{"id":"W2543360016","doi":"10.2196/medinform.5544","title":"Natural Language Processing–Enabled and Conventional Data Capture Methods for Input to Electronic Health Records: A Comparative Usability Study","year":2016,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine","keywords":"Usability; Documentation; Dictation; Computer science; Workflow; Natural language processing; Protocol (science); Artificial intelligence; Information retrieval; Medicine; Database; Human–computer interaction; Speech recognition; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.07102712,0.001040072,0.001337113,0.002914698,0.001256835,0.002163353,0.001406776,0.001166086,0.001635548],"category_scores_gemma":[0.1558709,0.0007263308,0.002319683,0.001466607,0.001738331,0.003252977,0.002007426,0.0008643047,0.0002918388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001927797,"about_ca_system_score_gemma":0.001618038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001316817,"about_ca_topic_score_gemma":0.001915419,"domain_scores_codex":[0.9318895,0.05072727,0.007441302,0.002475457,0.0063897,0.001076776],"domain_scores_gemma":[0.7785581,0.1798832,0.009653506,0.00641228,0.02397752,0.001515392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.04176598,0.04126583,0.1566112,0.02119062,0.003468574,0.001929934,0.2031329,0.0025945,0.01965618,0.001176243,0.0021829,0.5050252],"study_design_scores_gemma":[0.01150286,0.3532511,0.4694202,0.005422808,0.005070068,0.003490671,0.09784602,0.01426698,0.02259143,0.001789206,0.01429514,0.00105356],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935147,0.0006829119,0.002732578,0.00006384542,0.0000453825,0.001886804,0.00006384723,0.00002735886,0.000982705],"genre_scores_gemma":[0.9798756,0.001013621,0.01345291,0.0001729752,0.00008546494,0.004564599,0.00019243,0.00005129391,0.0005912234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07102712,"threshold_uncertainty_score":0.3756318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1075956413765061,"score_gpt":0.5541402620888575,"score_spread":0.4465446207123513,"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."}}