{"id":"W4410595514","doi":"10.2196/72838","title":"Auxiliary Teaching and Student Evaluation Methods Based on Facial Expression Recognition in Medical Education","year":2025,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Technology and Human Factors in Education and Health","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Facial expression; Computer science; Dependency (UML); Facial recognition system; Expression (computer science); Facial expression recognition; Quality (philosophy); Data collection; Teaching method; Multimedia; Artificial intelligence; Mathematics education; Pattern recognition (psychology); Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001603236,0.0001445822,0.0002244059,0.00078408,0.0003210354,0.00002141007,0.00008424504,0.0003123941,0.0008764757],"category_scores_gemma":[0.0006674099,0.0001245477,0.00004237471,0.0001395522,0.00008087169,0.00007295443,0.00002810719,0.0008368283,0.000005550656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003047437,"about_ca_system_score_gemma":0.0007473635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003646421,"about_ca_topic_score_gemma":0.0000486147,"domain_scores_codex":[0.99828,0.0004920699,0.0003350841,0.0003210969,0.000407145,0.0001645292],"domain_scores_gemma":[0.999326,0.0001719456,0.0000871098,0.0002169288,0.00007789987,0.0001201413],"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":[0.000123113,0.00276112,0.3697957,0.0001953796,0.00001640398,0.000001360252,0.004720715,0.000001279477,0.001467154,0.002202727,0.003949147,0.6147659],"study_design_scores_gemma":[0.001538716,0.0002138204,0.9863916,0.0008046432,0.00003751943,0.00000101866,0.002305325,0.0002636968,0.001100789,0.00324415,0.003969292,0.0001293974],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9884902,0.00006917944,0.0001569458,0.001874773,0.0005401006,0.0008496642,0.000001984376,0.00009451587,0.007922656],"genre_scores_gemma":[0.996148,0.00000884841,0.0009703051,0.002052526,0.00008275915,0.0001958044,0.0001968928,0.000009317901,0.0003355735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6165959,"threshold_uncertainty_score":0.9596794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06448336788098032,"score_gpt":0.5227531546202071,"score_spread":0.4582697867392268,"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."}}