{"id":"W3107993253","doi":"10.1016/j.transci.2020.103020","title":"Emerging use of machine learning and advanced technologies to assess red cell quality","year":2020,"lang":"en","type":"review","venue":"Transfusion and Apheresis Science","topic":"Blood transfusion and management","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; St. Michael's Hospital; Canadian Blood Services; University of Toronto; Toronto Metropolitan University; Ted Rogers Centre for Heart Research","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Adverse effect; Emerging technologies; Quality (philosophy); Transfusion medicine; Medicine; Blood product; Computer science; Blood transfusion; Machine learning; Intensive care medicine; Artificial intelligence; Pathology; Surgery; Internal medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005177812,0.0003071414,0.001234522,0.0003453555,0.0002277639,0.00005489259,0.0002041367,0.0001264242,0.00005794745],"category_scores_gemma":[0.0002061611,0.0002277005,0.0001446379,0.00134997,0.0003309872,0.0001350258,0.0001803374,0.0004027592,0.000002545913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002179227,"about_ca_system_score_gemma":0.0001133453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007634482,"about_ca_topic_score_gemma":0.00004194175,"domain_scores_codex":[0.9978371,0.00009158336,0.0005454452,0.0007586993,0.0004928685,0.000274256],"domain_scores_gemma":[0.9991463,0.0001364634,0.0001463429,0.0002734666,0.00007465274,0.0002228047],"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":[0.00004345995,0.00006009665,0.0000771758,0.008467433,0.00001665126,0.00001162056,0.0001431866,7.757735e-7,0.005490396,0.0001497803,0.00002384838,0.9855156],"study_design_scores_gemma":[0.0006151915,0.0002575449,0.0001297446,0.004396233,0.0004012468,0.00001166228,0.000482733,0.00006127747,0.001117506,0.000008407812,0.9922382,0.0002802886],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002561688,0.9916241,0.0009721796,0.00146585,0.00007757904,0.00160449,0.00002038643,0.0002463504,0.001427357],"genre_scores_gemma":[0.003194004,0.9915813,0.004652199,0.00007530563,0.00000621659,0.00002852116,0.000004521587,0.00002237597,0.0004355124],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9922143,"threshold_uncertainty_score":0.9285358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09492625935810785,"score_gpt":0.3793188531542798,"score_spread":0.2843925937961719,"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."}}