{"id":"W4297312826","doi":"10.3389/fdata.2022.979465","title":"The ABC recommendations for validation of supervised machine learning results in biomedical sciences","year":2022,"lang":"en","type":"article","venue":"Frontiers in Big Data","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Front (military); Public opinion; Volume (thermodynamics); Data science; Public health; Artificial intelligence; Computer science; Medicine; Political science; Engineering; Data mining; Pathology; Mechanical engineering","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":[0.1552666,0.002547378,0.004413087,0.01311663,0.00493953,0.01393818,0.00977501,0.02126326,0.02606031],"category_scores_gemma":[0.5604181,0.001594802,0.004667492,0.00792258,0.00662138,0.01011026,0.005319146,0.01493609,0.02581373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005491876,"about_ca_system_score_gemma":0.01357783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01565475,"about_ca_topic_score_gemma":0.01562929,"domain_scores_codex":[0.8369982,0.08439777,0.02329117,0.00797877,0.04499508,0.002339038],"domain_scores_gemma":[0.3351502,0.3592799,0.01491882,0.04895059,0.2343317,0.007368834],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001211643,0.0003173725,0.008052927,0.002403799,0.0005265205,0.0002959737,0.0002675332,0.01006864,0.001305328,0.0630327,0.6969318,0.2155858],"study_design_scores_gemma":[0.001562797,0.0006868839,0.01343993,0.008948403,0.0006427229,0.001018972,0.0004849434,0.1597136,0.009336465,0.3005442,0.5031827,0.0004383925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01003214,0.01827144,0.5363297,0.2627882,0.03505592,0.003991268,0.01991899,0.01263524,0.1009771],"genre_scores_gemma":[0.1222211,0.004850702,0.7392877,0.06210297,0.01238597,0.005375012,0.029147,0.003318301,0.02131108],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8447334,"threshold_uncertainty_score":0.8211379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1559307450808685,"score_gpt":0.3363171335948982,"score_spread":0.1803863885140297,"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."}}