{"id":"W2142004159","doi":"10.3899/jrheum.130813","title":"Item Response Theory, Computerized Adaptive Testing, and PROMIS: Assessment of Physical Function","year":2013,"lang":"en","type":"article","venue":"The Journal of Rheumatology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":208,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Computerized adaptive testing; Patient-Reported Outcomes Measurement Information System; Item response theory; Item bank; CLARITY; Medicine; Reliability (semiconductor); Standardization; Perspective (graphical); Short Forms; Construct (python library); Applied psychology; Function (biology); Psychometrics; Computer science; Psychology; Clinical psychology; Artificial intelligence","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":[0.03893904,0.001956327,0.002096681,0.006277141,0.0005139171,0.001547497,0.002088175,0.001750572,0.005746262],"category_scores_gemma":[0.1074202,0.0004529819,0.002025729,0.01152929,0.001423411,0.002077831,0.002520027,0.003374055,0.002693571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001877078,"about_ca_system_score_gemma":0.003768194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001639657,"about_ca_topic_score_gemma":0.001493077,"domain_scores_codex":[0.8934825,0.08685353,0.004762859,0.002287758,0.01205563,0.0005576941],"domain_scores_gemma":[0.9454875,0.03565212,0.008493402,0.002819315,0.006859671,0.000687935],"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":[0.001166531,0.001322663,0.06975468,0.007402937,0.001879806,0.0002238467,0.001471587,0.01072439,0.0009973865,0.03147014,0.04650845,0.8270776],"study_design_scores_gemma":[0.002620512,0.00622469,0.5763922,0.01189532,0.002263198,0.005749926,0.002112772,0.06208725,0.002787787,0.146112,0.1810233,0.0007311305],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09679815,0.06298154,0.6988117,0.0168528,0.001993426,0.0356941,0.02186958,0.004347635,0.06065103],"genre_scores_gemma":[0.380141,0.02061686,0.5076527,0.00548115,0.001137567,0.06560244,0.01348241,0.0002615754,0.005624328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03893904,"threshold_uncertainty_score":0.2059318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2335860100349148,"score_gpt":0.4218876205134344,"score_spread":0.1883016104785196,"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."}}