{"id":"W4225983369","doi":"10.3389/fgene.2022.784397","title":"Benchmark of Data Processing Methods and Machine Learning Models for Gut Microbiome-Based Diagnosis of Inflammatory Bowel Disease","year":2022,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Mila - Quebec Artificial Intelligence Institute","funders":"Horizon 2020; Biotechnology and Biological Sciences Research Council","keywords":"Generalizability theory; Machine learning; Artificial intelligence; Computer science; Benchmark (surveying); Microbiome; Support vector machine; Data mining; Bioinformatics; Biology; Statistics; Mathematics","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":[0.02502802,0.001635038,0.0008444622,0.001781718,0.0009771228,0.001581361,0.001810464,0.00152731,0.0007925474],"category_scores_gemma":[0.04568885,0.0005178247,0.001580914,0.002050535,0.0009904716,0.001561707,0.002069921,0.002147538,0.0007330138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001746854,"about_ca_system_score_gemma":0.002675124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01137884,"about_ca_topic_score_gemma":0.00764246,"domain_scores_codex":[0.9886858,0.005616033,0.001436252,0.001914977,0.001975854,0.0003710539],"domain_scores_gemma":[0.9738163,0.01464731,0.0013787,0.004471001,0.005243771,0.0004429777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004665726,0.002875612,0.1266426,0.001550866,0.001811816,0.0004978746,0.0006421311,0.4634546,0.0159825,0.00383107,0.01683543,0.3612097],"study_design_scores_gemma":[0.0003985431,0.001461446,0.04650487,0.0002234306,0.0002395177,0.0002432272,0.0003282604,0.911636,0.02627872,0.005440497,0.007132943,0.0001126422],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7500907,0.005431219,0.2132019,0.002571362,0.0005518763,0.002670486,0.01274677,0.00758089,0.005154872],"genre_scores_gemma":[0.6768603,0.001047431,0.2908054,0.0006343944,0.0001222288,0.00180946,0.02725095,0.0004377243,0.001032094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02502802,"threshold_uncertainty_score":0.1323624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03142683150782653,"score_gpt":0.3121835818152904,"score_spread":0.2807567503074638,"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."}}