{"id":"W2912907847","doi":"10.1016/j.jbi.2019.103114","title":"Automatic ICD code assignment of Chinese clinical notes based on multilayer attention BiRNN","year":2019,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Code (set theory); Feature engineering; Word embedding; Feature (linguistics); Artificial intelligence; Natural language processing; Block (permutation group theory); Representation (politics); Artificial neural network; Semantics (computer science); Word (group theory); Recurrent neural network; Hamming code; Embedding; Deep learning; Block code; Linguistics; Programming language; Algorithm; Decoding methods","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":[0.001356214,0.00015857,0.0004457624,0.000152399,0.00002600062,0.00001537315,0.000312386,0.0003453184,0.00009630266],"category_scores_gemma":[0.001298691,0.00009948447,0.0003017967,0.0001488579,0.0002842781,0.00000896361,0.00007507994,0.0002921266,0.00003170054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000217658,"about_ca_system_score_gemma":0.0001877726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001099495,"about_ca_topic_score_gemma":5.584778e-7,"domain_scores_codex":[0.9974176,0.00009350364,0.001537466,0.00008964774,0.0006569014,0.0002048546],"domain_scores_gemma":[0.9981048,0.0002796965,0.0009704743,0.0002771926,0.0001553629,0.0002125393],"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":[0.001341288,0.00444408,0.2393814,0.001603278,0.001013853,0.00003833488,0.0007431821,0.0009047364,0.09642301,0.00003587865,0.02143075,0.6326402],"study_design_scores_gemma":[0.0212415,0.03152957,0.2968152,0.002098518,0.0003189754,0.0002122521,0.001443138,0.5053542,0.01422598,0.0002948923,0.1252165,0.001249202],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.974468,0.00006952025,0.02376815,0.0005938712,0.0007922252,0.0001124141,0.00001888284,0.000009527417,0.0001674103],"genre_scores_gemma":[0.9793149,0.00006218658,0.01966909,0.0006629623,0.0002129745,0.000001397494,0.00002875552,0.00001014434,0.00003754293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.631391,"threshold_uncertainty_score":0.4056859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02064373706993933,"score_gpt":0.3388898037443068,"score_spread":0.3182460666743675,"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."}}