{"id":"W2892534902","doi":"10.3233/978-1-61499-896-9-160","title":"Finding Needles in the Haystack: Identifying Patients with Rare Subtype of Multiple Myeloma Supported by a Data Warehouse and Information Extraction","year":2018,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Multiple Myeloma Research and Treatments","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Haystack; Multiple myeloma; Data warehouse; Warehouse; Extraction (chemistry); Data extraction; Medicine; Computer science; Database; Business; MEDLINE; World Wide Web; Internal medicine; Biology; Chemistry; Chromatography; Marketing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00306479,0.0009230311,0.001186633,0.007876159,0.0008309393,0.002510774,0.001058482,0.001151469,0.002306334],"category_scores_gemma":[0.01012448,0.0005251639,0.001383503,0.005462734,0.0002561434,0.001757336,0.00168039,0.0006500807,0.001983082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006080983,"about_ca_system_score_gemma":0.001645641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005466072,"about_ca_topic_score_gemma":0.006792637,"domain_scores_codex":[0.9975142,0.0004522951,0.0007053505,0.000505404,0.0006641573,0.0001585752],"domain_scores_gemma":[0.9928741,0.00334553,0.001076288,0.001100341,0.00119403,0.000409767],"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":[0.001702889,0.001192975,0.4209497,0.002676044,0.0005699023,0.009490119,0.002819457,0.006346277,0.03457284,0.002458657,0.04528482,0.4719363],"study_design_scores_gemma":[0.0007084614,0.001321392,0.4415411,0.001568154,0.001395796,0.03135072,0.01284359,0.2696809,0.09158618,0.01546316,0.1320125,0.0005280141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7375858,0.003091613,0.1434406,0.003674169,0.0001845304,0.001595536,0.08679516,0.01828994,0.005342613],"genre_scores_gemma":[0.6118709,0.001206245,0.3165764,0.0007265871,0.0001087367,0.0004231702,0.06719743,0.0003703743,0.001520131],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007876159,"threshold_uncertainty_score":0.01620841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08103195734588782,"score_gpt":0.3906184988051443,"score_spread":0.3095865414592565,"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."}}