{"id":"W3158786325","doi":"10.1101/2021.05.03.442488","title":"Benchmark of data processing methods and machine learning models for gut microbiome-based diagnosis of inflammatory bowel disease","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Mila - Quebec Artificial Intelligence Institute","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Machine learning; Generalizability theory; Artificial intelligence; Computer science; Microbiome; Benchmark (surveying); Support vector machine; Inflammatory bowel disease; Disease; Medicine; Bioinformatics; Biology; Pathology; 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":[0.0213671,0.001842131,0.0008915178,0.00179272,0.0008733801,0.001499563,0.001964422,0.001384293,0.001166842],"category_scores_gemma":[0.04134342,0.0005410639,0.001908004,0.001830776,0.0008772981,0.00142943,0.001818284,0.002102613,0.0009464397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001754438,"about_ca_system_score_gemma":0.002611045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01217086,"about_ca_topic_score_gemma":0.007774226,"domain_scores_codex":[0.9903228,0.004515251,0.001193714,0.001896431,0.001720394,0.0003513224],"domain_scores_gemma":[0.9766498,0.01268255,0.001265968,0.00382501,0.005174393,0.0004022692],"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":[0.004207897,0.002447988,0.1429487,0.001590563,0.002173409,0.0003921723,0.0005078439,0.4290289,0.01756089,0.002513899,0.0178066,0.3788213],"study_design_scores_gemma":[0.0002916897,0.001302036,0.04146386,0.0001874943,0.00023426,0.0001752752,0.0002592126,0.9229441,0.02397456,0.003869278,0.005208734,0.0000894606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7485086,0.004970275,0.212036,0.002359471,0.0005484591,0.0023267,0.01433595,0.01055412,0.004360388],"genre_scores_gemma":[0.7067612,0.0007389045,0.2639308,0.0005578517,0.000108113,0.001591036,0.02484264,0.0004542116,0.001015141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0213671,"threshold_uncertainty_score":0.1130014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03308706094020308,"score_gpt":0.2933946964435865,"score_spread":0.2603076355033834,"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."}}