Predictive Models for Recurrent Membranous Nephropathy After Kidney Transplantation
Background. Recurrent membranous nephropathy (MN) posttransplantation affects 35% to 50% of kidney transplant recipients (KTRs) and accounts for 50% allograft loss 5 y after diagnosis. Predictive factors for recurrent MN may include HLA-D risk alleles, but other factors have not been explored with c...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer
2022-09-01
|
| Series: | Transplantation Direct |
| Online Access: | http://journals.lww.com/transplantationdirect/fulltext/10.1097/TXD.0000000000001357 |
| _version_ | 1828150421565210624 |
|---|---|
| author | Edmund Y. M. Chung, MD Katrina Blazek, BMedSci Armando Teixeira-Pinto, PhD Ankit Sharma, PhD Siah Kim, PhD Yingxin Lin, PhD Karen Keung, PhD Bhadran Bose, MBBS Lukas Kairaitis, PhD Hugh McCarthy, PhD Pierre Ronco, PhD Stephen I. Alexander, MD Germaine Wong, PhD |
| author_facet | Edmund Y. M. Chung, MD Katrina Blazek, BMedSci Armando Teixeira-Pinto, PhD Ankit Sharma, PhD Siah Kim, PhD Yingxin Lin, PhD Karen Keung, PhD Bhadran Bose, MBBS Lukas Kairaitis, PhD Hugh McCarthy, PhD Pierre Ronco, PhD Stephen I. Alexander, MD Germaine Wong, PhD |
| author_sort | Edmund Y. M. Chung, MD |
| collection | DOAJ |
| description | Background. Recurrent membranous nephropathy (MN) posttransplantation affects 35% to 50% of kidney transplant recipients (KTRs) and accounts for 50% allograft loss 5 y after diagnosis. Predictive factors for recurrent MN may include HLA-D risk alleles, but other factors have not been explored with certainty.
Methods. The Australian and New Zealand Dialysis and Transplant registry was used to develop 3 prediction models for recurrent MN (Group Least Absolute Shrinkage and Selection Operator [LASSO], penalized Cox regression, and random forest), which were tuned using tenfold cross-validation in a derivation cohort with complete HLA data. KTRs with MN but incomplete HLA data formed the validation cohort. Model performance was evaluated using area under the receiver operating characteristic curve (AUC-ROC).
Results. One hundred ninety-nine KTRs with MN were included, and 25 (13%) had recurrent MN (median follow-up 5.9 y). The AUC-ROCs for Group LASSO, penalized Cox regression, and random forest models were 0.85 (95% confidence interval, 0.76-0.94), 0.91 (0.85-0.96), and 0.62 (0.57-0.69), respectively, in the derivation cohort, with moderate agreement in selected variables between the models (55%-70%). In their validation cohorts, the AUC-ROCs for Group LASSO and penalized Cox regression were 0.60 (0.49-0.70) and 0.73 (0.59-0.86), respectively. Variables of importance chosen by all models included recipient HLA-A2, donor HLA-DR12, donor-recipient HLA-B65, and HLA-DR12 match.
Conclusions. A penalized Cox regression performed reasonably for predicting recurrent MN and was superior to Group LASSO and random forest models. These models highlighted the importance of donor-recipient HLA characteristics to recurrent MN, although validation in larger datasets is required. |
| first_indexed | 2024-04-11T21:44:16Z |
| format | Article |
| id | doaj.art-be8d4697ae2c4af78ad7b0e22122bbcc |
| institution | Directory Open Access Journal |
| issn | 2373-8731 |
| language | English |
| last_indexed | 2024-04-11T21:44:16Z |
| publishDate | 2022-09-01 |
| publisher | Wolters Kluwer |
| record_format | Article |
| series | Transplantation Direct |
| spelling | doaj.art-be8d4697ae2c4af78ad7b0e22122bbcc2022-12-22T04:01:29ZengWolters KluwerTransplantation Direct2373-87312022-09-0189e135710.1097/TXD.0000000000001357202209000-00005Predictive Models for Recurrent Membranous Nephropathy After Kidney TransplantationEdmund Y. M. Chung, MD0Katrina Blazek, BMedSci1Armando Teixeira-Pinto, PhD2Ankit Sharma, PhD3Siah Kim, PhD4Yingxin Lin, PhD5Karen Keung, PhD6Bhadran Bose, MBBS7Lukas Kairaitis, PhD8Hugh McCarthy, PhD9Pierre Ronco, PhD10Stephen I. Alexander, MD11Germaine Wong, PhD121 Centre for Kidney Research, The Children’s Hospital at Westmead, Westmead, NSW, Australia.2 School of Population Health, University of New South Wales, Kensington, NSW, Australia.3 School of Public Health, The University of Sydney, Camperdown, NSW, Australia.1 Centre for Kidney Research, The Children’s Hospital at Westmead, Westmead, NSW, Australia.1 Centre for Kidney Research, The Children’s Hospital at Westmead, Westmead, NSW, Australia.5 School of Mathematics and Statistics, The University of Sydney, Camperdown, NSW, Australia.6 Department of