{"id":"W2020445160","doi":"10.1155/2013/303982","title":"A Machine-Learned Predictor of Colonic Polyps Based on Urinary Metabolomics","year":2013,"lang":"en","type":"article","venue":"BioMed Research International","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Colonoscopy; Colorectal cancer; Medicine; Urine; Classifier (UML); Adenomatous polyps; Artificial intelligence; Bowel preparation; Internal medicine; Gold standard (test); Gastroenterology; Computer science; Machine learning; Cancer","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":[0.001377349,0.0007326259,0.0007754959,0.001792978,0.0003410875,0.0008148188,0.0005544632,0.0009439366,0.001282977],"category_scores_gemma":[0.005579042,0.0001726109,0.0004449202,0.0005543021,0.0001704759,0.0005712408,0.0003786836,0.0008082334,0.0008381439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003718687,"about_ca_system_score_gemma":0.0006141262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003416733,"about_ca_topic_score_gemma":0.004272261,"domain_scores_codex":[0.999341,0.0001732277,0.0000584246,0.0002015615,0.0001436388,0.00008220337],"domain_scores_gemma":[0.9964478,0.00228984,0.0003253079,0.0001408331,0.0006535103,0.0001426042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001539152,0.001381773,0.3631611,0.0001589585,0.0004967877,0.0005795268,0.00006952726,0.1189833,0.01431216,0.0004180652,0.008216632,0.490683],"study_design_scores_gemma":[0.0000461736,0.0003131939,0.03158819,0.00001928449,0.00006680823,0.0002417785,0.00002046742,0.9609448,0.005407799,0.0005575256,0.0007613999,0.00003252903],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7653543,0.00175301,0.2208861,0.001151156,0.0003060643,0.0002171919,0.003348343,0.004465102,0.002518684],"genre_scores_gemma":[0.9400118,0.0001849285,0.05621056,0.0002022598,0.0001541909,0.00008860268,0.002070725,0.00003720888,0.001039672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003416733,"threshold_uncertainty_score":0.007284164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03817795438439802,"score_gpt":0.3451175406894116,"score_spread":0.3069395863050136,"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."}}