Ishan Paranjpe, Xuan Wang, Nanditha Anandakrishnan, Jonathan C Haydak, Tielman Van Vleck, Stefanie DeFronzo, Zhengzhe Li, Anthony Mendoza, Ruijie Liu, Jia Fu, Iain Forrest, Weibin Zhou, Kyung Lee, Ross O'Hagan, Sergio Dellepiane, Kartikeya M Menon, Faris Gulamali, Samir Kamat, Gabriele Luca Gusella, Alexander W Charney, Ira Hofer, Judy H Cho, Ron Do, Benjamin S Glicksberg, John C He, Girish N Nadkarni, Evren U Azeloglu
Kidney disease affects 50% of all diabetic patients; however, prediction of disease progression has been challenging due to inherent disease heterogeneity. We use deep learning to identify novel genetic signatures prognostically associated with outcomes. Using autoencoders and unsupervised clustering of electronic health record data on 1,372 diabetic kidney disease patients, we establish two clusters with differential prevalence of end-stage kidney disease. Exome-wide associations identify a novel variant in ARHGEF18, a Rho guanine exchange factor specifically expressed in glomeruli...
September 7, 2023: medRxiv