{"id":"W3047602034","doi":"10.1038/s41598-020-70583-0","title":"Detecting ulcerative colitis from colon samples using efficient feature selection and machine learning","year":2020,"lang":"en","type":"preprint","venue":"Scientific Reports","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ulcerative colitis; Feature selection; Support vector machine; Artificial intelligence; Classifier (UML); Inflammatory bowel disease; Machine learning; Colitis; Feature (linguistics); Computer science; Pattern recognition (psychology); Medicine; Disease; Internal medicine","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":[0.001852121,0.001045983,0.001353133,0.00209858,0.0002874767,0.0008924557,0.0004693141,0.000769679,0.0005721342],"category_scores_gemma":[0.003896656,0.0002721826,0.001225506,0.001301563,0.0002146162,0.0005401514,0.0005239689,0.0005876141,0.0004970604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003388699,"about_ca_system_score_gemma":0.0005779155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002394681,"about_ca_topic_score_gemma":0.002191148,"domain_scores_codex":[0.999054,0.0003020992,0.00008843094,0.0002769005,0.0001852665,0.00009318069],"domain_scores_gemma":[0.9985238,0.0008830401,0.0001378045,0.0001721097,0.0002398548,0.00004342966],"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":[0.001244991,0.0006795279,0.0496594,0.000262609,0.0004981851,0.0007890484,0.0001130389,0.1694338,0.08595056,0.0006313837,0.004168797,0.6865687],"study_design_scores_gemma":[0.00004919197,0.000186687,0.01362908,0.00001044761,0.00006412479,0.0002735363,0.00002329504,0.9706973,0.01319123,0.001100436,0.0007529628,0.00002173272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3851746,0.001002951,0.6062232,0.0002890028,0.00008635072,0.0002282233,0.001577829,0.004826617,0.0005911434],"genre_scores_gemma":[0.7549039,0.0002595772,0.2393899,0.0000901735,0.00006373115,0.0002448208,0.00421377,0.00009801486,0.0007361934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002394681,"threshold_uncertainty_score":0.00979507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0267656272165912,"score_gpt":0.286506875205339,"score_spread":0.2597412479887478,"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."}}