{"id":"W1990652932","doi":"10.1109/bibm.2014.6999219","title":"Deep learning for healthcare decision making with EMRs","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":181,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Machine learning; Representation (politics); Feature learning; Feature (linguistics); Deep belief network; Convolutional neural network; Health care; Feature engineering; Data science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007082389,0.0001497008,0.000188922,0.0001191414,0.0004075373,0.000151599,0.0006434696,0.00007400467,0.00001729068],"category_scores_gemma":[0.0004495612,0.0001146922,0.00004752789,0.0002961095,0.00001848507,0.0002257585,0.0001607455,0.0003213616,0.00003167547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006076966,"about_ca_system_score_gemma":0.00005618936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001116408,"about_ca_topic_score_gemma":0.000328538,"domain_scores_codex":[0.9983208,0.0001697627,0.0002346603,0.0005100744,0.0003245596,0.0004401645],"domain_scores_gemma":[0.9981112,0.0009262405,0.0001252042,0.0005131559,0.0001939031,0.0001303192],"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":[0.00002639702,0.000007873488,0.03528497,0.00009049845,0.000003883612,0.000001831769,0.0005531969,0.0142726,0.000002525809,0.08665549,0.00009444026,0.8630063],"study_design_scores_gemma":[0.0003321411,0.0006306793,0.0136776,0.0001280862,0.000002043926,0.00002482341,0.00005109296,0.9628648,0.00001217712,0.005564242,0.01651461,0.0001977428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006943924,0.0000754802,0.9863008,0.004052449,0.0002050079,0.0002819057,9.304861e-8,0.0004549541,0.001685386],"genre_scores_gemma":[0.6060601,0.000001821099,0.3927113,0.0009752676,0.0000735572,0.00002438092,0.000001206297,0.00001478168,0.0001375924],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9485921,"threshold_uncertainty_score":0.4677014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01691262218145499,"score_gpt":0.3207586463739029,"score_spread":0.3038460241924479,"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."}}