Cargando…
Examination of alternative eGFR definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs
Deep learning (DL) models have shown promise in detecting chronic kidney disease (CKD) from fundus photographs. However, previous studies have utilized a serum creatinine-only estimated glomerular rate (eGFR) equation to measure kidney function despite the development of more up-to-date methods. In...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10688656/ https://www.ncbi.nlm.nih.gov/pubmed/38032977 http://dx.doi.org/10.1371/journal.pone.0295073 |
_version_ | 1785152208071819264 |
---|---|
author | An, Songyang Vaghefi, Ehsan Yang, Song Xie, Li Squirrell, David |
author_facet | An, Songyang Vaghefi, Ehsan Yang, Song Xie, Li Squirrell, David |
author_sort | An, Songyang |
collection | PubMed |
description | Deep learning (DL) models have shown promise in detecting chronic kidney disease (CKD) from fundus photographs. However, previous studies have utilized a serum creatinine-only estimated glomerular rate (eGFR) equation to measure kidney function despite the development of more up-to-date methods. In this study, we developed two sets of DL models using fundus images from the UK Biobank to ascertain the effects of using a creatinine and cystatin-C eGFR equation over the baseline creatinine-only eGFR equation on fundus image-based DL CKD predictors. Our results show that a creatinine and cystatin-C eGFR significantly improved classification performance over the baseline creatinine-only eGFR when the models were evaluated conventionally. However, these differences were no longer significant when the models were assessed on clinical labels based on ICD10. Furthermore, we also observed variations in model performance and systemic condition incidence between our study and the ones conducted previously. We hypothesize that limitations in existing eGFR equations and the paucity of retinal features uniquely indicative of CKD may contribute to these inconsistencies. These findings emphasize the need for developing more transparent models to facilitate a better understanding of the mechanisms underpinning the ability of DL models to detect CKD from fundus images. |
format | Online Article Text |
id | pubmed-10688656 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-106886562023-12-01 Examination of alternative eGFR definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs An, Songyang Vaghefi, Ehsan Yang, Song Xie, Li Squirrell, David PLoS One Research Article Deep learning (DL) models have shown promise in detecting chronic kidney disease (CKD) from fundus photographs. However, previous studies have utilized a serum creatinine-only estimated glomerular rate (eGFR) equation to measure kidney function despite the development of more up-to-date methods. In this study, we developed two sets of DL models using fundus images from the UK Biobank to ascertain the effects of using a creatinine and cystatin-C eGFR equation over the baseline creatinine-only eGFR equation on fundus image-based DL CKD predictors. Our results show that a creatinine and cystatin-C eGFR significantly improved classification performance over the baseline creatinine-only eGFR when the models were evaluated conventionally. However, these differences were no longer significant when the models were assessed on clinical labels based on ICD10. Furthermore, we also observed variations in model performance and systemic condition incidence between our study and the ones conducted previously. We hypothesize that limitations in existing eGFR equations and the paucity of retinal features uniquely indicative of CKD may contribute to these inconsistencies. These findings emphasize the need for developing more transparent models to facilitate a better understanding of the mechanisms underpinning the ability of DL models to detect CKD from fundus images. Public Library of Science 2023-11-30 /pmc/articles/PMC10688656/ /pubmed/38032977 http://dx.doi.org/10.1371/journal.pone.0295073 Text en © 2023 An et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article An, Songyang Vaghefi, Ehsan Yang, Song Xie, Li Squirrell, David Examination of alternative eGFR definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs |
title | Examination of alternative eGFR definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs |
title_full | Examination of alternative eGFR definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs |
title_fullStr | Examination of alternative eGFR definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs |
title_full_unstemmed | Examination of alternative eGFR definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs |
title_short | Examination of alternative eGFR definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs |
title_sort | examination of alternative egfr definitions on the performance of deep learning models for detection of chronic kidney disease from fundus photographs |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10688656/ https://www.ncbi.nlm.nih.gov/pubmed/38032977 http://dx.doi.org/10.1371/journal.pone.0295073 |
work_keys_str_mv | AT ansongyang examinationofalternativeegfrdefinitionsontheperformanceofdeeplearningmodelsfordetectionofchronickidneydiseasefromfundusphotographs AT vaghefiehsan examinationofalternativeegfrdefinitionsontheperformanceofdeeplearningmodelsfordetectionofchronickidneydiseasefromfundusphotographs AT yangsong examinationofalternativeegfrdefinitionsontheperformanceofdeeplearningmodelsfordetectionofchronickidneydiseasefromfundusphotographs AT xieli examinationofalternativeegfrdefinitionsontheperformanceofdeeplearningmodelsfordetectionofchronickidneydiseasefromfundusphotographs AT squirrelldavid examinationofalternativeegfrdefinitionsontheperformanceofdeeplearningmodelsfordetectionofchronickidneydiseasefromfundusphotographs |