{"id":"W4408806526","doi":"10.1136/bmj-2024-082505","title":"PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","year":2025,"lang":"en","type":"article","venue":"BMJ","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":383,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Machine learning; Regression; Artificial intelligence; Quality (philosophy); Data mining; Predictive modelling; Statistics; Mathematics","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":[0.006644177,0.0001347251,0.0002803329,0.0001136865,0.000209428,0.00008547935,0.0003657236,0.0001170217,0.000004546266],"category_scores_gemma":[0.0006578119,0.0001039851,0.00004895169,0.0004463006,0.00006222502,0.0003665605,0.0003008853,0.0002479374,1.017019e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009000823,"about_ca_system_score_gemma":0.0003446054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003612009,"about_ca_topic_score_gemma":0.00005254835,"domain_scores_codex":[0.9965765,0.001665589,0.0007599838,0.0005601255,0.0002418901,0.0001959094],"domain_scores_gemma":[0.997929,0.0005967458,0.0003791659,0.0007410105,0.0002923799,0.00006173391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002324869,0.0002054131,0.03232628,0.0005411992,0.00003086086,4.994844e-7,0.0005654941,0.08046215,0.001452423,0.08995175,0.0001473852,0.7940841],"study_design_scores_gemma":[0.00007259728,0.0001456944,0.00804875,0.00007931147,0.0000155146,0.000001773991,0.00005372121,0.9030159,0.001732159,0.08665711,0.00008702897,0.00009045043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07537428,0.00002044471,0.9217816,0.00101895,0.0002244381,0.001390482,0.00003715819,0.0001111869,0.0000414413],"genre_scores_gemma":[0.3094008,0.000003872178,0.6903543,0.00007089086,0.00004362045,0.00009173813,0.00001239426,0.000005534633,0.00001691087],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8225538,"threshold_uncertainty_score":0.424039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2415969247576334,"score_gpt":0.5481893865262898,"score_spread":0.3065924617686564,"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."}}