{"id":"W4401211805","doi":"10.1109/mrl.2024.3430192","title":"The Role of Data Quality for Reliable AI Performance in Medical Applications","year":2024,"lang":"en","type":"article","venue":"IEEE reliability magazine ","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Quality (philosophy); Computer science; Reliability engineering; Artificial intelligence; 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":[0.055912,0.0009075921,0.001187002,0.003494615,0.002040687,0.015128,0.003621493,0.004243763,0.007328337],"category_scores_gemma":[0.2582747,0.000836166,0.0004764866,0.004756608,0.005919562,0.01443572,0.005337167,0.004681373,0.004743963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004569572,"about_ca_system_score_gemma":0.008177082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00366016,"about_ca_topic_score_gemma":0.001954395,"domain_scores_codex":[0.9365355,0.02871027,0.00584594,0.004024567,0.0237487,0.001135129],"domain_scores_gemma":[0.7068942,0.1991198,0.0146864,0.02829404,0.04723761,0.003767922],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007009882,0.0001571758,0.0145264,0.002201433,0.0001510908,0.0004153917,0.001916825,0.01578856,0.005787476,0.3062051,0.08128782,0.5708618],"study_design_scores_gemma":[0.0001844808,0.0004494382,0.008020379,0.002491035,0.0001595184,0.001149018,0.001330566,0.09686017,0.01403108,0.5863053,0.2887687,0.00025043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02077327,0.04838379,0.685228,0.183642,0.003014579,0.0005963916,0.002506977,0.003845718,0.05200925],"genre_scores_gemma":[0.571391,0.02375618,0.3705911,0.01520035,0.007503045,0.0007243209,0.003280774,0.002219161,0.005334046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.944088,"threshold_uncertainty_score":0.2956945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1309250564315619,"score_gpt":0.4731493103841323,"score_spread":0.3422242539525705,"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."}}