{"id":"W2793303269","doi":"10.1109/tcbb.2018.2817488","title":"Automated ICD-9 Coding via A Deep Learning Approach","year":2018,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":145,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Central South University; National Natural Science Foundation of China","keywords":"Deep learning; Artificial intelligence; Computer science; Convolutional neural network; ENCODE; Support vector machine; Machine learning; Coding (social sciences); Artificial neural network; Pattern recognition (psychology); Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001675343,0.0009393159,0.0008108288,0.004334545,0.0006882466,0.001287965,0.001519147,0.00107722,0.00368556],"category_scores_gemma":[0.007355249,0.0003445264,0.0006741224,0.002717679,0.0004484485,0.001677084,0.001754175,0.002423509,0.002298158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001700718,"about_ca_system_score_gemma":0.003184427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01064511,"about_ca_topic_score_gemma":0.01523136,"domain_scores_codex":[0.9982992,0.0003851005,0.0002056496,0.0004090444,0.0005018258,0.0001991443],"domain_scores_gemma":[0.9966587,0.001213234,0.0003895344,0.0005362963,0.001066331,0.0001358967],"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":[0.0003097386,0.0004499015,0.008259813,0.0001809815,0.00005760582,0.0001829686,0.0002027645,0.04357862,0.006037078,0.006967091,0.02963373,0.9041398],"study_design_scores_gemma":[0.00005488431,0.00007376973,0.002934495,0.00006559426,0.00003026461,0.0001624127,0.0001754031,0.9523509,0.008083574,0.02719349,0.008836229,0.00003904978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07941265,0.0008740274,0.8895636,0.00275515,0.0003758322,0.0005734385,0.006519292,0.01260159,0.007324457],"genre_scores_gemma":[0.4174542,0.0005574201,0.5559361,0.0008290982,0.0002150731,0.0003357993,0.01732018,0.0002504857,0.0071017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01064511,"threshold_uncertainty_score":0.02116627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01649582494325603,"score_gpt":0.2844612318899851,"score_spread":0.267965406946729,"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."}}