{"id":"W4406731330","doi":"10.2196/60215","title":"Customizing Computerized Adaptive Test Stopping Rules for Clinical Settings Using the Negative Affect Subdomain of the NIH Toolbox Emotion Battery: Simulation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"NIH Office of the Director; National Institutes of Health","keywords":"Affect (linguistics); Toolbox; Reliability (semiconductor); Sadness; Psychology; Anger; Inter-rater reliability; Computer science; Statistics; Clinical psychology; Rating scale; Mathematics; Developmental 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01690295,0.001072086,0.0009004737,0.00070924,0.0003424586,0.001209361,0.001828597,0.001220077,0.002335909],"category_scores_gemma":[0.1083946,0.0006940363,0.001006917,0.0005588764,0.0005912103,0.0009619147,0.001237985,0.001470647,0.0004544409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001297037,"about_ca_system_score_gemma":0.001864946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003242918,"about_ca_topic_score_gemma":0.003083437,"domain_scores_codex":[0.9932159,0.005071732,0.0004583036,0.0006653179,0.0003518709,0.0002368076],"domain_scores_gemma":[0.9039353,0.08234221,0.003986898,0.005448544,0.003425892,0.0008611465],"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":[0.02817235,0.01195586,0.1281998,0.0007716115,0.001102968,0.0006202033,0.003177863,0.6150241,0.01020989,0.007897101,0.003792905,0.1890754],"study_design_scores_gemma":[0.002707588,0.009934406,0.0143924,0.0001176814,0.0003370304,0.0002124102,0.0002360157,0.9573258,0.009126875,0.003461833,0.002022082,0.0001260122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.891141,0.0001020434,0.1039771,0.0001452775,0.0000532618,0.002237358,0.0003210983,0.0006220706,0.001400751],"genre_scores_gemma":[0.9118643,0.00004761449,0.0843915,0.00009380146,0.00001136215,0.002755986,0.0003707171,0.00008492491,0.0003797197],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01690295,"threshold_uncertainty_score":0.08939242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2991523874598335,"score_gpt":0.5905082986049747,"score_spread":0.2913559111451411,"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."}}