{"id":"W4390776874","doi":"10.2196/51308","title":"Comprehensiveness, Accuracy, and Readability of Exercise Recommendations Provided by an AI-Based Chatbot: Mixed Methods Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"CVS Health; University of Connecticut","keywords":"Readability; Chatbot; Medicine; Health care; Medical education; Physical therapy; Computer science; Artificial intelligence","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":[0.08635827,0.0007068053,0.001950454,0.003492301,0.001461971,0.003250263,0.001886274,0.001057258,0.003032933],"category_scores_gemma":[0.1730465,0.00095958,0.002738684,0.00318671,0.002083755,0.003345736,0.002789567,0.001249224,0.0005686594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002812669,"about_ca_system_score_gemma":0.002828255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002297112,"about_ca_topic_score_gemma":0.003789605,"domain_scores_codex":[0.9301056,0.04250142,0.01156619,0.004775574,0.009684544,0.001366676],"domain_scores_gemma":[0.7176582,0.2094265,0.03372092,0.0110615,0.02616705,0.001965768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.006338657,0.005925342,0.6637819,0.01509577,0.004745432,0.0005595638,0.1677415,0.0006602692,0.001844457,0.001307156,0.002485256,0.1295146],"study_design_scores_gemma":[0.001670645,0.01800667,0.7932929,0.01242248,0.005050941,0.001355776,0.1340072,0.01130864,0.006175222,0.002907001,0.01311802,0.0006845299],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9860792,0.001377081,0.005972578,0.0002012766,0.00004990708,0.003799725,0.0007403757,0.00004479004,0.00173502],"genre_scores_gemma":[0.9741068,0.0007788005,0.01173957,0.0004272211,0.00005957457,0.01165596,0.0005690004,0.00004808685,0.0006149707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08635827,"threshold_uncertainty_score":0.4567116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05046909020929952,"score_gpt":0.5520507845820172,"score_spread":0.5015816943727176,"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."}}