{"id":"W4390605262","doi":"10.1186/s13040-023-00352-y","title":"Machine learning approaches to identify systemic lupus erythematosus in anti-nuclear antibody-positive patients using genomic data and electronic health records","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Systemic Lupus Erythematosus Research","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Academia Sinica; Taichung Veterans General Hospital; National Science and Technology Council","keywords":"Logistic regression; Single-nucleotide polymorphism; Medicine; Random forest; Titer; Gradient boosting; Artificial intelligence; Medical record; Machine learning; Systemic lupus erythematosus; Internal medicine; Cohort; Support vector machine; Oncology; Immunology; Antibody; Computer science; Disease; Biology; Genetics; Genotype","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002258288,0.0003620259,0.0008233445,0.0008497837,0.0002145279,0.0002851315,0.0005343058,0.0001475136,0.00002094755],"category_scores_gemma":[0.0003283024,0.0003353977,0.00005450282,0.0008442577,0.00007641534,0.0004504002,0.001290458,0.0006598197,0.00007698884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008521454,"about_ca_system_score_gemma":0.0005314467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007665101,"about_ca_topic_score_gemma":0.00007932384,"domain_scores_codex":[0.9959561,0.0003627137,0.0008181758,0.00130882,0.0005394103,0.001014754],"domain_scores_gemma":[0.998225,0.0002147206,0.0001694045,0.00102202,0.00004895051,0.0003199463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002221946,0.0001259353,0.9690961,0.004561451,0.0002636971,0.0002267977,0.007720669,0.00002217139,0.008346267,0.0001593837,0.0004435295,0.008811775],"study_design_scores_gemma":[0.0114499,0.003064541,0.05727405,0.06219552,0.0005981222,0.1154272,0.034626,0.696498,0.0002800564,0.00004052632,0.01582676,0.002719244],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819611,0.01484204,0.0005322692,0.0002718339,0.0004244143,0.00134687,0.0003184515,0.0001531227,0.000149949],"genre_scores_gemma":[0.9951003,0.001042087,0.001859787,0.00007213729,0.0001626547,0.0000130523,0.001428167,0.0001401748,0.0001815955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9118221,"threshold_uncertainty_score":0.9999098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1125995094971304,"score_gpt":0.3603028582297049,"score_spread":0.2477033487325745,"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."}}