{"id":"W4406352685","doi":"10.5195/jmla.2025.1936","title":"Algorithmic indexing in MEDLINE frequently overlooks important concepts and may compromise literature search results","year":2025,"lang":"en","type":"article","venue":"Journal of the Medical Library Association JMLA","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada; Université de Montréal","funders":"McGill University Health Centre; McGill University","keywords":"Search engine indexing; Information retrieval; MEDLINE; Computer science; Medical record; Subject (documents); Index (typography); Data mining; Medicine; Library science; World Wide Web; Radiology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001347331,0.00009554228,0.0002170847,0.00007645238,0.00005502808,0.00005424158,0.0003130301,0.000383822,0.00001417049],"category_scores_gemma":[0.002425651,0.00006005647,0.00009280057,0.0002207118,0.0001057195,0.00001517121,0.0001954585,0.0006211866,2.68015e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003477724,"about_ca_system_score_gemma":0.0003251831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003701925,"about_ca_topic_score_gemma":0.000003658461,"domain_scores_codex":[0.998325,0.0003092242,0.0005749403,0.0001437582,0.0004710957,0.0001759176],"domain_scores_gemma":[0.9991851,0.0001926877,0.0003314434,0.0001207415,0.00005277591,0.0001172033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001688125,0.0005366629,0.7762861,0.0002030568,0.0007607967,0.0003536307,0.001746368,0.00003669556,0.02333576,0.0008525801,0.1203944,0.07380584],"study_design_scores_gemma":[0.02120918,0.001123602,0.4523631,0.004196045,0.0001320271,0.0003250903,0.001088709,0.003465371,0.04400442,0.005045502,0.4663623,0.0006846318],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9454666,0.006081199,0.0001536062,0.0464691,0.0008208259,0.0001276931,0.00004746976,0.00001018162,0.0008233559],"genre_scores_gemma":[0.9892593,0.001466529,0.001306885,0.002493454,0.0005894847,0.000002314393,0.00005305029,0.000009742716,0.004819259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3459679,"threshold_uncertainty_score":0.2960387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005347617935268055,"score_gpt":0.2804653613786845,"score_spread":0.2751177434434164,"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."}}