{"id":"W2737370169","doi":"10.1038/gim.2017.108","title":"Knowledge base and mini-expert platform for the diagnosis of inborn errors of metabolism","year":2017,"lang":"en","type":"article","venue":"Genetics in Medicine","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":109,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Genome British Columbia; BC Children's Hospital","funders":"Genome British Columbia; FP7 Health; Michael Smith Health Research BC; BC Children's Hospital; Universiteit van Amsterdam; Children's Hospital Foundation; Canadian Institutes of Health Research; Genome Canada","keywords":"Medical diagnosis; Expert system; Knowledge base; Computer science; Medicine; Genetic diagnosis; Inborn error of metabolism; Bioinformatics; Computational biology; Artificial intelligence; Pathology; Genetics; Gene; Biology; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002657564,0.00009520108,0.0002040893,0.00003576436,0.00007284906,0.000004167526,0.00027648,0.00007105523,0.000008723943],"category_scores_gemma":[0.0004014107,0.00006221685,0.00004656001,0.00002325158,0.0003681192,0.000001308272,0.0001404819,0.00003282598,1.31229e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002635014,"about_ca_system_score_gemma":0.00004885578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007368385,"about_ca_topic_score_gemma":0.0002140488,"domain_scores_codex":[0.9994031,0.00001077516,0.0002283417,0.0001623844,0.00006615355,0.0001292375],"domain_scores_gemma":[0.999174,0.0000669169,0.000143823,0.0004718621,0.00009062105,0.00005279611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008968221,0.0008181554,0.2335454,0.0007922899,0.0006153143,0.00001120785,0.005220158,0.0001431493,0.5195796,0.001474847,0.0238695,0.2130336],"study_design_scores_gemma":[0.005179594,0.001023618,0.3683316,0.0002112077,0.0002806273,0.000008616759,0.001814571,0.0008510844,0.4517828,0.001139958,0.1690349,0.0003413502],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.948118,0.05055205,0.0001009211,0.0004648803,0.0002477508,0.0002380568,0.00005267227,8.215151e-7,0.0002248163],"genre_scores_gemma":[0.9851894,0.01368357,0.0006537905,0.0001000389,0.0002302203,0.00005053467,0.00002162949,0.00001158534,0.00005924387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2126923,"threshold_uncertainty_score":0.253713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04011651731844972,"score_gpt":0.3319995670368288,"score_spread":0.291883049718379,"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."}}