{"id":"W2964990093","doi":"10.24963/ijcai.2019/641","title":"Medical Concept Embedding with Multiple Ontological Representations","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Categorization; Computer science; Embedding; Representation (politics); Ontology; Medical classification; Artificial intelligence; Medical diagnosis; Text categorization; Mechanism (biology); Data science; Information retrieval; Natural language processing; Machine learning; Medicine; Epistemology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002145926,0.00008212151,0.0001297902,0.00003860498,0.00008044468,0.00005858449,0.0006435776,0.00007413156,0.00130249],"category_scores_gemma":[0.0003781966,0.00005468629,0.0000268216,0.0002041424,0.00004504912,0.0001983247,0.0002012978,0.0002875158,0.0002591679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002259011,"about_ca_system_score_gemma":0.0001075145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006384123,"about_ca_topic_score_gemma":0.0001566797,"domain_scores_codex":[0.9985964,0.0001296529,0.0001614409,0.0003787548,0.0004994213,0.0002343735],"domain_scores_gemma":[0.9987833,0.0004358602,0.00004809833,0.0004980401,0.00006389165,0.000170844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001037635,0.0000557622,0.8159315,0.00001852052,0.00001422984,0.00007714164,0.001462209,0.00302492,0.00002590277,0.1603566,0.0009954188,0.01802737],"study_design_scores_gemma":[0.0006294079,0.000200974,0.1152894,0.00002915364,0.000001343961,0.0001074687,0.0001667194,0.8802534,0.00009307632,0.0002933553,0.002773602,0.0001620181],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1861191,0.00003808468,0.7727091,0.01215478,0.0003380005,0.0003159201,6.014013e-7,0.0005925008,0.02773187],"genre_scores_gemma":[0.8933774,9.929853e-7,0.1040464,0.001072437,0.00003809291,0.00001046947,0.000002572005,0.000004543166,0.001447112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8772285,"threshold_uncertainty_score":0.9996105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01784325121460368,"score_gpt":0.3355493694415357,"score_spread":0.3177061182269321,"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."}}