Advanced

Analysis of HLA-A, -B and -DR Alleles as Risk Factors for One-Year Mortality in Heart Transplants Using Artificial Neural Networks

Henning, Frieder LU (2017) FYTM03 20171
Department of Astronomy and Theoretical Physics
Computational Biology and Biological Physics
Abstract
The beneficial effects of HLA matching at the HLA-A, -B and -DR loci on recipient short- and long-term survival in heart transplants have been established in a number of studies. The objective of the present study was to evaluate the importance of individual HLA alleles at the HLA-A, -B and -DR loci as risk factors for recipient death within one year after transplant by using artificial neural networks.

Records of 24,838 heart transplants from the UNOS databased consisting of 19 risk variables which include the two recipient and donor HLA alleles at the study loci were analyzed by an ensemble of five multilayer perceptrons in a binary classification task. The importance of the classification variables as predictors was measured in a... (More)
The beneficial effects of HLA matching at the HLA-A, -B and -DR loci on recipient short- and long-term survival in heart transplants have been established in a number of studies. The objective of the present study was to evaluate the importance of individual HLA alleles at the HLA-A, -B and -DR loci as risk factors for recipient death within one year after transplant by using artificial neural networks.

Records of 24,838 heart transplants from the UNOS databased consisting of 19 risk variables which include the two recipient and donor HLA alleles at the study loci were analyzed by an ensemble of five multilayer perceptrons in a binary classification task. The importance of the classification variables as predictors was measured in a sensitivity analysis and odds ratios were calculated to identify risk factors for early death. The risk factor calculations for two alleles were validated in a Kaplan-Meier survival analysis. The influence of HLA matching on recipient one-year survival was analyzed in a sensitivity analysis and by risk factor calculations.

The donors HLA-A 23 and HLA-B 53 alleles were identified as risk factors for early death with odds ratios that were comparable to an increased ischemic time of one hour. The HLA-B 27 allele could be associated with decreased risk of early death. These alleles are important predictors to the network ensemble. In the survival analysis, the difference in the survival probabilities of two groups containing 100 transplants with donor HLA-A 23 and HLA-B 27 alleles each was significant ($P=0.0078$, Log-rank test).

At all loci, one mismatch and at the HLA-A and HLA-DR loci two mismatches were associated with a decreased risk of early death relative to no mismatches. At the HLA-B locus, two mismatches were associated with an increased risk of early death

The network ensemble was able to identify alleles as risk factors and the result was validated. The analysis on the influence of HLA matching gave results that were in conflict with previous studies. (Less)
Popular Abstract (Swedish)
Hjärttransplantationer syftar till att rädda liv men kan även vara riskabla ingrepp. Det är mycket som kan gå fel. Det transplanterade hjärtat lider stor risk att avstötas i mottagarens kropp, och en mer detaljerad kunskap om faktorerna som påverkar avstötning har således möjligheten att rädda liv.

Avstötning orsakas av att mottagarens immunförsvar känner av HLA-molekylerna, där HLA står för Human Leukocyte Antigen, på cellytorna hos det transplanterade hjärtat och tolkar dem som kroppsfrämmande. HLA-molekylerna delas in i två klasser och i varje klass ingår tre klassiska HLA molekyler. De klassiska HLA-molekylerna skiljer sig i sin form genom fysiska variationer, vilka har sitt ursprung i människans genuppsättning där HLA-molekylerna... (More)
Hjärttransplantationer syftar till att rädda liv men kan även vara riskabla ingrepp. Det är mycket som kan gå fel. Det transplanterade hjärtat lider stor risk att avstötas i mottagarens kropp, och en mer detaljerad kunskap om faktorerna som påverkar avstötning har således möjligheten att rädda liv.

