{"id":"W4416768144","doi":"10.1186/s41687-025-00964-4","title":"Beyond diagnostic test performance: two content-validated questionnaires assessing patient and clinician satisfaction with diagnostic tests","year":2025,"lang":"en","type":"article","venue":"Journal of Patient-Reported Outcomes","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Armand Frappier Museum","funders":"","keywords":"Debriefing; Diagnostic test; Test (biology); Patient satisfaction; Medical diagnosis; Cognitive interview; Diagnostic accuracy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005399566,0.0003448681,0.0009633574,0.000396381,0.0001979944,0.0001222488,0.0000752768,0.0001512694,0.00002904315],"category_scores_gemma":[0.2396197,0.0002318525,0.0001906251,0.0004257295,0.0002103334,0.0003652069,0.00005887956,0.0006107569,0.000004724353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001759135,"about_ca_system_score_gemma":0.0005718528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002531704,"about_ca_topic_score_gemma":0.0001000774,"domain_scores_codex":[0.9964247,0.0001214451,0.002011185,0.0003456906,0.0007346146,0.0003623939],"domain_scores_gemma":[0.9473246,0.04881752,0.001921608,0.0003787073,0.001146412,0.000411137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001694603,0.0006323588,0.9090241,0.00006314921,0.0003465041,0.0007707076,0.0001792809,0.00008428472,0.0001142738,0.00001828096,0.0004587084,0.08813886],"study_design_scores_gemma":[0.005321298,0.0026789,0.9793688,0.00882392,0.001287889,0.0008642138,0.0005061739,0.00009386792,0.0006029636,0.0001406244,0.00008003675,0.0002313137],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953327,0.0007505772,0.00015523,0.001520693,0.00135727,0.0005440807,0.00000756005,0.00005914058,0.0002727346],"genre_scores_gemma":[0.9965302,0.0004510942,0.001420668,0.001354595,0.0001026345,0.00002026269,0.00002042923,0.00003089871,0.00006916824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2390798,"threshold_uncertainty_score":0.9454669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02388479223893791,"score_gpt":0.3438147388133355,"score_spread":0.3199299465743976,"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."}}