Back to Search Start Over

Discovery of Novel Digital Biomarkers for Type 2 Diabetic Nephropathy Classification via Integration of Urinary Proteomics and Pathology.

Authors :
Lucarelli N
Yun D
Han D
Ginley B
Moon KC
Rosenberg AZ
Tomaszewski JE
Zee J
Jen KY
Han SS
Sarder P
Source :
MedRxiv : the preprint server for health sciences [medRxiv] 2023 May 03. Date of Electronic Publication: 2023 May 03.
Publication Year :
2023

Abstract

Background: The heterogeneous phenotype of diabetic nephropathy (DN) from type 2 diabetes complicates appropriate treatment approaches and outcome prediction. Kidney histology helps diagnose DN and predict its outcomes, and an artificial intelligence (AI)-based approach will maximize clinical utility of histopathological evaluation. Herein, we addressed whether AI-based integration of urine proteomics and image features improves DN classification and its outcome prediction, altogether augmenting and advancing pathology practice.<br />Methods: We studied whole slide images (WSIs) of periodic acid-Schiff-stained kidney biopsies from 56 DN patients with associated urinary proteomics data. We identified urinary proteins differentially expressed in patients who developed end-stage kidney disease (ESKD) within two years of biopsy. Extending our previously published human-AI-loop pipeline, six renal sub-compartments were computationally segmented from each WSI. Hand-engineered image features for glomeruli and tubules, and urinary protein measurements, were used as inputs to deep-learning frameworks to predict ESKD outcome. Differential expression was correlated with digital image features using the Spearman rank sum coefficient.<br />Results: A total of 45 urinary proteins were differentially detected in progressors, which was most predictive of ESKD ( AUC =0.95), while tubular and glomerular features were less predictive ( AUC =0.71 and AUC =0.63, respectively). Accordingly, a correlation map between canonical cell-type proteins, such as epidermal growth factor and secreted phosphoprotein 1, and AI-based image features was obtained, which supports previous pathobiological results.<br />Conclusions: Computational method-based integration of urinary and image biomarkers may improve the pathophysiological understanding of DN progression as well as carry clinical implications in histopathological evaluation.<br />Competing Interests: Disclosures The authors have no conflicts of interest to declare.

Details

Language :
English
Database :
MEDLINE
Journal :
MedRxiv : the preprint server for health sciences
Accession number :
37205413
Full Text :
https://doi.org/10.1101/2023.04.28.23289272