{"id":"W3049704679","doi":"10.1007/s11517-020-02206-9","title":"A comparison of regularized logistic regression and random forest machine learning models for daytime diagnosis of obstructive sleep apnea","year":2020,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Random forest; Logistic regression; Daytime; Feature selection; Obstructive sleep apnea; Artificial intelligence; Machine learning; Polysomnography; Sleep apnea; Computer science; Regression; Regression analysis; Stepwise regression; Apnea; Statistics; Pattern recognition (psychology); Medicine; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000645965,0.0002596617,0.001200171,0.0001005114,0.00007511667,0.000008949727,0.0002092836,0.000289806,0.00005811532],"category_scores_gemma":[0.009840262,0.0001813543,0.0001824981,0.0002979098,0.000361022,0.00003673407,0.0003414539,0.0007139613,0.000001108883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003729741,"about_ca_system_score_gemma":0.00002146148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001604474,"about_ca_topic_score_gemma":2.820224e-7,"domain_scores_codex":[0.997714,0.0001271856,0.000750498,0.0004686536,0.0005307447,0.0004088831],"domain_scores_gemma":[0.9965628,0.002435875,0.0002310875,0.0001482102,0.0001793838,0.0004426182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004479003,0.0005515428,0.6909181,0.002532029,0.0006409299,0.00007904295,0.001573391,0.1359514,0.0310974,0.002448922,0.0000226766,0.1297055],"study_design_scores_gemma":[0.004564526,0.001055109,0.01670111,0.0002919584,0.00007361042,0.00001884141,0.00007924687,0.9743326,0.002553086,0.0001219466,0.0000493925,0.0001585883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5946787,0.0007803413,0.4034628,0.0004130019,0.00005676256,0.0004960235,0.0000102936,0.00007307695,0.00002900152],"genre_scores_gemma":[0.9783441,0.00002401632,0.02133668,0.00004674114,0.0001378566,0.00002594148,0.00005612974,0.00002684531,0.000001705824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8383812,"threshold_uncertainty_score":0.9985003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06777806899720137,"score_gpt":0.3276183284087276,"score_spread":0.2598402594115262,"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."}}