{"id":"W2558756233","doi":"10.2196/medinform.6373","title":"Finding Important Terms for Patients in Their Electronic Health Records: A Learning-to-Rank Approach Using Expert Annotations","year":2016,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Heart, Lung, and Blood Institute; Health Services Research and Development; U.S. Department of Veterans Affairs","keywords":"Health records; Electronic health record; Rank (graph theory); Computer science; Natural language processing; Artificial intelligence; Information retrieval; Machine learning; Data science; Health care; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.00165173,0.0002047641,0.0003343939,0.0003226549,0.0002371615,0.00007253209,0.0007935817,0.0001489877,0.00001283816],"category_scores_gemma":[0.001102666,0.0001368757,0.0000726673,0.0005749293,0.0000407522,0.0005312235,0.0002221965,0.0005131352,0.00001017896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004891239,"about_ca_system_score_gemma":0.0007380353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008999446,"about_ca_topic_score_gemma":0.00005573274,"domain_scores_codex":[0.9969,0.000179448,0.00115495,0.0002407993,0.0006341547,0.0008906464],"domain_scores_gemma":[0.9981744,0.0004702818,0.0004379565,0.000388978,0.0001006676,0.0004277724],"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":[0.00005039761,0.0004399661,0.1218252,0.0006698302,0.00003151871,0.00000232766,0.1184731,0.0004257553,0.000007314524,0.007392076,0.001956299,0.7487262],"study_design_scores_gemma":[0.001508567,0.0008617869,0.006064717,0.0006069081,0.000001254574,0.00001697446,0.001065812,0.9741829,0.000007501408,0.0007366631,0.01459301,0.0003538828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2782965,0.00003842083,0.7161016,0.003616512,0.0002582163,0.001349543,0.000008248897,0.0001855334,0.0001453983],"genre_scores_gemma":[0.8732538,0.0001238915,0.1214744,0.004389972,0.0001472221,0.000477619,0.00004214374,0.00003467019,0.00005635108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9737571,"threshold_uncertainty_score":0.5581628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02870106664999751,"score_gpt":0.3455673002033193,"score_spread":0.3168662335533218,"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."}}