{"id":"W4403152806","doi":"10.1182/bloodadvances.2024013756","title":"Novel machine learning technique further clarifies unrelated donor selection to optimize transplantation outcomes","year":2024,"lang":"en","type":"article","venue":"Blood Advances","topic":"Organ Transplantation Techniques and Outcomes","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Cancer Moonshot; National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; Office of Naval Research; Legend Biotech; Pharmacyclics; Takeda Oncology; Health Resources and Services Administration; National Institutes of Health; MorphoSys; Seagen; Astellas Pharma; Adaptive Biotechnologies; Pfizer; Incyte; Kiadis Pharma; bluebird bio; Medac; Jazz Pharmaceuticals; BeiGene; HistoGenetics; Atara Biotherapeutics; CareDx; Actinium Pharmaceuticals; National Cancer Institute; Gilead Sciences; Moonshot Research and Development Program; Sanofi; GlaxoSmithKline; CSL Behring; Bristol-Myers Squibb; AstraZeneca; Gateway for Cancer Research; Swedish Orphan Biovitrum; Omeros Corporation; Vertex Pharmaceuticals; Alexion Pharmaceuticals; Mallinckrodt Pharmaceuticals; Astellas Pharma US; Amgen; National Heart, Lung, and Blood Institute; Novartis Pharmaceuticals Corporation","keywords":"Selection (genetic algorithm); Transplantation; Computer science; Computational biology; Machine learning; Artificial intelligence; Medicine; Biology; Internal medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001813693,0.0002212607,0.0002915662,0.0002913955,0.00009565,0.00005491585,0.00006696736,0.000140346,0.0001835185],"category_scores_gemma":[0.00002964445,0.0001735671,0.0001197277,0.0004493335,0.00002681907,0.0002625919,0.000006937164,0.0003976993,0.00003526376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003141813,"about_ca_system_score_gemma":0.00004289934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006681411,"about_ca_topic_score_gemma":0.00005228475,"domain_scores_codex":[0.9988769,0.00003104692,0.0003091599,0.0003479964,0.0002130731,0.0002218559],"domain_scores_gemma":[0.9995865,0.0001128107,0.00004448384,0.0001027794,0.00005811941,0.00009533029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001122633,0.0007263077,0.2904011,0.005178025,0.0009463207,0.0004144218,0.004564875,0.003317092,0.6671844,0.003391742,0.0001486372,0.02260439],"study_design_scores_gemma":[0.0035168,0.001466797,0.05038833,0.001507889,0.001921743,0.001660611,0.0002648339,0.001431496,0.8949268,0.0004562805,0.04153532,0.0009231276],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08384412,0.004380703,0.89724,0.005990597,0.0004666723,0.00201389,0.0001139903,0.003626622,0.002323411],"genre_scores_gemma":[0.8161222,0.005733236,0.1725225,0.0006644826,0.0001222797,0.0002150657,0.000176633,0.00009325615,0.004350273],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7322781,"threshold_uncertainty_score":0.707786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009809484060171627,"score_gpt":0.2815315142204878,"score_spread":0.2717220301603162,"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."}}