{"id":"W4291632994","doi":"10.2196/39917","title":"Training and Profiling a Pediatric Facial Expression Classifier for Children on Mobile Devices: Machine Learning Study","year":2022,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; Islamic Development Bank; U.S. National Library of Medicine; Weston Havens Foundation; Bill and Melinda Gates Foundation; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Hartwell Foundation; Wu Tsai Neurosciences Institute, Stanford University; National Institutes of Health; National Science Foundation","keywords":"Computer science; Sadness; Convolutional neural network; Artificial intelligence; Facial expression; Facial expression recognition; Disgust; Machine learning; Classifier (UML); Anger; Facial recognition system; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001844953,0.0001240528,0.0001695367,0.0004946695,0.00131732,0.00005211207,0.0001438179,0.00005824585,0.0007095289],"category_scores_gemma":[0.00005702467,0.0001080912,0.00005223612,0.0003781592,0.00004114778,0.000145248,0.0001818673,0.001044809,0.00004419083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007042727,"about_ca_system_score_gemma":0.00004139938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001307637,"about_ca_topic_score_gemma":0.000005188687,"domain_scores_codex":[0.9973822,0.001087715,0.0002475395,0.0003338118,0.0005174036,0.0004313838],"domain_scores_gemma":[0.9992107,0.0003713924,0.0001005214,0.0001207689,0.0001046151,0.00009204805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.002323158,0.005403009,0.1420838,0.0002144102,0.0002032542,0.00001890577,0.4973104,0.0001919153,0.0008048611,0.0007448907,0.00476602,0.3459354],"study_design_scores_gemma":[0.01586599,0.03433042,0.3945063,0.00007356481,0.00005797474,0.00007043179,0.5324237,0.003946325,0.0005501461,0.0007065902,0.0165484,0.0009201174],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915525,0.0001074958,0.0001092079,0.00003534038,0.0001860666,0.002875101,0.00009323599,0.00006404359,0.004977002],"genre_scores_gemma":[0.994322,0.000008499961,0.0000549186,0.00003344322,0.0001815714,0.004409863,0.0001749385,0.00002520718,0.0007895327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3450153,"threshold_uncertainty_score":0.9999828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1398498578831423,"score_gpt":0.4528776521375235,"score_spread":0.3130277942543812,"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."}}