{"id":"W3086518401","doi":"10.36227/techrxiv.12950279.v1","title":"The Effect of Improving Facial Alignment Accuracy on the Video-based Detection of Neurological Diseases","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Facial Nerve Paralysis Treatment and Research","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; Vector Institute; Sunnybrook Health Science Centre","funders":"Michael J. Fox Foundation for Parkinson's Research","keywords":"Landmark; Computer science; Artificial intelligence; Classifier (UML); Amyotrophic lateral sclerosis; Pattern recognition (psychology); Speech recognition; Medicine; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000393444,0.0002422642,0.0005256423,0.00006506861,0.0001513863,0.00002796435,0.0002572186,0.0001517771,0.00007321891],"category_scores_gemma":[0.001872671,0.00009041398,0.000584737,0.0001366394,0.0002283551,0.00001068698,0.0002962423,0.0004925539,0.00001472997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004220928,"about_ca_system_score_gemma":0.00009948812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001615453,"about_ca_topic_score_gemma":0.0000129722,"domain_scores_codex":[0.997802,0.0005607611,0.0003723197,0.0003607891,0.0006971579,0.0002069799],"domain_scores_gemma":[0.9963977,0.002677826,0.0002305319,0.000523272,0.00007019566,0.0001004795],"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":[0.04481948,0.001488353,0.115296,0.002844186,0.002659759,0.0001391853,0.0001693598,0.002412324,0.2519157,0.0003241446,0.0009430274,0.5769885],"study_design_scores_gemma":[0.003146284,0.01449211,0.08083504,0.0001737171,0.001449599,0.000001279702,0.00003601428,0.02130186,0.8775244,0.0001503855,0.0006668454,0.000222439],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905943,0.0002627573,0.0001950619,0.006460638,0.0001703879,0.001856682,0.00002840626,0.00004102778,0.0003907023],"genre_scores_gemma":[0.9993363,0.00006113076,0.00000856211,0.000141815,0.0001213349,0.0001975064,0.00003069279,0.00001350981,0.00008912404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6256087,"threshold_uncertainty_score":0.3686975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03147930520958044,"score_gpt":0.3194089055141022,"score_spread":0.2879296003045217,"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."}}