{"id":"W4311964438","doi":"10.3389/fdgth.2022.1058826","title":"Using apple watch ECG data for heart rate variability monitoring and stress prediction: A pilot study","year":2022,"lang":"en","type":"article","venue":"Frontiers in Digital Health","topic":"Heart Rate Variability and Autonomic Control","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Institute for Aging; University Health Network; Public Health Ontario; University of Toronto; University of Waterloo","funders":"","keywords":"Support vector machine; Stress (linguistics); Wearable computer; Data collection; Smartwatch; Mental health; Psychological intervention; Wearable technology; Predictive modelling; Computer science; Machine learning; Artificial intelligence; Medicine; Statistics; Embedded system; Nursing","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002686132,0.0001528379,0.000521534,0.00008239038,0.000340826,0.00006969306,0.0001574755,0.00002585017,0.000008768566],"category_scores_gemma":[0.0002447166,0.000160191,0.00002805045,0.0002211816,0.0000535191,0.0003709921,0.0003265035,0.0003199769,3.20346e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006354445,"about_ca_system_score_gemma":0.0006829713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003463631,"about_ca_topic_score_gemma":0.000009388466,"domain_scores_codex":[0.9980019,0.0001912487,0.0005446698,0.000657298,0.0001946148,0.0004103223],"domain_scores_gemma":[0.9987552,0.0001896546,0.00007964007,0.0007289358,0.0000376376,0.0002088927],"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":[0.0005382805,0.002079924,0.9846733,0.0003174769,0.00005727995,0.000004731678,0.0006793609,0.0003707365,0.00005929251,0.000007560393,0.002259593,0.00895247],"study_design_scores_gemma":[0.01889652,0.01675962,0.3474559,0.0002974773,0.000166732,0.00007904854,0.02426957,0.4993981,0.00005673345,0.002466414,0.0893818,0.0007720941],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9706738,0.0003353795,0.01592649,0.00225403,0.001565771,0.004187619,0.004937681,0.00008595493,0.00003324656],"genre_scores_gemma":[0.9931327,0.000007286784,0.005873113,0.0001223948,0.0002216354,0.0001737618,0.0003511039,0.00002297097,0.00009506164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6372174,"threshold_uncertainty_score":0.6532398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07602742396197423,"score_gpt":0.3369067089851246,"score_spread":0.2608792850231504,"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."}}