{"id":"W4385068605","doi":"10.3389/fpubh.2023.1169083","title":"Digital health technology combining wearable gait sensors and machine learning improve the accuracy in prediction of frailty","year":2023,"lang":"en","type":"article","venue":"Frontiers in Public Health","topic":"Frailty in Older Adults","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Guangzhou Municipal Science and Technology Project; National Natural Science Foundation of China; Guangdong Provincial Hospital of Traditional Chinese Medicine","keywords":"Machine learning; Wearable computer; Artificial intelligence; Gait; Computer science; Feature selection; Wearable technology; Gait analysis; Feature (linguistics); Identification (biology); Preferred walking speed; Physical medicine and rehabilitation; Medicine","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":[0.001850897,0.0001711892,0.0005806157,0.00101133,0.0001481897,0.00003880305,0.0001559839,0.0001619459,0.000006913272],"category_scores_gemma":[0.002355026,0.0001431261,0.00003736528,0.00186217,0.0002213895,0.0002923849,0.0001309065,0.001068337,0.000004195046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004036615,"about_ca_system_score_gemma":0.0007032902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005882932,"about_ca_topic_score_gemma":0.00007827151,"domain_scores_codex":[0.9975918,0.0001910819,0.0007433119,0.0003850429,0.0003164637,0.000772304],"domain_scores_gemma":[0.9988562,0.0002090221,0.0003100177,0.0003434442,0.00006208212,0.0002192697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004037565,0.0001020755,0.6151338,0.000325558,0.00002802208,0.00000943703,0.002778948,0.00007292887,0.00001839669,0.0001058471,0.008150497,0.3732341],"study_design_scores_gemma":[0.01099814,0.003459985,0.6612723,0.001751294,0.00001267352,0.0001593843,0.04385762,0.162846,0.00007015619,0.001799908,0.1133654,0.0004070661],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8015909,0.002805452,0.001599731,0.189659,0.001006957,0.001694878,0.0001288286,0.000445168,0.001069185],"genre_scores_gemma":[0.9951576,0.002127724,0.0009314997,0.0006113655,0.00004309841,0.00004403028,0.0001180773,0.00003486056,0.0009317732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.372827,"threshold_uncertainty_score":0.5836511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03847551720265994,"score_gpt":0.2960313146119115,"score_spread":0.2575557974092516,"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."}}