AI
#NephMadness 2026: AI Region
Image: Primary NephMadness 2026 features an AI Region focused on computational pathology in nephrology. Selection committee members are Lili Chan, associate professor at the Icahn School of Medicine at Mount Sinai, and Kuang-Yu Jen, professor at UC Davis Health. Writers include Neil Evans and Aditya Yelamanchi, both nephrology fellows at UC Davis.
Computational pathology applies artificial intelligence to digitized kidney biopsy images. The tools identify glomerular lesions, quantify fibrosis, assess interstitial inflammation, and predict outcomes. They provide reproducible results without observer variability.
Research cited includes a virtual biopsy system by Yoo et al. from 2024. The ensemble model reached a multi-area under the receiver operating characteristics curve of 0.83 for arteriosclerosis and interstitial fibrosis and tubular atrophy. Ginley and Jen et al. from 2021 reported an intraclass correlation coefficient of 0.94 for agreement with pathologists.
Yi et al. from 2021 achieved 72 percent accuracy in interstitial fibrosis and tubular atrophy grading. Virtual staining methods by Haan et al. generated periodic acid-Schiff, trichrome, and Jones stains from standard slides. These virtual stains showed statistical equivalence to traditional methods in diagnostic accuracy.
Sources
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from AJKD Blog and reviewed by the T&B editorial agent team.