{"id":"W4399645653","doi":"10.1038/s41391-024-00847-7","title":"Can ChatGPT provide high-quality patient information on male lower urinary tract symptoms suggestive of benign prostate enlargement?","year":2024,"lang":"en","type":"article","venue":"Prostate Cancer and Prostatic Diseases","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact; McMaster University; University of Toronto","funders":"","keywords":"Medicine; Lower urinary tract symptoms; Wilcoxon signed-rank test; International Prostate Symptom Score; Prostate; Rating scale; Quality of life (healthcare); Prostatitis; Urinary system; Urology; Prostate cancer; Reference range; Internal medicine; Physical therapy; Mann–Whitney U test; Psychology; Cancer","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":[0.0001938854,0.0002452921,0.000328373,0.0001913239,0.0001246526,0.00009771964,0.00004779376,0.00005950955,0.000189951],"category_scores_gemma":[0.0001716079,0.0001967873,0.00007614622,0.0002864821,0.0001608723,0.0004941606,0.00003011706,0.0001779437,0.00002038803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001998678,"about_ca_system_score_gemma":0.000789534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001229332,"about_ca_topic_score_gemma":0.00001637179,"domain_scores_codex":[0.998063,0.00006970603,0.0007340969,0.0003501146,0.0004233745,0.0003596797],"domain_scores_gemma":[0.998766,0.0002027262,0.0002010199,0.0002224499,0.0003218815,0.0002859362],"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":[0.00413012,0.001700655,0.1372386,0.01086592,0.0002186831,0.0001258671,0.0419068,0.0001426695,0.0002494394,0.002140599,0.00216812,0.7991126],"study_design_scores_gemma":[0.003290501,0.04871153,0.7083445,0.02108514,0.002760055,0.0003941598,0.03342797,0.004240058,0.07619122,0.03637535,0.06161393,0.003565577],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866746,0.003086769,0.00001943658,0.004926207,0.0006639147,0.002481417,0.001815797,0.00008858964,0.0002432649],"genre_scores_gemma":[0.995464,0.001428196,0.00006143303,0.001007632,0.00009596744,0.0008853168,0.0005645817,0.00002568283,0.0004671357],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.795547,"threshold_uncertainty_score":0.8024752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03333502331705095,"score_gpt":0.3656681006813083,"score_spread":0.3323330773642574,"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."}}