{"id":"W4412626405","doi":"10.2196/80416","title":"A Multiassessment and Multiprofessional Agents Approach for Medical Chatbot Risk Estimation: Development and Evaluation Study","year":2025,"lang":"en","type":"preprint","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Chatbot; Estimation; Computer science; Data science; Artificial intelligence; Engineering; World Wide Web; Systems engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01509009,0.001019534,0.0007223547,0.001536906,0.0007060082,0.001776869,0.00244042,0.001760981,0.003548336],"category_scores_gemma":[0.0303396,0.0005827848,0.0007338732,0.0006285775,0.0007358365,0.002989557,0.003437927,0.001877746,0.00110556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002158073,"about_ca_system_score_gemma":0.003145837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005253234,"about_ca_topic_score_gemma":0.005776003,"domain_scores_codex":[0.9877971,0.007967468,0.0007082424,0.0008773557,0.002293211,0.000356602],"domain_scores_gemma":[0.9716288,0.01739077,0.001021326,0.001583612,0.006219639,0.002155758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004109171,0.01506354,0.06114481,0.003902938,0.000762997,0.001115555,0.0087016,0.04688292,0.02613816,0.007032387,0.01130055,0.8138454],"study_design_scores_gemma":[0.0009996512,0.009900875,0.03562025,0.0006022051,0.0007089494,0.0008399491,0.004139341,0.8971355,0.02332558,0.002772667,0.02370836,0.0002467631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7147057,0.0009087901,0.2566868,0.0009241602,0.0002271973,0.008964916,0.0005752526,0.006338811,0.01066834],"genre_scores_gemma":[0.6242909,0.0003148628,0.3646879,0.0003377965,0.00004079793,0.004557977,0.001169268,0.0001532701,0.004447268],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01509009,"threshold_uncertainty_score":0.07980502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2365809564263897,"score_gpt":0.5380787372499735,"score_spread":0.3014977808235837,"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."}}