<> <http://www.w3.org/2000/01/rdf-schema#comment> "The repository administrator has not yet configured an RDF license."^^<http://www.w3.org/2001/XMLSchema#string> .
<> <http://xmlns.com/foaf/0.1/primaryTopic> <https://discovery.ucl.ac.uk/id/eprint/10204427> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Thesis> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Article> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/dc/terms/title> "Machine learning and GPU-accelerated computing applied to platelet inventory management in a hospital blood bank"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/ontology/bibo/abstract> "Hospital blood banks must maintain an adequate stock of platelets and other blood\r\nproducts to ensure that patients can receive transfusions when needed, while trying\r\nto minimize wastage. Challenges include short product shelf lives, donor-recipient\r\ncompatibility, and the fact that some requested units may not be transfused.\r\nI used machine learning (ML) and graphics processing unit (GPU)-accelerated\r\ncomputing methods to find policies for two key decisions: how many platelet units\r\nto order from a supplier (replenishment) and selecting platelet units to meet demand\r\n(issuing).\r\nMy review of the literature identified opportunities to: use deep reinforcement\r\nlearning (DRL) to learn how to act in the large state spaces needed to represent\r\nperishable stock; use GPU hardware to compute the optimal replenishment policy\r\nfor larger, more realistic problems; and improve issuing policies which have\r\nreceived less attention than replenishment decisions.\r\nI first developed a novel reinforcement learning environment to model a\r\nsimple platelet replenishment problem. DRL policies performed near-optimally on\r\nsimulated data and outperformed commonly used heuristic policies on real demand\r\ntrajectories from a UK hospital.\r\nMy GPU-accelerated implementation of value iteration enabled the optimal\r\npolicy to be computed for perishable inventory management problems where this\r\nwas recently deemed infeasible or impractical, with up to 16.8M states, using\r\nconsumer-grade hardware. These results can support benchmarking approximate\r\napproaches including DRL.\r\nI designed a novel ML-guided issuing policy to address the fact that not all requested platelet units are transfused. I explored how the utility of the policy\r\ndepended on the quality of patient-level ML predictions of transfusion and trained\r\nan ML model, with AUROC 0.74, sufficiently good to support wastage reductions\r\nunder the new policy.\r\nFinally, I extended the problem to jointly optimize replenishment and issuing\r\npolicies to manage multiple perishable products with substitution, including\r\nplatelets with all eight ABO/RhD blood types."^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/dc/terms/date> "2025-02-28" .
<https://discovery.ucl.ac.uk/id/document/1825512> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Document> .
<https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Organization> .
<https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> <http://xmlns.com/foaf/0.1/name> "UCL (University College London)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/dc/terms/issuer> <https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> .
<https://discovery.ucl.ac.uk/id/org/ext-d065c602b22c642b4d5f4bee000f90fe> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Organization> .
<https://discovery.ucl.ac.uk/id/org/ext-d065c602b22c642b4d5f4bee000f90fe> <http://xmlns.com/foaf/0.1/name> "Institute of Health Informatics, UCL (University College London)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/org/ext-d065c602b22c642b4d5f4bee000f90fe> <http://purl.org/dc/terms/isPartOf> <https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/dc/terms/issuer> <https://discovery.ucl.ac.uk/id/org/ext-d065c602b22c642b4d5f4bee000f90fe> .
<https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/org/ext-d065c602b22c642b4d5f4bee000f90fe> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/ontology/bibo/status> <http://purl.org/ontology/bibo/status/unpublished> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-eb50fe77e95d2b589e509efc76f6663a> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10204427#authors> .
<https://discovery.ucl.ac.uk/id/eprint/10204427#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_1> <https://discovery.ucl.ac.uk/id/person/ext-eb50fe77e95d2b589e509efc76f6663a> .
