{"id":"W4293153282","doi":"10.2139/ssrn.4173130","title":"A Novel Hybrid Machine Learning Approach for the Prediction of Lupus Nephritis Using Polygenic Risk Score and Electronic Health Record","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Systemic Lupus Erythematosus Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Lupus nephritis; Electronic health record; Health records; Machine learning; Artificial intelligence; Polygenic risk score; Medicine; Computer science; Computational biology; Internal medicine; Biology; Genotype; Genetics; Gene; Single-nucleotide polymorphism; Disease","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":[0.001757625,0.0007472332,0.001414055,0.00325683,0.0006722208,0.001626233,0.001436115,0.001379254,0.002472542],"category_scores_gemma":[0.002495374,0.0003328907,0.001164212,0.002089655,0.0002198276,0.001403717,0.0009450539,0.0009540833,0.0009686315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006391716,"about_ca_system_score_gemma":0.001400571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01148054,"about_ca_topic_score_gemma":0.01760851,"domain_scores_codex":[0.9989005,0.0003321622,0.00009117428,0.0002917582,0.0002507227,0.0001335093],"domain_scores_gemma":[0.9984999,0.0008086722,0.00009351177,0.00009145515,0.0004053839,0.0001010065],"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":[0.001063763,0.002147799,0.1005055,0.0001975115,0.001512243,0.0007134986,0.0001437329,0.1065408,0.007491001,0.003721416,0.007847874,0.7681148],"study_design_scores_gemma":[0.0000438263,0.0001120423,0.007928861,0.00001425694,0.0001276328,0.0001766077,0.000031921,0.9883375,0.0006570176,0.001857696,0.0006862874,0.00002641372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.246971,0.002917835,0.7383338,0.002138589,0.0004283492,0.000278296,0.001617195,0.002119662,0.005195336],"genre_scores_gemma":[0.787811,0.000602744,0.2027337,0.0004682715,0.0005000637,0.0001907282,0.001677581,0.00004233433,0.005973537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01148054,"threshold_uncertainty_score":0.02282745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02605396500871026,"score_gpt":0.279764508447955,"score_spread":0.2537105434392448,"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."}}