{"id":"W2590915444","doi":"10.2196/mental.6545","title":"Applying Computerized Adaptive Testing to the Four-Dimensional Symptom Questionnaire (4DSQ): A Simulation Study","year":2017,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computerized adaptive testing; Psychology; Medicine; Computer science; Medical physics; Artificial intelligence; Clinical psychology; Psychometrics","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.008892362,0.000194463,0.0003950724,0.0002461317,0.003453065,0.0005294427,0.00110379,0.00004275843,0.00002061049],"category_scores_gemma":[0.009948016,0.0001213396,0.00007234015,0.0007906386,0.0000710349,0.0002946505,0.0006766758,0.0002226066,0.00009239385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001890481,"about_ca_system_score_gemma":0.0001325897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006850988,"about_ca_topic_score_gemma":0.0001220616,"domain_scores_codex":[0.9956571,0.001032872,0.0007722672,0.000665135,0.001440586,0.0004320782],"domain_scores_gemma":[0.988948,0.00867214,0.0008862963,0.0009970758,0.0002530928,0.0002433788],"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":[0.0001370591,0.0002169136,0.1731882,0.000005897698,0.00001581022,0.000006239946,0.002093635,0.008146347,0.00003027216,0.0001037512,0.001385254,0.8146706],"study_design_scores_gemma":[0.0008059019,0.0007613302,0.836661,0.0001257943,0.000002726719,0.00001283814,0.001569799,0.1578047,0.000002283884,0.001019734,0.00108894,0.0001449626],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9582966,0.00008133957,0.03022545,0.004530118,0.001700185,0.004432333,0.00001781091,0.0001309944,0.0005851483],"genre_scores_gemma":[0.9677007,5.412931e-7,0.03054376,0.00110167,0.0002688874,0.0002379699,0.000001642432,0.00001323453,0.0001316536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8145257,"threshold_uncertainty_score":0.9983916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5552826323121655,"score_gpt":0.5414749915067238,"score_spread":0.01380764080544161,"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."}}