{"id":"W4415216333","doi":"10.1101/2025.10.13.25337935","title":"A machine learning model to support the screening for methods guidance articles in MEDLINE: A performance evaluation of ASReview simulation mode","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Support vector machine; Naive Bayes classifier; Artificial neural network; Feature (linguistics); Precision and recall; Search engine indexing; Feature extraction; Recall","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":[0.007023941,0.001265827,0.00144679,0.003409639,0.0004878873,0.001412694,0.001643534,0.001440583,0.001836211],"category_scores_gemma":[0.02342075,0.0004499337,0.001315125,0.001606378,0.0003059446,0.001499401,0.0006587059,0.001065728,0.0009844786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001819087,"about_ca_system_score_gemma":0.003423535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01795795,"about_ca_topic_score_gemma":0.01484548,"domain_scores_codex":[0.9981805,0.0008557445,0.0002374931,0.000391822,0.0002463377,0.00008807617],"domain_scores_gemma":[0.9751875,0.01932032,0.001021686,0.0007932028,0.003175077,0.0005021651],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005455406,0.001967032,0.06608349,0.001818041,0.001177555,0.0004392669,0.000297772,0.6118839,0.006026681,0.001053452,0.0182131,0.2855843],"study_design_scores_gemma":[0.00008213914,0.0002115968,0.001365113,0.00003823338,0.00007802726,0.00004550326,0.00002709387,0.9956664,0.001638524,0.0003431108,0.0004896118,0.0000145273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.811646,0.005915571,0.1466688,0.002829183,0.0005751689,0.001527221,0.008787811,0.01836098,0.003689097],"genre_scores_gemma":[0.8801283,0.0008558954,0.1074552,0.0006484601,0.0001231208,0.0006398506,0.008552903,0.0001227348,0.001473712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9929761,"threshold_uncertainty_score":0.03714663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1593125589647672,"score_gpt":0.4639775403229227,"score_spread":0.3046649813581555,"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."}}