{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003826735,0.001081057,0.0009754443,0.003417075,0.0006424225,0.001188133,0.00163831,0.00115693,0.002100173],"category_scores_gemma":[0.01012443,0.0005098571,0.002536589,0.002126542,0.0005446572,0.00157334,0.002056408,0.001489062,0.001291771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006939033,"about_ca_system_score_gemma":0.001491664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007850855,"about_ca_topic_score_gemma":0.02386512,"domain_scores_codex":[0.9977939,0.001069421,0.0001455988,0.0006505771,0.0002191589,0.0001213029],"domain_scores_gemma":[0.9928499,0.005648438,0.0004253876,0.0005891488,0.000320708,0.000166322],"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":[0.001601104,0.0008231418,0.1497523,0.001894119,0.002262094,0.001203315,0.004407412,0.142936,0.01433332,0.02736261,0.07558143,0.5778432],"study_design_scores_gemma":[0.0002134508,0.0001760951,0.01462291,0.000134077,0.0003549814,0.0004479057,0.0004216846,0.9139627,0.003129995,0.05088013,0.01557943,0.00007677832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09861577,0.002505101,0.8683847,0.002002295,0.0001232196,0.000573262,0.01815637,0.007984678,0.001654667],"genre_scores_gemma":[0.4961924,0.001137668,0.4410724,0.001249469,0.0004160613,0.001493188,0.05333026,0.000800271,0.004308309],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007850855,"threshold_uncertainty_score":0.02023798,"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."}}