{"id":"W4413413384","doi":"10.1007/s11136-025-04046-2","title":"Tree-based item-response theory model for evaluating differential item functioning in patient-reported outcome measures: a web-based R Shiny implementation","year":2025,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Manitoba; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Differential item functioning; Item response theory; Quality of Life Research; Patient-reported outcome; Outcome (game theory); Psychometrics; Quality of life (healthcare); Differential (mechanical device); Public health; Psychology; Clinical psychology; Medicine; Mathematics; Psychotherapist; Nursing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.179286,0.0002097059,0.0007580848,0.003021332,0.0004704626,0.0002548174,0.0007791933,0.000160588,0.0002035166],"category_scores_gemma":[0.6795112,0.0001694371,0.000319982,0.004200256,0.0002157942,0.0001887169,0.0001864948,0.0004558034,0.000003092063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002312884,"about_ca_system_score_gemma":0.002020645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003781588,"about_ca_topic_score_gemma":0.0003181537,"domain_scores_codex":[0.9693696,0.02066087,0.003500212,0.0009553964,0.004742641,0.0007712332],"domain_scores_gemma":[0.6337835,0.3613176,0.001101629,0.001062056,0.002549422,0.0001857728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0117179,0.0003193542,0.7208325,0.0001579026,0.00006204976,0.000001427955,0.000806635,0.007515688,0.01520414,0.0009601227,0.0005009252,0.2419213],"study_design_scores_gemma":[0.004511096,0.0003579672,0.3395167,0.00008691358,0.00001504726,1.003289e-7,0.006227101,0.6309115,0.0008826238,0.01729008,0.00004240409,0.0001583681],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6536089,0.00007584086,0.3442422,0.0008357943,0.0001815621,0.0008298341,0.00003689705,0.00003542171,0.0001535131],"genre_scores_gemma":[0.9843435,0.000001082136,0.01487049,0.0002011343,0.00002629483,0.000266862,0.00001701921,0.00001559304,0.0002579993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6233959,"threshold_uncertainty_score":0.8450978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8819502951575374,"score_gpt":0.6573421513145343,"score_spread":0.2246081438430031,"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."}}