Nanditha Anandakrishnan, Zhengzi Yi, Zeguo Sun, Tong Liu, Jonathan Haydak, Sean Eddy, Pushkala Jayaraman, Stefanie DeFronzo, Aparna Saha, Qian Sun, Dai Yang, Anthony Mendoza, Gohar Mosoyan, Huei Hsun Wen, Jennifer A Schaub, Jia Fu, Thomas Kehrer, Rajasree Menon, Edgar A Otto, Bradley Godfrey, Mayte Suarez-Farinas, Sean Leffters, Akosua Twumasi, Kristin Meliambro, Alexander W Charney, Adolfo García-Sastre, Kirk N Campbell, G Luca Gusella, John Cijiang He, Lisa Miorin, Girish N Nadkarni, Juan Wisnivesky, Hong Li, Matthias Kretzler, Steve G Coca, Lili Chan, Weijia Zhang, Evren U Azeloglu
COVID-19 has been a significant public health concern for the last four years; however, little is known about the mechanisms that lead to severe COVID-associated kidney injury. In this multicenter study, we combined quantitative deep urinary proteomics and machine learning to predict severe acute outcomes in hospitalized COVID-19 patients. Using a 10-fold cross-validated random forest algorithm, we identified a set of urinary proteins that demonstrated predictive power for both discovery and validation set with 87% and 79% accuracy, respectively...
March 19, 2024: medRxiv