{"id":"W2907434209","doi":"10.3174/ajnr.a5926","title":"A Deep Learning–Based Approach to Reduce Rescan and Recall Rates in Clinical MRI Examinations","year":2019,"lang":"en","type":"article","venue":"American Journal of Neuroradiology","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network","funders":"National Institutes of Health; Biomedical Engineering Department, University of Michigan; University of Michigan; U.S. Department of Health and Human Services","keywords":"Medicine; Stroke (engine); Deep learning; Recall; Reading (process); Test (biology); Series (stratigraphy); Magnetic resonance imaging; Nuclear medicine; Artificial intelligence; Radiology; Medical physics; Computer science; Cognitive psychology; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.002803329,0.0006312515,0.0005407652,0.001132522,0.0003253183,0.000628769,0.001212613,0.0008184962,0.001210668],"category_scores_gemma":[0.00889236,0.0004018103,0.0005290928,0.0006366319,0.000289713,0.0008023798,0.0009524781,0.0009562739,0.0003608533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001216776,"about_ca_system_score_gemma":0.001794865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008523593,"about_ca_topic_score_gemma":0.01289126,"domain_scores_codex":[0.9988826,0.0004248292,0.0001253153,0.0002050578,0.0002465246,0.0001157531],"domain_scores_gemma":[0.9954433,0.002449374,0.000559174,0.0004544292,0.0009552669,0.0001384062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008061545,0.0006438253,0.02927965,0.0001944843,0.0002297378,0.0002509081,0.0002072126,0.1379034,0.00721961,0.001182862,0.006243998,0.8158382],"study_design_scores_gemma":[0.00003846316,0.0002025617,0.008742745,0.00002569675,0.00006033994,0.0001860133,0.00003457849,0.9819974,0.005701852,0.001737963,0.00125247,0.00001982618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4501087,0.001662704,0.5391165,0.001413191,0.00009974815,0.0003036708,0.0008647409,0.003751679,0.002679051],"genre_scores_gemma":[0.8725982,0.000222101,0.1239085,0.0002866574,0.00006752439,0.0001445327,0.0009088137,0.00006566007,0.001797984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008523593,"threshold_uncertainty_score":0.01694793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03058357188087202,"score_gpt":0.3764862211284146,"score_spread":0.3459026492475426,"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."}}