{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008788584,0.0001216,0.0002363424,0.0001298695,0.0004324799,0.00004953856,0.0001242786,0.0001823323,0.000008368846],"category_scores_gemma":[0.004868271,0.00009693448,0.00004276345,0.0001375904,0.0002325226,0.00005055686,0.00008566813,0.0004360955,2.526052e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004178802,"about_ca_system_score_gemma":0.00065853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006245208,"about_ca_topic_score_gemma":0.0003307805,"domain_scores_codex":[0.9984695,0.00002155441,0.0007734381,0.0003266554,0.0001996869,0.0002091702],"domain_scores_gemma":[0.9978101,0.001120523,0.0001955419,0.00008507828,0.0006799837,0.0001087322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008757553,0.0004776396,0.3656696,0.002931141,0.00009374335,3.709409e-7,0.01700053,0.0006398825,0.00513089,0.5882236,0.00165726,0.01729955],"study_design_scores_gemma":[0.0006981802,0.004296726,0.2505859,0.009618963,0.0002253777,0.0000654207,0.0448926,0.06633908,0.2144533,0.405593,0.002030919,0.001200603],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9376028,0.00009067389,0.0001689498,0.06031522,0.0005817094,0.001010997,0.00001728501,0.00001755397,0.0001948495],"genre_scores_gemma":[0.9962574,0.0000733429,0.00203397,0.001372386,0.0001614874,0.00007226113,0.000007310937,0.000008185769,0.00001370693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2093224,"threshold_uncertainty_score":0.5828127,"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."}}