{"id":"W4416707687","doi":"10.2139/ssrn.5770481","title":"Data-Efficient Deep Learning for Differentiating Upper Trapezius Muscle with Myofascial Trigger Point on a Small Prospective sEMG Dataset","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Myofascial pain diagnosis and treatment","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Discriminative model; Deep learning; Electromyography; Pattern recognition (psychology); Convolutional neural network; Receiver operating characteristic; Segmentation; Trapezius muscle","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0005914515,0.001133124,0.0006087799,0.0005990369,0.0003368208,0.0004506168,0.0008456531,0.001243556,0.002121734],"category_scores_gemma":[0.001995004,0.000252136,0.0007117345,0.000518201,0.0002862863,0.0002863256,0.0006724688,0.0009392286,0.001017019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000427522,"about_ca_system_score_gemma":0.000836474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01105341,"about_ca_topic_score_gemma":0.02432182,"domain_scores_codex":[0.99978,0.00004728321,0.00001413221,0.00007360407,0.00003944189,0.00004548159],"domain_scores_gemma":[0.9995937,0.0001952037,0.00002368114,0.00007265979,0.00007862452,0.00003616326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003980321,0.001912553,0.06596774,0.001033165,0.001144628,0.002294091,0.0001537103,0.2059292,0.02967286,0.001705003,0.1981386,0.4880682],"study_design_scores_gemma":[0.0006612526,0.0007461841,0.05996215,0.0001387472,0.0002931245,0.001029512,0.0002325753,0.9015506,0.01407534,0.005672134,0.01554768,0.00009076808],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.850633,0.00446786,0.0524924,0.002323759,0.0007180885,0.0002738674,0.07806399,0.006436238,0.00459065],"genre_scores_gemma":[0.8060258,0.0006344398,0.03797764,0.0004548739,0.0001511375,0.0002196865,0.1488149,0.0002429356,0.00547856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01105341,"threshold_uncertainty_score":0.02197814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01427287908373037,"score_gpt":0.2680798575355883,"score_spread":0.2538069784518579,"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."}}