{"id":"W4308183710","doi":"10.3233/shti220992","title":"What Can We Learn from Quality Requirements in ISO/TS 82304-2 for Evaluating Conversational Agents in Healthcare?","year":2022,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Usability; Readability; Computer science; Quality (philosophy); Set (abstract data type); Relevance (law); Health care; Work (physics); Process management; Risk analysis (engineering); Knowledge management; Human–computer interaction; Engineering; Business","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002567514,0.0001088997,0.0003219164,0.0004684226,0.000356008,0.00002400179,0.0003650085,0.00008626964,0.000002214889],"category_scores_gemma":[0.0005020404,0.0001171073,0.00001687353,0.0007798264,0.0001525833,0.0005573936,0.0005192548,0.0003991246,8.403721e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007383869,"about_ca_system_score_gemma":0.0002555744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005813625,"about_ca_topic_score_gemma":0.001700123,"domain_scores_codex":[0.9977853,0.0002344996,0.001153868,0.0002202155,0.0002570038,0.0003490865],"domain_scores_gemma":[0.9987971,0.0003991233,0.000387041,0.0003122229,0.00007290446,0.00003156088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006562939,0.0001826709,0.3994777,0.001316834,0.00002929048,0.000001414008,0.1212745,0.00108654,0.000002717267,0.1212078,0.000206665,0.3551483],"study_design_scores_gemma":[0.003509954,0.0009946449,0.2139246,0.0004828374,0.000003331969,0.000005980664,0.1616187,0.1746892,0.00002336395,0.4402501,0.004078068,0.0004192307],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9077536,0.003783288,0.003200308,0.08304021,0.0007979406,0.001299388,0.00003573847,0.00007932014,0.00001017844],"genre_scores_gemma":[0.984824,0.002625089,0.009912023,0.00220451,0.000005839408,0.0003899665,0.00002586915,0.000003291006,0.000009416927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3547291,"threshold_uncertainty_score":0.4775498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2701706356446133,"score_gpt":0.4690826344258091,"score_spread":0.1989119987811958,"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."}}