{"id":"W4386496107","doi":"10.2196/42477","title":"Applying Natural Language Processing to Textual Data From Clinical Data Warehouses: Systematic Review","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Unstructured data; Natural language processing; Information retrieval; Artificial intelligence; Data extraction; Information extraction; Named-entity recognition; Systematic review; Big data; MEDLINE; Data science; Task (project management); Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.00567947,0.0002483572,0.0008579629,0.0001399252,0.0001819851,0.0002975834,0.01078778,0.0001839742,0.00004677477],"category_scores_gemma":[0.01136236,0.0001830583,0.00005474626,0.001266941,0.00006876267,0.001507203,0.008945672,0.001209522,0.001830792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004449701,"about_ca_system_score_gemma":0.0005587715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006883311,"about_ca_topic_score_gemma":0.00004642088,"domain_scores_codex":[0.9943186,0.0003884326,0.002203391,0.0005126848,0.002025028,0.000551861],"domain_scores_gemma":[0.9921876,0.001448609,0.0005376025,0.005104137,0.0001056494,0.0006164128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006261515,0.00008694625,0.0005210342,0.3904821,0.00008858338,0.0001981787,0.01149547,0.00001117558,3.972625e-7,0.0002297859,0.1686792,0.4282008],"study_design_scores_gemma":[0.0001965491,0.00003143956,0.0001434336,0.06248709,0.00003681313,0.00003347381,0.001473653,0.928754,1.596321e-7,0.0000112594,0.006581551,0.0002505233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01366849,0.08995989,0.7653082,0.06380881,0.008117448,0.03640635,0.002008911,0.01713054,0.003591361],"genre_scores_gemma":[0.2747566,0.006074912,0.4375767,0.2507248,0.004381977,0.003321808,0.02190054,0.000301444,0.0009611779],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9287429,"threshold_uncertainty_score":0.9990698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1218366320840245,"score_gpt":0.4661288339060583,"score_spread":0.3442922018220338,"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."}}