{"id":"W4206531341","doi":"10.1101/2022.01.07.475444","title":"A graph-embedded topic model enables characterization of diverse pain phenotypes among UK Biobank individuals","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Virginia Agricultural Experiment Station, Virginia Polytechnic Institute and State University","keywords":"Interpretability; Biobank; Inference; Autoencoder; Computer science; Graph; Chronic pain; Machine learning; Missing data; Medicine; Artificial intelligence; Data mining; Data science; Deep learning; Bioinformatics; Theoretical computer science; Physical therapy","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":[0.00132625,0.00039274,0.0004346587,0.001278756,0.0002621651,0.0007454754,0.0006233791,0.0008683024,0.001854512],"category_scores_gemma":[0.006737352,0.0003076973,0.0007829185,0.001160244,0.0003598745,0.0008040522,0.0007726373,0.0009160636,0.0006200735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000621681,"about_ca_system_score_gemma":0.0005177445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0154743,"about_ca_topic_score_gemma":0.0176619,"domain_scores_codex":[0.9993746,0.0002639304,0.00003463865,0.0002172117,0.00004889102,0.00006077615],"domain_scores_gemma":[0.9965071,0.002655029,0.0002555628,0.0003159164,0.000203004,0.00006337959],"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":[0.00109416,0.0002621391,0.165605,0.0004498687,0.0006048102,0.0007397689,0.001555644,0.5440177,0.0104081,0.03370777,0.02657506,0.21498],"study_design_scores_gemma":[0.00002890493,0.00003787481,0.02240266,0.00003466399,0.00005950832,0.0001431382,0.00009961607,0.9569321,0.0006165329,0.01643616,0.00318533,0.00002347465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4810486,0.001430723,0.5014844,0.0016309,0.00009724744,0.0001485694,0.01002953,0.001292778,0.002837169],"genre_scores_gemma":[0.937147,0.0004017109,0.04938261,0.0002107294,0.00008286097,0.0001425306,0.01031558,0.00009199064,0.002225043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0154743,"threshold_uncertainty_score":0.03076845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009215586274432822,"score_gpt":0.1992144837123172,"score_spread":0.1899988974378844,"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."}}