{"id":"W2960917904","doi":"10.1016/j.ymeth.2019.07.009","title":"A disease inference method based on symptom extraction and bidirectional Long Short Term Memory networks","year":2019,"lang":"en","type":"article","venue":"Methods","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Inference; Representation (politics); Word2vec; Disease; Computer science; Artificial intelligence; Term (time); Machine learning; Natural language processing; Data mining; Medicine; Pathology","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":[0.002529258,0.00018468,0.0002160913,0.0001846947,0.0001449622,0.0001343354,0.0003469212,0.00009990726,0.00007311928],"category_scores_gemma":[0.0004243094,0.0001715817,0.00006707253,0.0003507102,0.00002548871,0.0002224234,0.0001389379,0.0005061643,0.0000117817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007778284,"about_ca_system_score_gemma":0.0001261244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000622131,"about_ca_topic_score_gemma":0.000005551702,"domain_scores_codex":[0.9966816,0.001857741,0.0002292283,0.0006421817,0.0003053389,0.0002839611],"domain_scores_gemma":[0.9964275,0.002493726,0.000085798,0.000672142,0.00007650586,0.0002443108],"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":[0.00003271645,0.00003713094,0.2197451,0.0000634123,0.000008090037,0.00001104627,0.00006832259,0.06528515,0.0001743342,0.001131281,0.00001664401,0.7134268],"study_design_scores_gemma":[0.00008989263,0.00005362077,0.3846164,0.00004249363,0.000005953879,0.000006174925,0.000001701595,0.6144384,0.00009856302,0.0002213688,0.0003050213,0.0001203577],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02220526,0.000163892,0.9741901,0.0006655072,0.001125232,0.0002776835,0.000001128271,0.0002346871,0.001136508],"genre_scores_gemma":[0.3228658,0.000008877578,0.6760574,0.0005682399,0.0001297055,0.00003600274,0.000004744427,0.00001486262,0.0003143976],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7133064,"threshold_uncertainty_score":0.6996898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02926043206924572,"score_gpt":0.424331390032065,"score_spread":0.3950709579628193,"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."}}