Progression of chronic kidney disease in African American with type 2 diabetes mellitus using topology learning in electronic medical records
Background: Chronic kidney disease (CKD) is a common, complex, and heterogeneous disease impacting aging populations. Determining the landscape of disease progression trajectories from midlife to senior age in a "real-world" context allows us to better understand the progression of CKD, the heterogeneity of progression patterns among the risk population, and the interactions with other clinical conditions. Genetics also plays an important role. In previous work, we and others have demonstrated that African Americans with high-risk APOL1 genotypes are more likely to develop CKD, tend to develop CKD earlier, and the disease progresses faster. Diabetes, which is more common in African Americans, also significantly increases risk for CKD. Data and Method: Electronic medical records (EMRs) were used to outline the first CKD progression trajectory roadmap for an African American population with type 2 diabetes. By linking participants in 5 genome-wide association study (GWAS) to their clinical records at Wake Forest Baptist Medical Center (WFBMC), an EMR-GWAS cohort was established (n = 1,581). Patients' health status was described by 18 Essential Clinical Indices across 84,009 clinical encounters. A novel graph learning algorithm, Discriminative Dimensionality Reduction Tree (DDRTree) was implemented, to establish the trajectories of declines in health. Moreover, a prediction model for new patients was proposed along the learned graph structure. We annotated these trajectories with clinical and genomic features including kidney function, other major risk indices of CKD, APOL1 genotypes, and age. The prediction power of the learned disease progression trajectories was further examined using the k-nearest neighbor model. Results: The CKD progression trajectory roadmap revealed diverse kidney failure pathways associated with different clinical conditions. Specifically, we identified one high-risk trajectory and two low-risk trajectories. Switching pathways from low-risk trajectories to the high-risk one was associated with accelerated decline in kidney function. On this roadmap, patients with APOL1 high-risk genotypes were enriched in the high-risk trajectory, suggesting fundamentally different disease progression mechanisms from those without APOL1 risk genotypes. The k-nearest neighbor-based prediction showed effective prediction rate of 87%. Conclusion: The CKD progression trajectory roadmap revealed novel diverse renal failure pathways in African Americans with type 2 diabetes mellitus and highlights disease progression patterns that associate with APOL1 renal-risk genotypes.
- Downloaded 409 times
- Download rankings, all-time:
- Site-wide: 58,503
- In bioinformatics: 5,903
- Year to date:
- Site-wide: 76,378
- Since beginning of last month:
- Site-wide: 92,749
Downloads over time
Distribution of downloads per paper, site-wide
- 27 Nov 2020: The website and API now include results pulled from medRxiv as well as bioRxiv.
- 18 Dec 2019: We're pleased to announce PanLingua, a new tool that enables you to search for machine-translated bioRxiv preprints using more than 100 different languages.
- 21 May 2019: PLOS Biology has published a community page about Rxivist.org and its design.
- 10 May 2019: The paper analyzing the Rxivist dataset has been published at eLife.
- 1 Mar 2019: We now have summary statistics about bioRxiv downloads and submissions.
- 8 Feb 2019: Data from Altmetric is now available on the Rxivist details page for every preprint. Look for the "donut" under the download metrics.
- 30 Jan 2019: preLights has featured the Rxivist preprint and written about our findings.
- 22 Jan 2019: Nature just published an article about Rxivist and our data.
- 13 Jan 2019: The Rxivist preprint is live!