{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004920117,0.0001531238,0.0004906768,0.0001178058,0.0005744421,0.0003477111,0.0001519264,0.0001064229,0.000008342891],"category_scores_gemma":[0.004616907,0.0001202449,0.00006358662,0.0006959536,0.0002047884,0.0003470458,0.0001112369,0.0007330979,0.00002770062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003127943,"about_ca_system_score_gemma":0.001047842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005391245,"about_ca_topic_score_gemma":0.0003046926,"domain_scores_codex":[0.9966218,0.000284461,0.001413292,0.0005336753,0.0004847986,0.0006619248],"domain_scores_gemma":[0.9973315,0.0009312828,0.0004564806,0.0005860122,0.0005017162,0.0001929971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004002081,0.0002825276,0.04266001,0.0004746527,0.00002623754,0.000009312927,0.002495376,0.00006797958,0.00005485904,0.05355218,0.006283095,0.8936936],"study_design_scores_gemma":[0.0003435693,0.005679052,0.1296996,0.00503044,0.00009172534,0.0001871969,0.07984049,0.004158325,0.007799601,0.7056657,0.06045005,0.001054303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6347892,0.0002947358,0.02824918,0.3313597,0.0008687215,0.001540771,0.0000338509,0.0001005769,0.002763305],"genre_scores_gemma":[0.9872156,0.0008064908,0.003961125,0.006227204,0.001177344,0.0001009074,0.0001053366,0.00001892116,0.0003870945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8926393,"threshold_uncertainty_score":0.5527202,"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."}}