{"id":"W4401430643","doi":"10.1111/tme.13071","title":"The use of predictive modelling to determine the likelihood of donor return during the <scp>COVID</scp>‐19 pandemic","year":2024,"lang":"en","type":"article","venue":"Transfusion Medicine","topic":"Blood donation and transfusion practices","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Héma-Québec","funders":"","keywords":"Donation; Predictive modelling; Medicine; Coronavirus disease 2019 (COVID-19); Blood donor; Pandemic; Predictive value; Blood donations; Blood transfusion; Demography; Surgery; Computer science; Machine learning; Immunology; Internal medicine; Economics","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":[0.001725915,0.0002186499,0.0002782673,0.0002250821,0.000532247,0.0001306116,0.0004748309,0.00008004196,0.0001213169],"category_scores_gemma":[0.0006836975,0.00009682629,0.0001267813,0.00104846,0.0002605731,0.0007905221,0.00007349918,0.0004225307,0.00001457001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002040505,"about_ca_system_score_gemma":0.00005304105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001842243,"about_ca_topic_score_gemma":0.0008494678,"domain_scores_codex":[0.9979182,0.00007997571,0.0006774086,0.0003220213,0.0007239581,0.0002783647],"domain_scores_gemma":[0.9962475,0.002831528,0.000206066,0.0004263649,0.0002477582,0.00004081886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00361773,0.001298207,0.1433241,0.01118838,0.003045061,0.000211309,0.1028546,0.08651696,0.2814042,0.04329649,0.04449078,0.2787522],"study_design_scores_gemma":[0.003119377,0.0002334623,0.01245721,0.001586053,0.001531187,0.00005762062,0.008441893,0.2529345,0.001106255,0.003730883,0.7145765,0.000225101],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.953154,0.001848257,0.02842986,0.01277439,0.0008642689,0.001073498,0.0000134627,0.0001735792,0.001668632],"genre_scores_gemma":[0.9933226,0.003047257,0.00008286779,0.002161264,0.000698192,0.00004978177,0.000006900868,0.00003470516,0.0005964258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6700857,"threshold_uncertainty_score":0.4093668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05703402315369471,"score_gpt":0.2670238106987778,"score_spread":0.2099897875450831,"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."}}