Explainable artificial neural networks improve the performance of the Gender-Equity Model for liver Allocation (GEMA) to prioritize candidates for liver transplantation

Research areas:

• Uncategorized

Year:

2024

Type of Publication:

In Proceedings

Authors:

• Rodríguez-Perálvarez, M.
• Gómez-Orellana, Antonio Manuel
• Guijo-Rubio, David
• Gutiérrez, Pedro Antonio
• Majumdar, A.
• McCaughan, G.
• Taylor, R.
• Tsochatzis, E. A.
• Hervás-Martínez, César

Volume:

30

Book title:

ILTS Annual Congress 2024

Pages:

1-309

Month:

Septiembre

BibTex:

@conference{GEMA_FP21_2024, author = "M. Rodr{\'i}guez-Per{\'a}lvarez and Antonio Manuel G{\'o}mez-Orellana and David Guijo-Rubio and Pedro Antonio Guti{\'e}rrez and A. Majumdar and G. McCaughan and R. Taylor and E.A. Tsochatzis and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "Background: Current prioritization models for liver transplantation (LT) are hampered by their linear nature, which does not fully capture the severity of patients with extreme analytical values. Methods: Cohort study including adult patients who qualified for elective LT in the United Kingdom (2010-2020, model training and internal validation) and in two Australian institutions (1998-2020, external validation). The Gender-Equity model for Liver Allocation corrected by serum sodium (GEMA-Na) was compared with a shallow artificial neural network optimized by neuroevolution and hybridization (GEMA-AI) using the same input variables. The primary outcome was mortality or delisting for sickness within the first 90 days. Discrimination was assessed by Harrell’s c-statistic (Hc).", awards = "(JCR: 5.1)", booktitle = "ILTS Annual Congress 2024", comments = "(JCR: 5.1)", month = "Septiembre", note = "(JCR: 5.1)", pages = "1--309", title = "{E}xplainable artificial neural networks improve the performance of the {G}ender-{E}quity {M}odel for liver {A}llocation ({GEMA}) to prioritize candidates for liver transplantation", url = "journals.lww.com/lt/citation/2024/09001/ilts_annual_congress_2024_abstracts.1.aspx", volume = "30", year = "2024", }

Note:

(JCR: 5.1)

Abstract:

Background: Current prioritization models for liver transplantation (LT) are hampered by their linear nature, which does not fully capture the severity of patients with extreme analytical values. Methods: Cohort study including adult patients who qualified for elective LT in the United Kingdom (2010-2020, model training and internal validation) and in two Australian institutions (1998-2020, external validation). The Gender-Equity model for Liver Allocation corrected by serum sodium (GEMA-Na) was compared with a shallow artificial neural network optimized by neuroevolution and hybridization (GEMA-AI) using the same input variables. The primary outcome was mortality or delisting for sickness within the first 90 days. Discrimination was assessed by Harrell’s c-statistic (Hc).

Comments:

(JCR: 5.1)