{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03278127,0.0001817881,0.0005024718,0.0002075141,0.001157491,0.00005215916,0.002366833,0.0007550871,0.0001009215],"category_scores_gemma":[0.0228979,0.00008803099,0.00007136026,0.001052362,0.0005105201,0.001160314,0.0007655525,0.006672638,0.0001552893],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003531192,"about_ca_system_score_gemma":0.0108037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004022861,"about_ca_topic_score_gemma":0.0004436558,"domain_scores_codex":[0.9884905,0.002587961,0.002577505,0.0002392513,0.004944524,0.001160282],"domain_scores_gemma":[0.9765468,0.01865815,0.001203252,0.001320455,0.001901607,0.0003697802],"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":[0.005656558,0.0008705996,0.04586307,0.1243724,0.0003390369,0.000009713163,0.2980478,0.00001428885,0.00002805132,0.0100684,0.1155987,0.3991314],"study_design_scores_gemma":[0.005378567,0.001453508,0.003567493,0.01182243,0.00003470936,0.00004859369,0.3229617,0.6264827,0.00003252664,0.00002211664,0.02794334,0.000252309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9635451,0.000554554,0.004702292,0.008170789,0.002019621,0.01538029,0.00005869191,0.0001557512,0.005412926],"genre_scores_gemma":[0.9966296,0.00005173941,0.0005158901,0.0009490483,0.0006066164,0.0008580326,0.0001041235,0.00002480439,0.0002601411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6264684,"threshold_uncertainty_score":0.9959552,"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."}}