{"id":"W4387055551","doi":"10.1145/3625224","title":"Adaptive Integration of Categorical and Multi-relational Ontologies with EHR Data for Medical Concept Embedding","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Embedding; Categorical variable; Ontology; Open Biomedical Ontologies; Biomedicine; Analytics; Categorization; Data science; Data integration; Information retrieval; Artificial intelligence; Machine learning; Data mining; Domain knowledge; Upper ontology; Bioinformatics; Ontology alignment","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":[0.0003210043,0.0001105406,0.0002159006,0.000340014,0.0001594662,0.00002122967,0.0005640805,0.0002201792,0.000003711759],"category_scores_gemma":[0.0003418238,0.00008414875,0.00001478023,0.00045961,0.000196514,0.0001385567,0.00006017497,0.0002997738,0.000002213501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002750784,"about_ca_system_score_gemma":0.0000747088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003986103,"about_ca_topic_score_gemma":0.0002129691,"domain_scores_codex":[0.9988895,0.00005625096,0.0002951181,0.0003999342,0.0001939166,0.0001652533],"domain_scores_gemma":[0.9985557,0.000576229,0.0001033877,0.0005814531,0.0001312029,0.00005198962],"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":[0.00006586565,0.0001198247,0.001685321,0.0001816929,0.0001638534,0.00001685832,0.001543665,0.008110387,0.00005250671,0.3449104,0.0001310955,0.6430185],"study_design_scores_gemma":[0.0003001053,0.0005618996,0.0003804539,0.0001264145,0.00001305967,0.0001050381,0.001768697,0.9934342,0.0002514471,0.002355074,0.0005916498,0.0001119474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004983102,0.0003441723,0.9897537,0.00401932,0.0002270447,0.0003659307,0.00003151597,0.000269263,0.000005907087],"genre_scores_gemma":[0.9514413,0.0001195071,0.04821936,0.00001382708,0.0000125874,0.00009905739,0.0000214787,0.000007535533,0.00006529043],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9853238,"threshold_uncertainty_score":0.3431486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1010849558219556,"score_gpt":0.3623625424228274,"score_spread":0.2612775866008719,"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."}}