{"id":"W4413326439","doi":"10.1177/2327857925141037","title":"Artificial Intelligence-Driven Usability Testing Products and Ethical Considerations for Medical Solutions Design","year":2025,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Usability; Computer science; Usability engineering; Management science; Human–computer interaction; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.343378,0.001069111,0.0008737243,0.003405633,0.004211262,0.01337633,0.003493293,0.004496849,0.006167445],"category_scores_gemma":[0.5033061,0.0008879658,0.001472395,0.002187392,0.01469931,0.0111669,0.007083351,0.006795124,0.001842109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006051461,"about_ca_system_score_gemma":0.01726771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001190856,"about_ca_topic_score_gemma":0.001888575,"domain_scores_codex":[0.5008293,0.4261286,0.01700691,0.004630151,0.04919203,0.002213097],"domain_scores_gemma":[0.3310276,0.531691,0.02614529,0.04158969,0.06571477,0.003831668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006590316,0.0009008495,0.01007886,0.005578394,0.000156198,0.0008444881,0.08767729,0.002191691,0.004946642,0.3506568,0.02443695,0.5118728],"study_design_scores_gemma":[0.0006563697,0.004306074,0.0143793,0.02317737,0.0002779759,0.002405222,0.03724061,0.01298253,0.01153495,0.492183,0.4004277,0.0004288859],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08082668,0.007934633,0.6507432,0.1102499,0.002274992,0.01597641,0.0003157558,0.000867291,0.1308112],"genre_scores_gemma":[0.3815836,0.002648787,0.5678096,0.01574097,0.0005448921,0.0240248,0.0002063433,0.0003799486,0.00706102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.343378,"threshold_uncertainty_score":0.8097318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2537417162080087,"score_gpt":0.4303476746978047,"score_spread":0.176605958489796,"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."}}