{"id":"W4407357998","doi":"10.2139/ssrn.5128066","title":"Optimizing Physiological State Detection: Statistical Feature Selection of Hrv and Rqa Metrics for Machine Learning Models","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Heart Rate Variability and Autonomic Control","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Recurrence quantification analysis; Computer science; Feature selection; Machine learning; Selection (genetic algorithm); Feature (linguistics); Statistical learning; Pattern recognition (psychology); State (computer science); Algorithm; Nonlinear system","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":[0.002187009,0.001004028,0.001316921,0.0006378174,0.0002552825,0.0009667074,0.0008314843,0.0008332292,0.000959165],"category_scores_gemma":[0.006954176,0.0004487489,0.0008813752,0.0007479257,0.0003144017,0.0009037885,0.000809784,0.0009535085,0.0004713291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004153255,"about_ca_system_score_gemma":0.001134267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003557972,"about_ca_topic_score_gemma":0.002968967,"domain_scores_codex":[0.9992374,0.0003023138,0.00007145599,0.0001807877,0.000131479,0.0000764727],"domain_scores_gemma":[0.9984897,0.0008871197,0.0001310731,0.0001521361,0.0002953121,0.00004463052],"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":[0.0003020377,0.000321057,0.006593343,0.0001345041,0.0002238558,0.00006277773,0.00006485476,0.4890652,0.01961155,0.003354693,0.00387936,0.4763869],"study_design_scores_gemma":[0.000006409018,0.00004178472,0.001345248,0.000005465767,0.00001366929,0.00001278924,0.00000545783,0.9956402,0.001541275,0.001236973,0.0001452768,0.000005428919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05140082,0.0003618943,0.9460731,0.0002890825,0.00002896879,0.0000493611,0.000208004,0.001053452,0.0005354126],"genre_scores_gemma":[0.7983431,0.0002039322,0.1985071,0.0001175597,0.00009507746,0.0001893142,0.0008816643,0.0002751623,0.001387137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003557972,"threshold_uncertainty_score":0.01156616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02473287218663565,"score_gpt":0.2840694355466113,"score_spread":0.2593365633599756,"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."}}