{"id":"W3081455901","doi":"10.1101/2020.08.20.259226","title":"CLEP: A Hybrid Data- and Knowledge-Driven Framework for Generating Patient Representations","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Bundesministerium für Bildung und Forschung; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Computer science; Knowledge graph; Cluster analysis; Artificial intelligence; Machine learning; Embedding; Python (programming language); Variety (cybernetics); Graph; Documentation; Theoretical computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005888212,0.0005331572,0.0006032998,0.0002068466,0.0004995466,0.000791347,0.00241364,0.0003348854,0.000006781633],"category_scores_gemma":[0.002381031,0.0006057246,0.0001073289,0.0004905579,0.00008641125,0.0003663808,0.005579113,0.001369282,0.00002655474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001519973,"about_ca_system_score_gemma":0.001005888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007343277,"about_ca_topic_score_gemma":0.000004602305,"domain_scores_codex":[0.9954913,0.0003892919,0.0007631288,0.002362995,0.0003866226,0.0006066078],"domain_scores_gemma":[0.9939734,0.0006031992,0.0006431406,0.003707855,0.0005923208,0.0004800516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002901018,0.002339678,0.1624109,0.02760157,0.003268493,0.001178801,0.006490622,0.03521984,0.1787405,0.5232654,0.0541913,0.005002805],"study_design_scores_gemma":[0.0003403592,0.0001457225,0.008507483,0.0006424127,0.00007759356,8.928473e-8,0.000007557264,0.9713439,0.005035648,0.0001499667,0.01274654,0.001002698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1108746,0.001870546,0.8778004,0.003769738,0.002209537,0.001770823,0.000717861,0.0009800188,0.000006428342],"genre_scores_gemma":[0.5365444,0.00006563191,0.4619589,0.0004331555,0.0006245039,0.0002962128,0.000002438901,0.0000739503,8.36446e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9361241,"threshold_uncertainty_score":0.9996394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04579274490232325,"score_gpt":0.3097760788648998,"score_spread":0.2639833339625765,"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."}}