{"id":"W4390097263","doi":"10.1109/jbhi.2023.3346210","title":"EHR-HGCN: An Enhanced Hybrid Approach for Text Classification Using Heterogeneous Graph Convolutional Networks in Electronic Health Records","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China; Natural Science Foundation of Jilin Province","keywords":"Computer science; Sentence; Artificial intelligence; Natural language processing; Graph; Convolutional neural network; Graph database; Text graph; Biomedical text mining; Text mining; Information retrieval; Theoretical computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.003070811,0.0001163627,0.0003431218,0.0004152819,0.0001974653,0.00006093302,0.0003410331,0.00007812073,8.445744e-7],"category_scores_gemma":[0.00002341151,0.00009931172,0.00005911483,0.0004767771,0.00006370382,0.0004551186,0.00003716753,0.0003602866,5.568874e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002917607,"about_ca_system_score_gemma":0.001132256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002671214,"about_ca_topic_score_gemma":0.000008317626,"domain_scores_codex":[0.9973193,0.00008081785,0.00149741,0.0001227269,0.0003962511,0.0005835084],"domain_scores_gemma":[0.9984013,0.00007001584,0.0008659112,0.0001631135,0.000107898,0.0003916942],"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":[0.0001216648,0.0005448047,0.0002879455,0.001806901,0.00007993495,0.000006328631,0.007538893,0.1349199,0.0001048772,0.007234981,0.003440128,0.8439137],"study_design_scores_gemma":[0.0006673087,0.0006548201,0.0002946978,0.00009477846,0.000002178478,0.0001736539,0.0001565357,0.9955341,0.000009786215,0.001717672,0.0006060681,0.00008841877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07457894,0.0003602417,0.9223135,0.00199684,0.0004801214,0.000235404,0.000004249468,0.00002688857,0.000003861005],"genre_scores_gemma":[0.833819,0.001579578,0.1623978,0.00178716,0.0003696281,0.000009129472,0.00002522621,0.00000879947,0.000003704906],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8606142,"threshold_uncertainty_score":0.4049815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08133374493038933,"score_gpt":0.3412262027901213,"score_spread":0.259892457859732,"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."}}