{"id":"W4413681749","doi":"10.1016/j.landig.2025.100910","title":"How CHART (Chatbot Assessment Reporting Tool) can help to advance clinical artificial intelligence research through clearer task definition and robust validation","year":2025,"lang":"en","type":"article","venue":"The Lancet Digital Health","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Chatbot; Task (project management); Chart; Computer science; Data science; Artificial intelligence; Engineering; Systems engineering; Statistics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05188951,0.002102009,0.001122865,0.004897573,0.001150018,0.005882731,0.003231199,0.003677667,0.03487143],"category_scores_gemma":[0.2316623,0.001015282,0.00134184,0.001359358,0.001272602,0.0100491,0.005478085,0.002443681,0.01948199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001603958,"about_ca_system_score_gemma":0.005627676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005794527,"about_ca_topic_score_gemma":0.009329247,"domain_scores_codex":[0.9690732,0.02015037,0.003138493,0.002803683,0.004172446,0.0006617844],"domain_scores_gemma":[0.7442594,0.1878577,0.009418266,0.02640904,0.0273775,0.004678254],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001694649,0.001029511,0.01989856,0.00300362,0.0002780109,0.0004603748,0.003466903,0.004835558,0.007427979,0.01494977,0.2724738,0.6704813],"study_design_scores_gemma":[0.001289831,0.002360067,0.03379405,0.006167104,0.0004735297,0.001874395,0.003094482,0.1318724,0.03736165,0.08134435,0.6988802,0.001487794],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03236239,0.002011892,0.6719246,0.0186302,0.003027118,0.005561131,0.01839294,0.2137847,0.03430507],"genre_scores_gemma":[0.1463058,0.001005006,0.7936895,0.006168654,0.0007451561,0.005984549,0.01807939,0.01268653,0.01533551],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9481105,"threshold_uncertainty_score":0.2744212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6295280833288414,"score_gpt":0.5803598064640004,"score_spread":0.04916827686484093,"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."}}