{"id":"W4391643387","doi":"10.1007/s00405-024-08464-9","title":"Is generative pre-trained transformer artificial intelligence (Chat-GPT) a reliable tool for guidelines synthesis? A preliminary evaluation for biologic CRSwNP therapy","year":2024,"lang":"en","type":"article","venue":"European Archives of Oto-Rhino-Laryngology","topic":"Sinusitis and nasal conditions","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Mepolizumab; Medicine; Omalizumab; Dupilumab; Nasal polyps; Systematic review; Intensive care medicine; Population; Asthma; MEDLINE; Immunology; Immunoglobulin E; Antibody; Eosinophil","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001124159,0.0003355308,0.0005644895,0.000388146,0.0001933816,0.0000376939,0.0002509938,0.00009851858,0.0004100319],"category_scores_gemma":[0.001092527,0.0002628227,0.0005042469,0.000208178,0.0002715593,0.0001361576,0.00003734119,0.0001929821,0.00004056361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003096265,"about_ca_system_score_gemma":0.0002511651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001298198,"about_ca_topic_score_gemma":0.000006416095,"domain_scores_codex":[0.9973322,0.0003741102,0.0009419988,0.0007110704,0.0002087768,0.0004317994],"domain_scores_gemma":[0.9974937,0.001551569,0.000159764,0.0003889045,0.0003052303,0.0001008605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.008381426,0.0007319769,0.0002921647,0.0007211768,0.001024944,0.00007165681,0.007786563,0.0003145932,0.6357002,0.01235971,0.01115951,0.3214561],"study_design_scores_gemma":[0.003523797,0.02327555,0.03311963,0.002280768,0.00222575,0.0004819498,0.0009664704,0.2568058,0.5812747,0.04344269,0.05098314,0.001619645],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6701194,0.005590422,0.3058312,0.005773684,0.0006534689,0.006887691,0.001257494,0.0002460013,0.00364067],"genre_scores_gemma":[0.951807,0.0006573547,0.04183343,0.001900012,0.0009063655,0.001226692,0.0006790793,0.0001152728,0.0008747703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3198365,"threshold_uncertainty_score":0.9999824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1328556145027562,"score_gpt":0.3877791342628926,"score_spread":0.2549235197601364,"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."}}