{"id":"W4315874241","doi":"10.1038/s41598-023-27899-4","title":"Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Veterinary Equine Medical Research","field":"Veterinary","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Regional Development Fund; Arthritis Society; Dutch Arthritis Society","keywords":"Lameness; Computer science; Recurrent neural network; Gait; Ground reaction force; Artificial intelligence; Withers; Treadmill; Artificial neural network; Kinematics; Metric (unit); Pattern recognition (psychology); Physical medicine and rehabilitation; Body weight; Physical therapy; Medicine; Engineering; Surgery","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0007558358,0.00099535,0.0004542395,0.0004882404,0.000142995,0.00049419,0.0004776496,0.0005998368,0.0006451916],"category_scores_gemma":[0.002476578,0.0002981125,0.0005682763,0.0003544879,0.0002172387,0.0004519028,0.0003021804,0.0006080008,0.0002912729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003892647,"about_ca_system_score_gemma":0.0003066705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008980725,"about_ca_topic_score_gemma":0.006999473,"domain_scores_codex":[0.999813,0.00004947526,0.00001500315,0.00005847378,0.00003206669,0.00003199964],"domain_scores_gemma":[0.999423,0.000295458,0.00008291695,0.00004059331,0.0001353254,0.00002272002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000382054,0.0001745229,0.01834384,0.0001137741,0.0001515564,0.0001645151,0.00008308327,0.8543434,0.01332385,0.0001759723,0.000895271,0.1118481],"study_design_scores_gemma":[0.000002228456,0.00002769832,0.002964822,0.000005468184,0.000006171053,0.000005858387,0.000007353433,0.9959701,0.0008939659,0.0000684126,0.00004341421,0.000004485484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8763909,0.0007943063,0.120204,0.0001794076,0.00009963527,0.00003869656,0.0005279094,0.0008736544,0.000891468],"genre_scores_gemma":[0.9920971,0.00007444435,0.00703735,0.00001647419,0.000009511482,0.00002486345,0.0003360637,0.000014126,0.000390215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008980725,"threshold_uncertainty_score":0.0178569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3796498687531345,"score_gpt":0.3869054723407426,"score_spread":0.007255603587608073,"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."}}