prikaz prve stranice dokumenta Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation
  Download
PDF 1.12 MB
Conference presentation
Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation
At: Transplantation 2023;107 Suppl 9:eP-251/ - The 2023 Joint International Congress of ILTS, ELITA & LICAGE. Rotterdam, Netherlands, 2023. https://doi.org/10.1097/01.tp.0000978836.44371.fe
Bezjak, Miran; Stresec, Ivan; Jadrijević, Stipislav; Kocman, Branislav; Filipec Kanižaj, Tajana; Antonijević, Miro; Dalbelo Bašić, Bojana; Mikulić, Danko

Cite this document

Bezjak, M., Stresec, I., Jadrijević, S., Kocman, B., Filipec Kanižaj, T., Antonijević, M. ... Mikulić, D. Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation [PowerPoint slides]. Retrieved from https://urn.nsk.hr/urn:nbn:hr:264:071472

Bezjak, Miran, et al. "Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation." Transplantation 2023;107 Suppl 9:eP-251/ - The 2023 Joint International Congress of ILTS, ELITA & LICAGE, 03.05.2023.-06.05.2023., Rotterdam, Netherlands. Presentation. https://urn.nsk.hr/urn:nbn:hr:264:071472

Bezjak, Miran, Ivan Stresec, Stipislav Jadrijević, Branislav Kocman, Tajana Filipec Kanižaj, Miro Antonijević, Bojana Dalbelo Bašić and Danko Mikulić. "Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation." Presentation at Transplantation 2023;107 Suppl 9:eP-251/ - The 2023 Joint International Congress of ILTS, ELITA & LICAGE, Rotterdam, Netherlands, 03.05.2023.-06.05.2023. https://urn.nsk.hr/urn:nbn:hr:264:071472

Bezjak, M., et al. 'Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation' [Presentation], Transplantation 2023;107 Suppl 9:eP-251/ - The 2023 Joint International Congress of ILTS, ELITA & LICAGE. 03.05.2023.-06.05.2023. Available at: https://urn.nsk.hr/urn:nbn:hr:264:071472

Bezjak M, Stresec I, Jadrijević S, Kocman B, Filipec Kanižaj T, Antonijević M, and sur.. Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation. [Presentation] [cited 2024 December 13] Available at: https://urn.nsk.hr/urn:nbn:hr:264:071472

M. Bezjak, et al., "Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation", presented at: Transplantation 2023;107 Suppl 9:eP-251/ - The 2023 Joint International Congress of ILTS, ELITA & LICAGE, Rotterdam, 03.05.2023.-06.05.2023. Available at: https://urn.nsk.hr/urn:nbn:hr:264:071472

Please login to the repository to save this object to your list.
Metadata
Title (english)Machine-learning-assisted donor-recipient matching for orthotopic liver transplantation
AuthorMiran Bezjak
AuthorIvan Stresec
AuthorStipislav Jadrijević
AuthorBranislav Kocman
AuthorTajana Filipec Kanižaj
AuthorMiro Antonijević
AuthorBojana Dalbelo Bašić
AuthorDanko Mikulić
Author's institution(Merkur University Hospital)
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Clinical Medical Sciences
Surgery
Abstract (english)
Liver transplant allocation policies evolve over time. With no universal algorithm to predict the outcome of liver transplantation allocation, donor-recipient matching still relies heavily on the experience of the transplant team. Machine learning models, using data collected on-site could offer more reliable and relevant ranking systems in comparison to traditional prognostic scores. 27 donor and recipient parameters were collected from 656 patients who underwent liver transplantation from March 2013 through December 2018 at the Merkur Clinical Hospital in Zagreb. We designed a machine learning survival ranking system, testing several different models: the regularized Cox regression, the random survival forest, gradient-boosted trees, and the support vector machine (SVM). The models were evaluated using nested cross-validation and interpreted using Shapley additive explanations (SHAP). We compared the performance of our various ranking systems and more traditional scores, namely BAR and ET-DRI. As a measure of comparison, we employed Uno’s concordance index estimator, which was appropriate for the high censorship rates in our data. Our best ranking system, based on gradient boosted trees, achieved an average concordance index of 65% on the data, outperforming traditional scores that achieved a maximum concordance index of only 53%. Random survival forests performed similarly to the gradient-boosted trees, while the regularized Cox and SVM models showed inferior ranking capability. Interpretation of the ranking systems yielded several relevant predictors of survival: donor CRP and sodium levels, liver steatosis, cold ischemia time, and recipient age. With machine learning, we can improve existing metrics by creating an interpretable ranking system that better fits our data. Such a system could potentially provide superior assistance in donor-recipient matching and identify risk factors in the process.
Keywords (english)
Languageenglish
Peer reviewPeer review - international
DOIhttps://doi.org/10.1097/01.tp.0000978836.44371.fe
URN:NBNurn:nbn:hr:264:071472
Presentation date2023-05-03
ConferenceTitle: Transplantation 2023;107 Suppl 9:eP-251/ - The 2023 Joint International Congress of ILTS, ELITA & LICAGE
Location: Rotterdam, Netherlands
Organizer: International Liver Transplantation Society (ILTS)
Organizer: The European Liver and Intestine Transplant Association (ELITA)
Organizer: The Liver Intensive Care Group of Europe (LICAGE)
Start date: 2023-05-03
End date: 2023-05-06
Assembly type: Lecture
Document URLhttps://ilts2023.abstractserver.com/program/#/details/presentations/447
Type of resourceText
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-02-23 09:29:42