{"id":"W3042374417","doi":"10.2196/16727","title":"Calibrating Wrist-Worn Accelerometers for Physical Activity Assessment in Preschoolers: Machine Learning Approaches","year":2020,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institutes of Health","keywords":"Accelerometer; Wrist; Receiver operating characteristic; Logistic regression; Medicine; Intensity (physics); Cluster (spacecraft); Physical therapy; Physical medicine and rehabilitation; Mathematics; Statistics; Computer science; Surgery","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00239338,0.0007100925,0.0005646825,0.001439823,0.0002518343,0.0007034735,0.0006970396,0.0005797336,0.0006159046],"category_scores_gemma":[0.007551125,0.0002362076,0.000480793,0.001016539,0.0002969095,0.0004953371,0.0005167685,0.000686436,0.00034451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005619858,"about_ca_system_score_gemma":0.0006776968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004621275,"about_ca_topic_score_gemma":0.006503172,"domain_scores_codex":[0.9991705,0.0003531943,0.00007864268,0.000200654,0.0001516804,0.00004542534],"domain_scores_gemma":[0.997183,0.001499616,0.0005459618,0.000174243,0.0005498143,0.0000474218],"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":[0.0003298683,0.000488785,0.3354944,0.0004884985,0.0004835109,0.00012621,0.0005355876,0.07992803,0.01681135,0.0009000539,0.001404901,0.5630088],"study_design_scores_gemma":[0.00004498661,0.0005140502,0.2817115,0.0002505546,0.0002098243,0.0002407224,0.000584344,0.6994241,0.01106143,0.003989681,0.001904312,0.00006442799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4373268,0.002016373,0.5571496,0.0003454229,0.00005145066,0.0002606186,0.0003990707,0.0007771427,0.001673469],"genre_scores_gemma":[0.7693927,0.0006874762,0.2287209,0.00006332545,0.00003325139,0.0002683324,0.0003566717,0.00003304298,0.0004443216],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004621275,"threshold_uncertainty_score":0.01265758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.194690837372353,"score_gpt":0.434228422601906,"score_spread":0.2395375852295529,"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."}}