{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007508591,0.001559517,0.001905391,0.02822738,0.001140981,0.003337286,0.001533205,0.001959281,0.000679363],"category_scores_gemma":[0.02291983,0.0004179717,0.002811983,0.01078438,0.0003413433,0.00383165,0.002213553,0.001087858,0.0005648763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001092495,"about_ca_system_score_gemma":0.002068464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01470682,"about_ca_topic_score_gemma":0.01657481,"domain_scores_codex":[0.9923397,0.001555542,0.001677764,0.001836602,0.002270561,0.0003197762],"domain_scores_gemma":[0.9817784,0.009130253,0.002072326,0.002412278,0.003997095,0.0006096828],"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":[0.0007737135,0.001087893,0.1003765,0.001949357,0.001997793,0.001770211,0.001341391,0.03127659,0.02257234,0.002604455,0.008538746,0.825711],"study_design_scores_gemma":[0.0001401174,0.0008093524,0.07576405,0.0007880038,0.002541496,0.002223376,0.002437513,0.8433921,0.03280485,0.01496414,0.0238035,0.0003314761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3071423,0.01167081,0.6390427,0.005033079,0.0005393573,0.00196725,0.01876451,0.009498951,0.006340965],"genre_scores_gemma":[0.5412122,0.002367307,0.441159,0.0006024848,0.0002899582,0.0002821209,0.0133668,0.00005629857,0.0006638709],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02822738,"threshold_uncertainty_score":0.03970969,"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."}}