{"id":"W3217443545","doi":"10.1109/bigdata52589.2021.9672045","title":"MURAL: An Unsupervised Random Forest-Based Embedding for Electronic Health Record Data","year":2021,"lang":"en","type":"preprint","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Institutes of Health; Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Categorical variable; Random forest; Embedding; Computer science; Artificial intelligence; Random variable; Dimensionality reduction; Decision tree; Missing data; Data mining; Mathematics; Machine learning; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002815732,0.001135575,0.0009784381,0.001931558,0.000486643,0.0007532035,0.001458728,0.001201621,0.001700165],"category_scores_gemma":[0.008948884,0.0004313666,0.0013834,0.001402818,0.0005488652,0.001705433,0.001413254,0.001897914,0.001285955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006355461,"about_ca_system_score_gemma":0.0009474506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004719726,"about_ca_topic_score_gemma":0.008581569,"domain_scores_codex":[0.9984061,0.0007747713,0.00007500455,0.0003166984,0.0003099314,0.0001175728],"domain_scores_gemma":[0.996578,0.002122458,0.0002850217,0.0004365461,0.0004426319,0.0001352509],"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":[0.0006102002,0.000301635,0.007377666,0.0003677031,0.0002835077,0.000254651,0.0003475079,0.3324811,0.004997938,0.01285575,0.02449536,0.615627],"study_design_scores_gemma":[0.00002314071,0.00004989697,0.0004381682,0.00002027583,0.0000116267,0.0000728736,0.00002432768,0.9865,0.000699333,0.01026255,0.001882389,0.00001539015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01681322,0.0005288594,0.9774696,0.0003535912,0.00009747112,0.0001156723,0.001334916,0.002867199,0.0004195495],"genre_scores_gemma":[0.2636603,0.0005905203,0.7226177,0.0004002479,0.0002455639,0.0004280406,0.008886335,0.0005050154,0.002666362],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004719726,"threshold_uncertainty_score":0.01489121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4029666149370337,"score_gpt":0.4393100574242843,"score_spread":0.03634344248725058,"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."}}