{"id":"W3163233738","doi":"10.1093/bioinformatics/btab340","title":"CLEP: a hybrid data- and knowledge-driven framework for generating patient representations","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":16,"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; Python (programming language); Embedding; Cluster analysis; Documentation; Machine learning; Domain knowledge; Artificial intelligence; Graph; Knowledge graph; Data mining; Theoretical computer science; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0002012141,0.0001021936,0.000135593,0.00005099907,0.0002915298,0.0002711984,0.0004990951,0.00004683853,0.000005894432],"category_scores_gemma":[0.001149865,0.00009992047,0.00002795819,0.0002031353,0.00002401218,0.0005062033,0.0009658535,0.0001725918,0.00001766572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000241111,"about_ca_system_score_gemma":0.0002203624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008768583,"about_ca_topic_score_gemma":0.00001361056,"domain_scores_codex":[0.9989227,0.00006086531,0.0003983585,0.0002416757,0.000154546,0.0002218337],"domain_scores_gemma":[0.9979859,0.000471105,0.0001611995,0.001074286,0.0002002744,0.0001072499],"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":[0.000004310398,0.0000966557,0.005908679,0.0008858087,0.00005659648,0.00001595431,0.02405589,0.003100645,0.00003316629,0.1299185,0.01679115,0.8191327],"study_design_scores_gemma":[0.00011682,0.00004069906,0.0002808289,0.00005694409,0.000006149845,0.00004230662,0.0003871492,0.9811109,0.0001422343,0.001679347,0.01601736,0.0001192196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009752173,0.0003204161,0.9872522,0.001197053,0.000436817,0.0002549143,0.0000686959,0.0001171054,0.0006006588],"genre_scores_gemma":[0.03744296,0.00003031882,0.9616053,0.0005952006,0.0001084075,0.00002553552,0.0001366348,0.000008575605,0.00004705095],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9780103,"threshold_uncertainty_score":0.4074638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05388756787387535,"score_gpt":0.3534373595230252,"score_spread":0.2995497916491499,"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."}}