{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.240518,0.003644949,0.004101775,0.01409331,0.003374182,0.02356351,0.007495504,0.009258329,0.002583896],"category_scores_gemma":[0.4344946,0.001982183,0.004268064,0.008348042,0.01006721,0.02468484,0.008422072,0.01128437,0.002122589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0107902,"about_ca_system_score_gemma":0.02561941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01210439,"about_ca_topic_score_gemma":0.00838389,"domain_scores_codex":[0.6637423,0.128339,0.05433147,0.007605183,0.1406552,0.005326807],"domain_scores_gemma":[0.4419035,0.2593451,0.02908112,0.04479725,0.2208344,0.004038585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004711161,0.001504067,0.017201,0.01926614,0.0005318114,0.000684272,0.01346989,0.01323119,0.01235527,0.4162013,0.04616151,0.4589224],"study_design_scores_gemma":[0.0004412923,0.002802032,0.02884297,0.03854712,0.0009851555,0.001778933,0.01486177,0.04671528,0.02182104,0.4656469,0.3765054,0.001052106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04081054,0.0290747,0.749241,0.09262564,0.00550068,0.005455336,0.001551969,0.003797577,0.07194252],"genre_scores_gemma":[0.1975066,0.01417189,0.752996,0.01407167,0.001266105,0.009244204,0.004979781,0.002270675,0.003493024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.240518,"threshold_uncertainty_score":0.9365765,"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."}}