Renal Medicine, Prince of Wales Hospital, Randwick, NSW, Australia.7 Department of Renal Medicine, Nepean Hospital, Kingswood, NSW, Australia.8 Department of Renal Medicine, Blacktown Hospital, Blacktown, NSW, Australia.1 Centre for Kidney Research, The Children’s Hospital at Westmead, Westmead, NSW, Australia.10 Sorbonne Université, Université Pierre et Marie Curie, Paris, France.1 Centre for Kidney Research, The Children’s Hospital at Westmead, Westmead, NSW, Australia.1 Centre for Kidney Research, The Children’s Hospital at Westmead, Westmead, NSW, Australia.Background. Recurrent membranous nephropathy (MN) posttransplantation affects 35% to 50% of kidney transplant recipients (KTRs) and accounts for 50% allograft loss 5 y after diagnosis. Predictive factors for recurrent MN may include HLA-D risk alleles, but other factors have not been explored with certainty. Methods. The Australian and New Zealand Dialysis and Transplant registry was used to develop 3 prediction models for recurrent MN (Group Least Absolute Shrinkage and Selection Operator [LASSO], penalized Cox regression, and random forest), which were tuned using tenfold cross-validation in a derivation cohort with complete HLA data. KTRs with MN but incomplete HLA data formed the validation cohort. Model performance was evaluated using area under the receiver operating characteristic curve (AUC-ROC). Results. One hundred ninety-nine KTRs with MN were included, and 25 (13%) had recurrent MN (median follow-up 5.9 y). The AUC-ROCs for Group LASSO, penalized Cox regression, and random forest models were 0.85 (95% confidence interval, 0.76-0.94), 0.91 (0.85-0.96), and 0.62 (0.57-0.69), respectively, in the derivation cohort, with moderate agreement in selected variables between the models (55%-70%). In their validation cohorts, the AUC-ROCs for Group LASSO and penalized Cox regression were 0.60 (0.49-0.70) and 0.73 (0.59-0.86), respectively. Variables of importance chosen by all models included recipient HLA-A2, donor HLA-DR12, donor-recipient HLA-B65, and HLA-DR12 match. Conclusions. A penalized Cox regression performed reasonably for predicting recurrent MN and was superior to Group LASSO and random forest models. These models highlighted the importance of donor-recipient HLA characteristics to recurrent MN, although validation in larger datasets is required.http://journals.lww.com/transplantationdirect/fulltext/10.1097/TXD.0000000000001357 |
| spellingShingle | Edmund Y. M. Chung, MD Katrina Blazek, BMedSci Armando Teixeira-Pinto, PhD Ankit Sharma, PhD Siah Kim, PhD Yingxin Lin, PhD Karen Keung, PhD Bhadran Bose, MBBS Lukas Kairaitis, PhD Hugh McCarthy, PhD Pierre Ronco, PhD Stephen I. Alexander, MD Germaine Wong, PhD Predictive Models for Recurrent Membranous Nephropathy After Kidney Transplantation Transplantation Direct |
| title | Predictive Models for Recurrent Membranous Nephropathy After Kidney Transplantation |
| title_full | Predictive Models for Recurrent Membranous Nephropathy After Kidney Transplantation |
| title_fullStr | Predictive Models for Recurrent Membranous Nephropathy After Kidney Transplantation |
| title_full_unstemmed | Predictive Models for Recurrent Membranous Nephropathy After Kidney Transplantation |
| title_short | Predictive Models for Recurrent Membranous Nephropathy After Kidney Transplantation |
| title_sort | predictive models for recurrent membranous nephropathy after kidney transplantation |
| url | http://journals.lww.com/transplantationdirect/fulltext/10.1097/TXD.0000000000001357 |
| work_keys_str_mv | AT edmundymchungmd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT katrinablazekbmedsci predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT armandoteixeirapintophd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT ankitsharmaphd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT siahkimphd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT yingxinlinphd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT karenkeungphd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT bhadranbosembbs predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT lukaskairaitisphd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT hughmccarthyphd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT pierreroncophd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT stephenialexandermd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation AT germainewongphd predictivemodelsforrecurrentmembranousnephropathyafterkidneytransplantation |