745045,0.0006342329,0.00002067896,0.0001446405,0.00227272,0.0005915773,0.001277106,0.00193908,0.01809572,0.00005234418],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8946865,0.0002836121,0.003147084,0.1006816,0.0004926902,0.0001762443,0.000001266776,0.000003082106,0.0005279986],"genre_scores_gemma":[0.9984424,0.00005659609,0.0003727121,0.0008378,0.0002479496,0.000001378964,0.000004380377,0.000006710391,0.00003010295],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7704237,"threshold_uncertainty_score":0.2976737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.176172018817294,"score_gpt":0.3910555015728286,"score_spread":0.2148834827555346,"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."}}