{"id":"W4412823866","doi":"10.1136/bmjmed-2025-001632","title":"Reporting guideline for chatbot health advice studies: the Chatbot Assessment Reporting Tool (CHART) statement","year":2025,"lang":"en","type":"article","venue":"BMJ Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"McMaster University","keywords":"Chatbot; Checklist; Guideline; Computer science; Chart; Advice (programming); Medicine; Data science; Psychology; World Wide Web; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"category_scores_codex":[0.4529815,0.005051249,0.007702951,0.03092102,0.004516799,0.01342744,0.009942969,0.01248097,0.01988862],"category_scores_gemma":[0.7358335,0.006123809,0.01613233,0.0194736,0.005034176,0.01083976,0.01339627,0.01205811,0.0149284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01244315,"about_ca_system_score_gemma":0.06860302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01001353,"about_ca_topic_score_gemma":0.009861769,"domain_scores_codex":[0.340554,0.3629918,0.2488732,0.00706207,0.03650995,0.004009009],"domain_scores_gemma":[0.1438329,0.4606242,0.1072217,0.04297324,0.2405452,0.004802696],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001109168,0.0003319194,0.003779189,0.1411855,0.001304429,0.0005447391,0.00949954,0.002479592,0.001510316,0.01207835,0.6084219,0.2177553],"study_design_scores_gemma":[0.00295737,0.0005925752,0.005957666,0.2947138,0.001741455,0.0007218804,0.006073904,0.004415841,0.003949679,0.01686559,0.6612642,0.0007461339],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"protocol","genre_gemma":"methods","genre_scores_codex":[0.003795575,0.01709616,0.2895439,0.06663358,0.01389067,0.5061073,0.06957084,0.01262296,0.02073896],"genre_scores_gemma":[0.00577651,0.006237702,0.3614048,0.009155456,0.0009174553,0.5961648,0.01572074,0.0009797162,0.003642866],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5470185,"threshold_uncertainty_score":0.6745713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.506489169898254,"score_gpt":0.6595066021220202,"score_spread":0.1530174322237662,"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."}}