{"id":"W7117303567","doi":"10.1016/j.jtumed.2025.11.004","title":"From diagnostics to education: Multi-domain evaluation of LLM chatbots in neurology","year":2025,"lang":"en","type":"article","venue":"Journal of Taibah University Medical Sciences","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Workflow; Adaptation (eye); Neurology; Clinical neurology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.02014873,0.000839928,0.00120522,0.001769613,0.001217966,0.002448132,0.001213486,0.001382382,0.004416189],"category_scores_gemma":[0.09126725,0.0004835148,0.0009982417,0.0008309028,0.0008994773,0.003414701,0.003770479,0.001910149,0.001773125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002864293,"about_ca_system_score_gemma":0.003479342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004389743,"about_ca_topic_score_gemma":0.007016369,"domain_scores_codex":[0.9856652,0.009589915,0.001353342,0.001094038,0.001637064,0.0006605131],"domain_scores_gemma":[0.8954815,0.08043274,0.004422296,0.003837544,0.008111655,0.007714233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02902984,0.03199187,0.09104613,0.008169627,0.001001506,0.0004308247,0.04769897,0.007698963,0.007573352,0.001092142,0.01118806,0.7630786],"study_design_scores_gemma":[0.01430095,0.1140686,0.6416119,0.005843135,0.003688882,0.001090458,0.05974193,0.06438293,0.01973377,0.007961279,0.06627042,0.001305858],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9792922,0.000504084,0.005788208,0.0005913351,0.0001515991,0.004423623,0.0007870622,0.001063654,0.00739823],"genre_scores_gemma":[0.9556005,0.0006840217,0.0271523,0.0007224702,0.00009685821,0.008827312,0.001259667,0.0001684458,0.005488425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02014873,"threshold_uncertainty_score":0.1065579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2057126788288148,"score_gpt":0.4825346791552645,"score_spread":0.2768220003264498,"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."}}