{"id":"W2904119616","doi":"10.1609/aaai.v33i01.33011246","title":"Learning Phenotypes and Dynamic Patient Representations via RNN Regularized Collective Non-Negative Tensor Factorization","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Regularization (linguistics); Computer science; Tensor (intrinsic definition); Temporal database; Artificial intelligence; Machine learning; Pattern recognition (psychology); Data mining; Mathematics","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":[0.001970524,0.001262982,0.0007529728,0.0006483844,0.0002898133,0.0005934205,0.001051513,0.0008974005,0.0008502132],"category_scores_gemma":[0.006130135,0.0004877844,0.001194563,0.0008048161,0.0007295836,0.001113709,0.0007277067,0.001814036,0.0003556334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009464798,"about_ca_system_score_gemma":0.001216894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01289425,"about_ca_topic_score_gemma":0.01679674,"domain_scores_codex":[0.9992348,0.0003183943,0.00003424298,0.0002463286,0.00008685641,0.00007945212],"domain_scores_gemma":[0.9981849,0.0009457362,0.0003142697,0.0002109575,0.0002474374,0.00009677386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002760412,0.0001469027,0.009491326,0.00011009,0.0001588333,0.0003320279,0.0002981386,0.8189929,0.004013082,0.01312678,0.006666173,0.1463876],"study_design_scores_gemma":[0.000006921081,0.00001509729,0.0004520432,0.000005467721,0.000008549867,0.00002719255,0.000009013518,0.9924914,0.000170313,0.006531214,0.0002763079,0.000006332174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05680667,0.0004356993,0.9397417,0.0008578083,0.00009574249,0.00006685394,0.0006274866,0.00062795,0.0007401226],"genre_scores_gemma":[0.7759097,0.000511886,0.2172621,0.0004024022,0.0001996552,0.0002449649,0.002273464,0.0001277632,0.003067956],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01289425,"threshold_uncertainty_score":0.0256384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02497882665520336,"score_gpt":0.2892401545010073,"score_spread":0.264261327845804,"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."}}