Avstötning orsakas av att mottagarens immunförsvar känner av HLA-molekylerna, där HLA står för Human Leukocyte Antigen, på cellytorna hos det transplanterade hjärtat och tolkar dem som kroppsfrämmande. HLA-molekylerna delas in i två klasser och i varje klass ingår tre klassiska HLA molekyler. De klassiska HLA-molekylerna skiljer sig i sin form genom fysiska variationer, vilka har sitt ursprung i människans genuppsättning där HLA-molekylerna är kodade i HLA-komplexet. I HLA-komplexet motsvarar de olika HLA-molekylerna positioner, så kallade loci, och för varje locus finns ett antal genvarianter. Genvarianterna kallas alleler och en individ kan ha upp till tolv olika HLA-alleler.

Inom teorin för organavstötning spelar HLA-molekylerna en central roll. De positiva effekterna på mottagarens överlevnadstid efter en transplantation när mottagarens och donatorns HLA alleler matchar är allmänt vedertagna.

Det som i denna studie undersöks är om risken för avstötning inom ett år efter hjärttransplantationen ökar när vissa alleler förekommer hos antingen mottagaren eller donatorn. Detta innebär att data om hjärttransplantationer undersöks med en högre upplösning jämfört med tidigare studier.

I projektet utvärderas data från fler än tjugotusen hjärttransplantationer med hjälp av artificiella neurala nätverk som är en typ av artificiell intelligens. Artificiella neurala nätverk kan lära sig att sjävständigt känna igen mönster i data med många variabler och har därför blivit ett allt populärare verktyg inom dataanalys de senaste åren. (Less)
Please use this url to cite or link to this publication:
author
Henning, Frieder LU
supervisor
organization
course
FYTM03 20171
year
type
H2 - Master's Degree (Two Years)
subject
keywords
deep learning, HLA, heart transplant, risk factor, one-year mortality, artificial neural network
language
English
id
8921936
date added to LUP
2017-08-05 15:19:25
date last changed
2017-08-05 15:19:25
@misc{8921936,
  abstract     = {The beneficial effects of HLA matching at the HLA-A, -B and -DR loci on recipient short- and long-term survival in heart transplants have been established in a number of studies. The objective of the present study was to evaluate the importance of individual HLA alleles at the HLA-A, -B and -DR loci as risk factors for recipient death within one year after transplant by using artificial neural networks. 

Records of 24,838 heart transplants from the UNOS databased consisting of 19 risk variables which include the two recipient and donor HLA alleles at the study loci were analyzed by an ensemble of five multilayer perceptrons in a binary classification task. The importance of the classification variables as predictors was measured in a sensitivity analysis and odds ratios were calculated to identify risk factors for early death. The risk factor calculations for two alleles were validated in a Kaplan-Meier survival analysis. The influence of HLA matching on recipient one-year survival was analyzed in a sensitivity analysis and by risk factor calculations.

The donors HLA-A 23 and HLA-B 53 alleles were identified as risk factors for early death with odds ratios that were comparable to an increased ischemic time of one hour. The HLA-B 27 allele could be associated with decreased risk of early death. These alleles are important predictors to the network ensemble. In the survival analysis, the difference in the survival probabilities of two groups containing 100 transplants with donor HLA-A 23 and HLA-B 27 alleles each was significant ($P=0.0078$, Log-rank test). 

At all loci, one mismatch and at the HLA-A and HLA-DR loci two mismatches were associated with a decreased risk of early death relative to no mismatches. At the HLA-B locus, two mismatches were associated with an increased risk of early death

The network ensemble was able to identify alleles as risk factors and the result was validated. The analysis on the influence of HLA matching gave results that were in conflict with previous studies.},
  author       = {Henning, Frieder},
  keyword      = {deep learning,HLA,heart transplant,risk factor,one-year mortality,artificial neural network},
  language     = {eng},
  note         = {Student Paper},
  title        = {Analysis of HLA-A, -B and -DR Alleles as Risk Factors for One-Year Mortality in Heart Transplants Using Artificial Neural Networks},
  year         = {2017},
}