{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2410403,0.003013611,0.003894647,0.01397767,0.001619033,0.0112464,0.005833182,0.004593613,0.03412476],"category_scores_gemma":[0.6006835,0.002474154,0.01013642,0.01047784,0.002120628,0.01166135,0.01187545,0.007884391,0.01279455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00475092,"about_ca_system_score_gemma":0.01760498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003504113,"about_ca_topic_score_gemma":0.005748121,"domain_scores_codex":[0.7650961,0.1317586,0.0458893,0.003781891,0.05145082,0.002023289],"domain_scores_gemma":[0.1978616,0.6533688,0.03762343,0.02573518,0.08235322,0.003057799],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001489682,0.0003000126,0.01432029,0.02112102,0.002378933,0.0002101871,0.001514489,0.004328531,0.000476752,0.02037301,0.3176759,0.6158112],"study_design_scores_gemma":[0.002260516,0.001460457,0.02942885,0.03780144,0.005633933,0.002773734,0.001106533,0.03968269,0.004002165,0.1130214,0.761363,0.001465194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01123581,0.02249645,0.7516647,0.04649881,0.00390618,0.01652606,0.05582919,0.05319675,0.03864612],"genre_scores_gemma":[0.05130324,0.009659451,0.8634171,0.009330659,0.001519891,0.02655106,0.02512823,0.005934461,0.007155978],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7589597,"threshold_uncertainty_score":0.9359324,"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."}}