{"id":"W4409832437","doi":"10.1093/oncolo/oyaf038","title":"Medical accuracy of artificial intelligence chatbots in oncology: a scoping review","year":2025,"lang":"en","type":"review","venue":"The Oncologist","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Princess Margaret Cancer Centre; University of Waterloo; University of Toronto","funders":"","keywords":"Readability; Workload; MEDLINE; Medicine; Oncology; Inclusion (mineral); Resource (disambiguation); Internal medicine; Medical education; Psychology; Computer science; Political science","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":[],"consensus_categories":[],"category_scores_codex":[0.04794689,0.001119056,0.004217464,0.02243759,0.0009928264,0.006209438,0.003446016,0.003514812,0.00414315],"category_scores_gemma":[0.3154352,0.001399085,0.00498934,0.0143783,0.00363683,0.006565276,0.003076848,0.002280166,0.0006063553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006149246,"about_ca_system_score_gemma":0.0153419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01009437,"about_ca_topic_score_gemma":0.01076619,"domain_scores_codex":[0.9583088,0.01811409,0.0134513,0.002443405,0.007201545,0.0004807935],"domain_scores_gemma":[0.4511041,0.5040052,0.02133583,0.0038439,0.01917244,0.0005386067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002900674,0.0000606418,0.004381264,0.6213841,0.003149577,0.000188664,0.001781639,0.0007613701,0.0001453504,0.00245165,0.003997854,0.3614077],"study_design_scores_gemma":[0.00005102186,0.0001872212,0.00561296,0.9379393,0.009769524,0.0006527937,0.001111953,0.0006685363,0.0003907573,0.001907836,0.04163757,0.00007041192],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009977537,0.9959681,0.0006491901,0.001030378,0.0001959185,0.000119343,0.0001533061,0.00001394025,0.0008720966],"genre_scores_gemma":[0.02985425,0.9650915,0.002701689,0.001180665,0.0003387154,0.0004143689,0.0002823005,0.00002247501,0.0001139819],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.04794689,"threshold_uncertainty_score":0.2535704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4675575167168528,"score_gpt":0.6145205468759336,"score_spread":0.1469630301590809,"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."}}