{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003409541,0.00008555261,0.0002039325,0.00005390264,0.00009164007,0.00001851761,0.0003060202,0.0001238151,0.00005347593],"category_scores_gemma":[0.0009527462,0.00005969487,0.00004984415,0.0003959452,0.0001914208,0.0001674377,0.00004692062,0.0003059419,0.00008724263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001041824,"about_ca_system_score_gemma":0.0007984735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003918337,"about_ca_topic_score_gemma":0.0003269405,"domain_scores_codex":[0.9982796,0.00004646629,0.0007469686,0.0003654168,0.0003308615,0.0002307147],"domain_scores_gemma":[0.9973988,0.001096606,0.00005385813,0.001083277,0.0002597297,0.0001077257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003481245,0.0004836071,0.06168061,0.002482151,0.00002351178,8.810748e-7,0.0004794752,0.00006582653,0.001314776,0.004844609,0.008325808,0.9199506],"study_design_scores_gemma":[0.00007864372,0.0001904965,0.01152336,0.0003342711,0.00003832103,0.000009434408,0.0002895107,0.101864,0.007068149,0.01748622,0.8610013,0.0001162474],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8845375,0.008834235,0.01152915,0.08312362,0.00164909,0.004710444,0.0001750873,0.0002179144,0.005223008],"genre_scores_gemma":[0.9967743,0.0009184418,0.0007394384,0.0002205065,0.000406423,0.000335882,0.00009830173,0.00001350274,0.0004932072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9198344,"threshold_uncertainty_score":0.2434286,"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."}}