{"id":"W2552714763","doi":"10.2196/medinform.5977","title":"A Predictive Model for Medical Events Based on Contextual Embedding of Temporal Sequences","year":2016,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; National Science Foundation","keywords":"Medical diagnosis; Computer science; Representation (politics); Embedding; Artificial intelligence; Machine learning; Receiver operating characteristic; Event (particle physics); Semantics (computer science); Similarity (geometry); Data mining; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001567202,0.0001769899,0.0003352324,0.0001511074,0.00009028506,0.00001844043,0.001296871,0.0002955615,0.0001151361],"category_scores_gemma":[0.002640887,0.0001080506,0.0001093298,0.0001868195,0.0001966557,0.0004233075,0.0002072577,0.0003479193,0.0000161481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009111772,"about_ca_system_score_gemma":0.001276287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001234856,"about_ca_topic_score_gemma":0.0000074164,"domain_scores_codex":[0.9961056,0.0001042077,0.0009549122,0.0001787498,0.002256858,0.0003996617],"domain_scores_gemma":[0.997117,0.001315902,0.0003802949,0.0004339185,0.0002083524,0.0005444745],"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":[0.0008401721,0.001216086,0.03107831,0.003940387,0.0002039144,0.00005479389,0.04474156,0.01877243,0.0000194833,0.1300426,0.01907689,0.7500134],"study_design_scores_gemma":[0.001328258,0.0005354783,0.0001556427,0.0007974006,0.00000304593,0.000007847089,0.000115827,0.9949967,0.00002767947,0.001456809,0.0004448337,0.0001304776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01855986,0.000004801574,0.9739272,0.005884438,0.0002359252,0.0005256651,0.0000338216,0.000147115,0.0006811713],"genre_scores_gemma":[0.9519172,0.000005007506,0.04514999,0.002608779,0.00008615198,0.0001487425,0.000008936441,0.00001016619,0.000065025],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9762242,"threshold_uncertainty_score":0.4406174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02872785543354216,"score_gpt":0.3590050089687136,"score_spread":0.3302771535351715,"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."}}