prikaz prve stranice dokumenta Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma
  Preuzmi
PDF 360.02 KB
Znanstveni rad - Izvorni znanstveni rad
Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma
Annals of Translational Medicine, 11 (2023), 10; 345. https://doi.org/10.21037/atm-22-6469
Bezjak, Miran; Kocman, Branislav; Jadrijević, Stipislav; Filipec Kanižaj, Tajana; Antonijević, Miro; Dalbelo Bašić, Bojana; Mikulić, Danko

Citiranost:
,

Institucijski repozitorij: Dr Med - digitalni repozitorij Medicinskog fakulteta Sveučilišta u Zagrebu

Citirajte ovaj rad

Bezjak, M., Kocman, B., Jadrijević, S., Filipec Kanižaj, T., Antonijević, M., Dalbelo Bašić, B. i Mikulić, D. (2023). Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma. Annals of Translational Medicine, 11. (10). doi: 10.21037/atm-22-6469

Bezjak, Miran, et al. "Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma." Annals of Translational Medicine, vol. 11, br. 10, 2023. https://doi.org/10.21037/atm-22-6469

Bezjak, Miran, Branislav Kocman, Stipislav Jadrijević, Tajana Filipec Kanižaj, Miro Antonijević, Bojana Dalbelo Bašić i Danko Mikulić. "Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma." Annals of Translational Medicine 11, br. 10 (2023). https://doi.org/10.21037/atm-22-6469

Bezjak, M., et al. (2023) 'Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma', Annals of Translational Medicine, 11(10). doi: 10.21037/atm-22-6469

Bezjak M, Kocman B, Jadrijević S, Filipec Kanižaj T, Antonijević M, Dalbelo Bašić B, i sur.. Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma. Annals of Translational Medicine [Internet]. 30.08.2023. [pristupljeno 28.04.2025.];11(10). doi: 10.21037/atm-22-6469

M. Bezjak, et al., "Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma", Annals of Translational Medicine, vol. 11, br. 10, Kolovoz 2023. [Online]. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:105:073729. [Citirano: 28.04.2025.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:105:073729
Podaci o radu
Naslov (engleski)Use of machine learning models for identification of predictors of survival and tumour recurrence in liver transplant recipients with hepatocellular carcinoma
AutorMiran Bezjak
AutorBranislav Kocman
AutorStipislav Jadrijević
AutorTajana Filipec Kanižaj
AutorMiro Antonijević
AutorBojana Dalbelo Bašić
AutorDanko Mikulić
Autorova ustanovaSveučilište u Zagrebu
Medicinski fakultet
(KATEDRA ZA INTERNU MEDICINU)
Znanstveno / umjetničko
područje, polje i grana		BIOMEDICINA I ZDRAVSTVO
Kliničke medicinske znanosti
Interna medicina
Sažetak (engleski)
Background: Hepatocellular carcinoma (HCC) is one of the leading indications for liver transplantation (LT) however, selection criteria remain controversial. We aimed to identify survival factors and predictors for tumour recurrence using machine learning (ML) methods. We also compared ML models to the Cox regression model. Methods: Thirty pretransplant donor and recipient general and tumour specific parameters were analysed from 170 patients who underwent orthotopic liver transplantation for... Više HCC between March 2013 and December 2019 at the University Hospital Merkur, Zagreb. Survival rates were calculated using the Kaplan-Meier method and multivariate analysis was performed using the Cox proportional hazards regression model. Data was also processed through Coxnet (a regularized Cox regression model), Random Survival Forest (RSF), Survival Support Vector Machine (SVM) and Survival Gradient Boosting models, which included pre-processing, variable selection, imputation of missing data, training and cross-validation of the models. The cross-validated concordance index (CI) was used as an evaluation metric and to determine the best performing model. Results: Kaplan-Meier curves for 5-year survival time showed survival probability of 80% for recipient survival and 82% for graft survival. The 5-year HCC recurrence was observed in 19% of patients. The best predictive accuracy was observed in the RSF model with CI of 0.72, followed by the Survival SVM model (CI 0.70). Overall ML models outperform the Cox regression model with respect to their limitations. Random Forest analysis provided several relevant outcome predictors: alpha fetoprotein (AFP), donor C-reactive protein (CRP), recipient age and neutrophil to lymphocyte ratio (NLR). Cox multivariate analysis showed similarities with RSF models in identifying detrimental variables. Some variables such as donor age and number of transarterial chemoembolization treatments (TACE) were pointed out, but these were not influential in our RSF model. Conclusions: Using ML methods in addition to classical statistical analysis, it is possible to develop sufficient prognostic models, which, compared to established risk scores, could help us quantify survival probability and make changes in organ utilization. Sakrij dio sažetka
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objaveObjavljen
Vrsta recenzijeRecenziran
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov časopisaAnnals of Translational Medicine
Brojčani podacivol. 11, br. 10, 345
p-ISSN2305-5839
e-ISSN2305-5847
DOIhttps://doi.org/10.21037/atm-22-6469
URN:NBNurn:nbn:hr:105:073729
Datum objave publikacije2023-08-30
URL dokumentahttps://atm.amegroups.com/article/view/115164/html
Vrsta resursaTekst
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Imenovanje-Nekomercijalno-Bez prerada 4.0 međunarodna (CC BY-NC-ND 4.0)
Datum i vrijeme pohrane2024-06-19 11:21:20
accessibility

closePristupačnostrefresh

Ako želite spremiti trajne postavke, kliknite Spremi, ako ne - vaše će se postavke poništiti kad zatvorite preglednik.