{"id":"W2946991228","doi":"10.2196/13331","title":"Improving the Efficacy of the Data Entry Process for Clinical Research With a Natural Language Processing–Driven Medical Information Extraction System: Quantitative Field Research","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Shanghai Jiao Tong University; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Data extraction; Observational study; Electronic data capture; Field (mathematics); Process (computing); Data science; Data quality; Data collection; Information extraction; Chart; Quality (philosophy); Electronic medical record; Clinical trial; Data mining; Information retrieval; Medicine; MEDLINE; Pathology; Engineering; Operations management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3670715,0.001395797,0.0009141458,0.00223307,0.001064178,0.00318593,0.002355034,0.001481773,0.00307084],"category_scores_gemma":[0.5085858,0.0009308654,0.001710289,0.001538129,0.003449215,0.006154479,0.002077977,0.001483805,0.0004860416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003850878,"about_ca_system_score_gemma":0.005786783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002208368,"about_ca_topic_score_gemma":0.001558668,"domain_scores_codex":[0.6934523,0.2754409,0.01060947,0.006292169,0.01292103,0.001284231],"domain_scores_gemma":[0.2373493,0.6674027,0.02500682,0.02305621,0.04529661,0.001888442],"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":[0.01839623,0.03882941,0.1743339,0.01281723,0.0038752,0.0001488236,0.01442064,0.0151737,0.02068336,0.007533519,0.004490662,0.6892972],"study_design_scores_gemma":[0.01989486,0.1584599,0.4846944,0.007029407,0.00701427,0.0006281159,0.01261211,0.1835494,0.08307175,0.02070409,0.02132171,0.001019986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7840261,0.002031262,0.1819168,0.002957726,0.0002964245,0.0229235,0.0008094604,0.0005696499,0.004468805],"genre_scores_gemma":[0.7815013,0.0007313736,0.2063167,0.0007918195,0.0001913742,0.009433359,0.0004111803,0.00009251094,0.0005304956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6329285,"threshold_uncertainty_score":0.7805135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2661479106540887,"score_gpt":0.6249761169392618,"score_spread":0.3588282062851731,"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."}}