{"id":"W4281635259","doi":"10.1038/s41591-022-01833-z","title":"Evaluating and reducing cognitive load should be a priority for machine learning in healthcare","year":2022,"lang":"en","type":"letter","venue":"Nature Medicine","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; University of Toronto; Artificial Intelligence in Medicine (Canada); Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Health care; Cognition; Cognitive load; Computer science; Medicine; Psychology; Neuroscience; Economics","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":[],"category_scores_codex":[0.01105642,0.0007214005,0.001849314,0.001044223,0.004936209,0.007145035,0.002410162,0.04715724,0.01157993],"category_scores_gemma":[0.09957325,0.0005922294,0.001548367,0.0007705785,0.006571604,0.008481589,0.003325627,0.06797393,0.008385753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006551916,"about_ca_system_score_gemma":0.0182614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009638972,"about_ca_topic_score_gemma":0.02059556,"domain_scores_codex":[0.9900815,0.003968963,0.001233055,0.0007941162,0.003064166,0.0008581331],"domain_scores_gemma":[0.8874324,0.07414638,0.002767907,0.002498693,0.019969,0.0131857],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004305087,0.0001487958,0.001125565,0.0001206757,0.0000275468,0.0006157676,0.0001619054,0.0001531675,0.0001195072,0.005058473,0.9544153,0.03801026],"study_design_scores_gemma":[0.0002430743,0.0001706097,0.002731789,0.0015624,0.00006492854,0.00198798,0.001371254,0.00200524,0.0002985354,0.1151402,0.874265,0.0001589356],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.00009086535,0.0003706887,0.0001770454,0.9953908,0.003163464,0.000005367013,0.000008462618,0.00001571827,0.0007776604],"genre_scores_gemma":[0.002943197,0.001146766,0.001694999,0.9633168,0.02861121,0.00005129297,0.00001998767,0.00002344389,0.002192321],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.9889436,"threshold_uncertainty_score":0.05847263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09693438312235235,"score_gpt":0.4651619580729726,"score_spread":0.3682275749506203,"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."}}