{"id":"W3097720724","doi":"10.2196/19612","title":"Amplifying Domain Expertise in Clinical Data Pipelines","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; National Science Foundation","keywords":"Computer science; Domain (mathematical analysis); Data science; Pipeline (software); USable; Automatic summarization; Subject-matter expert; Data curation; Visualization; Process (computing); Domain model; Domain knowledge; Software engineering; Data mining; Artificial intelligence; Expert system; World Wide Web","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01344237,0.0001320066,0.0003758319,0.0001621139,0.00008647885,0.0004487568,0.00424653,0.0001228636,0.0007130255],"category_scores_gemma":[0.01903175,0.00009005053,0.00007043416,0.001193228,0.0001807333,0.000801188,0.003509298,0.0004151243,0.001668617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001632245,"about_ca_system_score_gemma":0.0001501894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007836728,"about_ca_topic_score_gemma":0.00002921712,"domain_scores_codex":[0.9929814,0.0002004868,0.002799473,0.0004575897,0.003216516,0.0003445405],"domain_scores_gemma":[0.9956444,0.001283728,0.0003537756,0.00198142,0.00008904558,0.000647645],"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":[0.0000164118,0.0000686362,0.004935413,0.00001743746,0.00000472228,0.00002582198,0.005351675,0.00001981723,3.684092e-7,0.0002859266,0.4521539,0.5371199],"study_design_scores_gemma":[0.0006612849,0.00003186405,0.002316785,0.00004940091,0.000002253697,0.000004038132,0.007739268,0.5596333,7.812706e-7,0.0008036505,0.4286261,0.0001313475],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5169219,0.0001419789,0.4435666,0.02480412,0.002689596,0.0006830054,0.00008919931,0.000262843,0.01084081],"genre_scores_gemma":[0.9059083,0.00006551944,0.05012111,0.04168549,0.001479237,0.00002445755,0.0002897116,0.00002135219,0.0004048232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5596135,"threshold_uncertainty_score":0.9991087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4335152015891584,"score_gpt":0.5153609075619537,"score_spread":0.08184570597279534,"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."}}