{"id":"W4405427511","doi":"10.1145/3698587.3701368","title":"MixEHR-Nest: Identifying Subphenotypes within Electronic Health Records through Hierarchical Guided-Topic Modeling","year":2024,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Universitas Brawijaya","keywords":"Health records; Computer science; Data science; Electronic health record; Multilevel model; Machine learning; Health care; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002422494,0.0001275733,0.0002345602,0.0001286644,0.0006405814,0.0003048628,0.000241822,0.00007035672,0.0004491397],"category_scores_gemma":[0.0001642661,0.0001098683,0.000170047,0.0008690174,0.00008323896,0.0003419574,0.00005495755,0.0003113842,0.00009634154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003729006,"about_ca_system_score_gemma":0.001055769,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0207915,"about_ca_topic_score_gemma":0.01498937,"domain_scores_codex":[0.9976304,0.0005111172,0.0004355838,0.0004054515,0.0005227054,0.0004947772],"domain_scores_gemma":[0.9993008,0.0003156471,0.00005115583,0.0001320317,0.00008476112,0.0001155526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003382155,0.00002022417,0.000256674,0.00003391741,0.00006500066,0.00000412315,0.009366841,0.005332901,0.00001125913,0.9441599,0.0006115136,0.04013428],"study_design_scores_gemma":[0.00007007712,0.00002897629,0.00007920097,0.00005955527,0.00003091553,0.000003557274,0.00123568,0.2829856,0.00001309845,0.6871989,0.02810859,0.000185823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09891053,0.004762717,0.8575335,0.01586814,0.001026852,0.0001829454,0.000001288874,0.0004487857,0.0212652],"genre_scores_gemma":[0.943971,0.0004414031,0.04547565,0.0007692698,0.000719076,0.00001088926,0.00001075441,0.00001750746,0.008584429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8450605,"threshold_uncertainty_score":0.9857292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1140098613197322,"score_gpt":0.4467655029363127,"score_spread":0.3327556416165804,"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."}}