{"id":"W2951861510","doi":"10.1002/gepi.22112","title":"An analytic approach for interpretable predictive models in high‐dimensional data in the presence of interactions with exposures","year":2018,"lang":"en","type":"article","venue":"Genetic Epidemiology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University; Jewish General Hospital; Université de Sherbrooke; McGill University Health Centre","funders":"Canadian Institutes of Health Research; Ludmer Centre for Neuroinformatics and Mental Health","keywords":"Cluster analysis; Dimensionality reduction; Computer science; Feature selection; Dimension (graph theory); Variable (mathematics); Selection (genetic algorithm); Curse of dimensionality; Data mining; Binary number; Correlation; Artificial intelligence; Machine learning; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001299677,0.0001234778,0.0002696367,0.00006250452,0.00003787129,0.0000048375,0.0006202936,0.0001188458,0.000004506269],"category_scores_gemma":[0.0001915536,0.00008280945,0.00002953547,0.0001010221,0.0002764602,0.00001319914,0.0001575548,0.0001188002,4.134876e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008846563,"about_ca_system_score_gemma":0.00007526375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001927698,"about_ca_topic_score_gemma":0.0006155224,"domain_scores_codex":[0.9985152,0.000296221,0.0004705753,0.0003848441,0.00005578212,0.0002774052],"domain_scores_gemma":[0.9985866,0.0002421735,0.0001697763,0.0008891583,0.0000740038,0.00003831411],"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":[0.001900433,0.0005509501,0.06441365,0.00009348457,0.0002473325,0.000001632889,0.001642157,0.9078634,0.008019147,0.002288374,0.005608125,0.007371248],"study_design_scores_gemma":[0.0004809774,0.001104187,0.01389478,0.00002114563,0.00002404483,0.00002121596,0.0002642437,0.9789278,0.0002246793,0.004756579,0.000172463,0.0001079054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4432148,0.0003871766,0.5553522,0.0001162009,0.00007077104,0.0004345718,0.00009039376,0.000002561049,0.0003313749],"genre_scores_gemma":[0.937642,0.00003700448,0.06126711,0.0004040449,0.0001429767,0.00005266688,0.0004260955,0.000009080645,0.00001898311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4944273,"threshold_uncertainty_score":0.3376871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04435830121658021,"score_gpt":0.3168484521232434,"score_spread":0.2724901509066632,"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."}}