{"id":"W2891377710","doi":"10.2196/11301","title":"Utilization of Electronic Medical Records and Biomedical Literature to Support the Diagnosis of Rare Diseases Using Data Fusion and Collaborative Filtering Approaches","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; U.S. National Library of Medicine; National Institute of General Medical Sciences","keywords":"Leverage (statistics); Computer science; Medical record; Electronic medical record; Medical literature; Disease; MEDLINE; Rare disease; Medical diagnosis; Medicine; Data science; Information retrieval; Data mining; Artificial intelligence; Pathology; Surgery","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":[0.001001604,0.0001316605,0.0002614439,0.0001109071,0.0001301993,0.00006775082,0.000982983,0.0001857663,0.00006631253],"category_scores_gemma":[0.001842138,0.00008532045,0.00001648371,0.0008698414,0.0004546591,0.0004681346,0.00154299,0.0003336515,8.42494e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002376172,"about_ca_system_score_gemma":0.0006467081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001958149,"about_ca_topic_score_gemma":0.00002310536,"domain_scores_codex":[0.9976442,0.0001633506,0.0006273892,0.0001899756,0.0011174,0.0002576699],"domain_scores_gemma":[0.9981898,0.0004124627,0.0002432821,0.000581259,0.0001792795,0.0003939205],"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":[0.0000712041,0.0002060909,0.02726571,0.002249986,0.00006220798,0.00001283571,0.06031632,0.00000672901,0.000006682814,0.004935184,0.006484671,0.8983824],"study_design_scores_gemma":[0.0004159497,0.0008535704,0.004028536,0.001016879,0.00001792929,0.00007744794,0.001297744,0.9812627,0.00008228066,0.000199838,0.01059286,0.00015422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8730553,0.000824945,0.1193488,0.005377697,0.0002718752,0.000771793,0.0001934708,0.00006799457,0.00008809174],"genre_scores_gemma":[0.9807264,0.0004954091,0.01753084,0.0008402143,0.0001781601,0.00003126759,0.0001842438,0.000009304519,0.000004225288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.981256,"threshold_uncertainty_score":0.3479267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06820863746338202,"score_gpt":0.365959971037203,"score_spread":0.297751333573821,"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."}}