{"id":"W4409136955","doi":"10.1371/journal.pone.0320151","title":"Using artificial intelligence tools to automate data extraction for living evidence syntheses","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Python (programming language); Parsing; Data extraction; Artificial intelligence; Information extraction; Data science; Machine learning; MEDLINE; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.132361,0.002838778,0.002688419,0.01475802,0.002724072,0.01160881,0.003610309,0.001826646,0.03609423],"category_scores_gemma":[0.3303203,0.003252324,0.007118236,0.009682677,0.00226336,0.00723275,0.008423784,0.005054281,0.01024648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003368021,"about_ca_system_score_gemma":0.0227012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003640605,"about_ca_topic_score_gemma":0.008640285,"domain_scores_codex":[0.940244,0.03704679,0.01199823,0.00428972,0.005881674,0.0005395457],"domain_scores_gemma":[0.5561284,0.3739018,0.02004163,0.03340707,0.01468418,0.001836965],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001148146,0.0002403354,0.006045855,0.03162078,0.003828559,0.000818475,0.005362357,0.01061324,0.009127084,0.05798516,0.1210825,0.7521276],"study_design_scores_gemma":[0.001690057,0.0002734804,0.006284562,0.009100267,0.002167481,0.0006876791,0.001116767,0.1004624,0.03079951,0.3603058,0.486477,0.0006349722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003983702,0.002203683,0.8987976,0.009313983,0.0009916195,0.003889217,0.01349653,0.06118327,0.006140405],"genre_scores_gemma":[0.009740935,0.0005477904,0.9804956,0.0008712307,0.0001307825,0.002661467,0.002350852,0.002442077,0.0007591248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8676391,"threshold_uncertainty_score":0.7,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.590885932505264,"score_gpt":0.4242192356674022,"score_spread":0.1666666968378618,"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."}}