{"id":"W4318762929","doi":"10.1101/2023.01.30.526246","title":"Smartwatch-based prediction of single-stride and stride-to-stride gait outcomes using regression-based machine learning","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science; University of Ottawa","keywords":"STRIDE; Inertial measurement unit; Gait; Computer science; Support vector machine; Gait analysis; Smartwatch; Accelerometer; Artificial intelligence; Intraclass correlation; Random forest; Machine learning; Mathematics; Wearable computer; Physical medicine and rehabilitation; Statistics; Medicine; Reproducibility","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001343055,0.0005970653,0.0007121504,0.0006414194,0.0001286411,0.0004360167,0.0004448513,0.0005134331,0.001992928],"category_scores_gemma":[0.002720923,0.0002787258,0.0005367497,0.0003572932,0.0001108854,0.0003725631,0.0003189511,0.0003452134,0.001156233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000250412,"about_ca_system_score_gemma":0.0002987341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003560751,"about_ca_topic_score_gemma":0.005469801,"domain_scores_codex":[0.9996727,0.00008657931,0.00002303434,0.0001456672,0.00004461263,0.00002758288],"domain_scores_gemma":[0.9991546,0.0003981243,0.0001321319,0.00006602458,0.0002011203,0.00004802461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002488334,0.001962419,0.3090798,0.0002793937,0.0006408244,0.0002097642,0.0001572569,0.2810594,0.03505353,0.000428303,0.003504054,0.3651369],"study_design_scores_gemma":[0.00002376008,0.0003860949,0.04745573,0.00001268735,0.00003285342,0.00004113607,0.00001593832,0.9491651,0.002503105,0.0001329857,0.0002159613,0.00001468797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8905951,0.0002176892,0.1047745,0.0001107655,0.00004919533,0.0001926318,0.001107372,0.001977259,0.0009755309],"genre_scores_gemma":[0.9698723,0.00006528164,0.0276656,0.00003504035,0.00001439939,0.0001405338,0.001094307,0.00004072004,0.001071833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003560751,"threshold_uncertainty_score":0.007102847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05213422331111302,"score_gpt":0.3085696020534661,"score_spread":0.2564353787423531,"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."}}