{"id":"W3195751257","doi":"10.3389/fninf.2021.712623","title":"A Validation of Supervised Deep Learning for Gait Analysis in the Cat","year":2021,"lang":"en","type":"article","venue":"Frontiers in Neuroinformatics","topic":"Veterinary Orthopedics and Neurology","field":"Veterinary","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; Université de Sherbrooke","funders":"National Institute of Neurological Disorders and Stroke; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Kinematics; Gait; Intraclass correlation; Motion analysis; Correlation coefficient; STRIDE; Gait analysis; Computer science; Treadmill; Pearson product-moment correlation coefficient; Software; Concordance correlation coefficient; Artificial intelligence; Simulation; Concordance; Match moving; Biomedical engineering; Motion (physics); Physical medicine and rehabilitation; Mathematics; Statistics; Reproducibility; Machine learning; Engineering; Medicine; Physics; Physical therapy","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":[0.003282782,0.0007127951,0.0003779384,0.0009675808,0.0003012688,0.0007074404,0.0007510175,0.0007618829,0.0009511018],"category_scores_gemma":[0.01184493,0.0002492047,0.0004736639,0.0004689977,0.0005165518,0.0004412254,0.0009554229,0.0005280969,0.0004767001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000649276,"about_ca_system_score_gemma":0.0009388273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006000745,"about_ca_topic_score_gemma":0.01038412,"domain_scores_codex":[0.9981489,0.0006106733,0.0001503744,0.0006294521,0.0003537604,0.0001068643],"domain_scores_gemma":[0.9955948,0.001858697,0.0004203343,0.0006057519,0.001346237,0.0001740791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002051261,0.0008369066,0.1501298,0.0007242712,0.001099401,0.0005005625,0.0005573453,0.1469785,0.1062431,0.002337911,0.006052982,0.5824881],"study_design_scores_gemma":[0.00009216986,0.001155934,0.09707815,0.0001613211,0.0001565805,0.000473382,0.0001746175,0.8611915,0.0344226,0.001606119,0.003424015,0.00006361931],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8231913,0.0007532277,0.1701147,0.0001817479,0.0001155604,0.0001647817,0.001144761,0.002027359,0.002306497],"genre_scores_gemma":[0.9180439,0.0001223987,0.07802188,0.0001176756,0.00001189342,0.0001820511,0.002201589,0.0001019414,0.001196763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006000745,"threshold_uncertainty_score":0.01736122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03625344534207654,"score_gpt":0.2885185631761684,"score_spread":0.2522651178340918,"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."}}