{"id":"W4415709876","doi":"10.1371/journal.pcbi.1013624","title":"Nine quick tips for trustworthy machine learning in the biomedical sciences","year":2025,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Ministero dell'Università e della Ricerca","keywords":"Trustworthiness; Pipeline (software); Software deployment; Learning curve; Open research; Open science","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":[],"category_scores_codex":[0.1236874,0.002312028,0.001497932,0.003506306,0.005980336,0.01824887,0.004148879,0.01662683,0.01167413],"category_scores_gemma":[0.2959272,0.00180087,0.00187188,0.001832244,0.02166776,0.02784299,0.01474984,0.02946364,0.00974056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004354695,"about_ca_system_score_gemma":0.01453284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001301207,"about_ca_topic_score_gemma":0.002633658,"domain_scores_codex":[0.8792489,0.08218624,0.009242356,0.004079064,0.02211773,0.003125663],"domain_scores_gemma":[0.6199993,0.2645754,0.01324645,0.03412382,0.05448124,0.01357373],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003743811,0.0003209026,0.00212145,0.002657288,0.0001808351,0.001264733,0.01089846,0.002691385,0.003176034,0.3202923,0.3595956,0.2964266],"study_design_scores_gemma":[0.0001155263,0.0002843803,0.0006882758,0.004746407,0.00008209166,0.000796834,0.004691906,0.002199322,0.003325591,0.5515739,0.4312569,0.0002388754],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.003197337,0.01391173,0.3171102,0.6342579,0.01159846,0.000585377,0.0002759989,0.002568071,0.01649499],"genre_scores_gemma":[0.09886313,0.02077856,0.6981449,0.1501437,0.008104423,0.002145431,0.0006351621,0.002670425,0.0185143],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.8763126,"threshold_uncertainty_score":0.6541293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1733115763309579,"score_gpt":0.4585847963718956,"score_spread":0.2852732200409378,"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."}}