A Computable Phenotype for Autosomal Dominant Polycystic Kidney Disease

Data driven approach to characterize rapid decline in autosomal dominant polycystic kidney disease

Autosomal dominant polycystic kidney disease (ADPKD) is a genetic kidney disease with high phenotypic variability. Furthering insights into patients' ADPKD progression could lead to earlier detection, management, and alter the course to end stage kidney disease (ESKD). We sought to identify patients with rapid decline (RD) in kidney function and to determine clinical factors associated with RD using a data-driven approach. A retrospective cohort study was performed among patients with incident ADPKD (1/1/2002-12/31/2018). Latent class mixed models were used to identify RD patients using differences in eGFR trajectories over time. Predictors of RD were selected based on agreements among feature selection methods, including logistic, regularized, and random forest modeling. The final model was built on the selected predictors and clinically relevant covariates. Among 1,744 patients with incident ADPKD, 125 (7%) were identified as RD. Feature selection included 42 clinical measurements for adaptation with multiple imputations; mean (SD) eGFR was 85.2 (47.3) and 72.9 (34.4) in the RD and non-RD groups, respectively. Multiple imputed datasets identified variables as important features to distinguish RD and non-RD groups with the final prediction model determined as a balance between area under the curve (AUC) and clinical relevance which included 6 predictors: age, sex, hypertension, cerebrovascular disease, hemoglobin, and proteinuria. Results showed 72%-sensitivity, 70%-specificity, 70%-accuracy, and 0.77-AUC in identifying RD. 5-year ESKD rates were 38% and 7% among RD and non-RD groups, respectively. Using real-world routine clinical data among patients with incident ADPKD, we observed that six variables highly predicted RD in kidney function.

US Veterans Administration Autosomal Dominant Polycystic Kidney Disease Cohort: Demographic, Comorbidity, and Key Laboratory Data Characteristics

Key Points

We built a cohort of 12,217 patients diagnosed with autosomal dominant polycystic kidney disease from 1999 to 2020 in the national Veteran Affairs electronic medical record system. We characterized the cohort on demographics, comorbidities, and key laboratory measurements.

Background

We used the largest integrated US healthcare system, the Veterans Health Administration, to establish a robust resource for demographic, longitudinal outcome, and predictive modeling studies in autosomal dominant polycystic kidney disease (ADPKD).

Methods

We built the ADPKD cohort by extracting the relevant electronic health record data from nationwide Veterans Health Administration database (years 1999–2020).

Results

We identified 12,217 patients diagnosed with ADPKD. By the end of the 20-year study period, 5342 patients with ADPKD were deceased, 1583 were alive but reached ESKD, and 4827 remained alive without ESKD. Most demographic characteristics of this ADPKD cohort resemble the total US veteran population. For example, 94% were male patients, 45% age 65 years or older, 85% non-Hispanic, and 66% white; however, 19% were Black/African Americans (versus 12% in the general veteran population; a relevant enrichment after considering age and sex distributions between races). The comorbidities overrepresented in the ADPKD cohort include hypertension (89% versus 50%), diabetes (32% versus 22%), depression (40% versus 10%), chronic obstructive pulmonary disease (30% versus 6%), and congestive heart failure (21% versus 1%). By contrast, obesity was underrepresented in veterans with ADPKD (30% versus 41%).

Conclusions

We established a large electronic medical record-based cohort of ADPKD veterans. Here, we provide initial analysis of its demographic, comorbidity, and key laboratory data.

Health Disparities in Kidney Failure Among Patients With Autosomal Dominant Polycystic Kidney Disease: A Cross-Sectional Study

Rationale & Objective

Understanding potential differences in patterns of kidney failure among patients with autosomal dominant polycystic kidney disease (ADPKD) may provide insights into improving disease management. We sought to characterize patients with ADPKD and kidney failure across different race/ethnicities.

Study Design

Cross-sectional study.

Setting & Participants

Kaiser Permanente Southern California members diagnosed with ADPKD between January1, 2002, and December 31, 2018.

Exposure

ADPKD.

Outcome

Kidney failure, dialysis, or receipt of kidney transplant.

Analytical Approach

Differences in characteristics by race/ethnicity were assessed using analysis of variance F test and χ² test. To compare the range and distribution of the average age at onset of kidney failure by race/ethnicity and sex, we used box plots and confidence intervals. Multivariable logistic regression was used to estimate OR for kidney transplant.

Results

Among 3,677 ADPKD patients, 1,027 (27.3%) had kidney failure. The kidney failure cohort was comprised of Black (n=138; 30.7%), White (n=496; 30.6%), Hispanic (n=306; 24.7%), and Asian (n=87; 23.6%) patients. Hispanic patients had the youngest mean age of kidney failure onset (50 years) compared to Black (56 years) and White (57 years) patients. Black (44.2%; OR, 0.72) and Hispanic (49.7%; OR, 0.65) patients had lower rates of kidney transplantation compared to White (53.8%) patients. Preemptive kidney transplantations occurred in 15.0% of patients.

Limitations

Retrospective study design and possible misclassification of ADPKD cases. Kidney function calculations were based on equations incorporating race, potentially overestimating kidney function in African Americans. The study was conducted within a single, integrated health care system in 1 geographic region and may not be generalizable to all ADPKD patients.

Conclusions

Among a large diverse ADPKD population, we observed racial/ethnic differences in rates of kidney failure, age of kidney failure onset, and rates of kidney transplantation. Our real-world ADPKD cohort provides insight into racial/ethnic variation in clinical features of disease and potential disparities in care, which may affect ADPKD outcomes.