<https://discovery.ucl.ac.uk/id/person/ext-eb50fe77e95d2b589e509efc76f6663a> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
<https://discovery.ucl.ac.uk/id/person/ext-eb50fe77e95d2b589e509efc76f6663a> <http://xmlns.com/foaf/0.1/givenName> "Joseph Marc"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-eb50fe77e95d2b589e509efc76f6663a> <http://xmlns.com/foaf/0.1/familyName> "Farrington"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-eb50fe77e95d2b589e509efc76f6663a> <http://xmlns.com/foaf/0.1/name> "Joseph Marc Farrington"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/EPrint> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/ThesisEPrint> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/dc/terms/isPartOf> <https://discovery.ucl.ac.uk/id/repository> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825512> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1825512> <http://www.w3.org/2000/01/rdf-schema#label> "Machine learning and GPU-accelerated computing applied to platelet inventory management in a hospital blood bank (Text)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://purl.org/dc/elements/1.1/hasVersion> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://eprints.org/ontology/hasAccepted> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825512> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10204427/1/Farrington_thesis.pdf> .
<https://discovery.ucl.ac.uk/id/document/1825512> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10204427/1/Farrington_thesis.pdf> .
<https://discovery.ucl.ac.uk/id/eprint/10204427/1/Farrington_thesis.pdf> <http://www.w3.org/2000/01/rdf-schema#label> "Farrington_thesis.pdf"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1825513> .
<https://discovery.ucl.ac.uk/id/document/1825513> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1825513> <http://www.w3.org/2000/01/rdf-schema#label> "Machine learning and GPU-accelerated computing applied to platelet inventory management in a hospital blood bank (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1825513> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825513> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825513> <http://eprints.org/relation/isIndexCodesVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825513> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10204427/2/indexcodes.txt> .
<https://discovery.ucl.ac.uk/id/document/1825513> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10204427/2/indexcodes.txt> .
<https://discovery.ucl.ac.uk/id/eprint/10204427/2/indexcodes.txt> <http://www.w3.org/2000/01/rdf-schema#label> "indexcodes.txt"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1825514> .
<https://discovery.ucl.ac.uk/id/document/1825514> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1825514> <http://www.w3.org/2000/01/rdf-schema#label> "Machine learning and GPU-accelerated computing applied to platelet inventory management in a hospital blood bank (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1825514> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825514> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825514> <http://eprints.org/relation/islightboxThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1825515> .
<https://discovery.ucl.ac.uk/id/document/1825515> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1825515> <http://www.w3.org/2000/01/rdf-schema#label> "Machine learning and GPU-accelerated computing applied to platelet inventory management in a hospital blood bank (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1825515> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825515> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825515> <http://eprints.org/relation/ispreviewThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1825516> .
<https://discovery.ucl.ac.uk/id/document/1825516> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1825516> <http://www.w3.org/2000/01/rdf-schema#label> "Machine learning and GPU-accelerated computing applied to platelet inventory management in a hospital blood bank (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1825516> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825516> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825516> <http://eprints.org/relation/ismediumThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1825517> .
<https://discovery.ucl.ac.uk/id/document/1825517> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1825517> <http://www.w3.org/2000/01/rdf-schema#label> "Machine learning and GPU-accelerated computing applied to platelet inventory management in a hospital blood bank (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1825517> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825517> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/document/1825517> <http://eprints.org/relation/issmallThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1825512> .
<https://discovery.ucl.ac.uk/id/eprint/10204427> <http://www.w3.org/2000/01/rdf-schema#seeAlso> <https://discovery.ucl.ac.uk/id/eprint/10204427/> .
<https://discovery.ucl.ac.uk/id/eprint/10204427/> <http://purl.org/dc/elements/1.1/title> "HTML Summary of #10204427 \n\nMachine learning and GPU-accelerated computing applied to platelet inventory management in a hospital blood bank\n\n" .
<https://discovery.ucl.ac.uk/id/eprint/10204427/> <http://purl.org/dc/elements/1.1/format> "text/html" .
<https://discovery.ucl.ac.uk/id/eprint/10204427/> <http://xmlns.com/foaf/0.1/primaryTopic> <https://discovery.ucl.ac.uk/id/eprint/10204427> .