Medical records-based chronic kidney disease phenotype for clinical care and "big data" observational and genetic studies

Renal-Cardiac Crosstalk in the Pathogenesis and Progression of Heart Failure

Chronic kidney disease (CKD) represents a global health issue with a high socioeconomic impact. Beyond a progressive decline of kidney function, patients with CKD are at increased risk of cardiovascular diseases, including heart failure (HF) and sudden cardiac death. HF in CKD can manifest both as HF with reduced ejection fraction and HF with preserved ejection fraction, with the latter further increasing in relative importance in the more advanced stages of CKD. Typical cardiac remodeling characteristics in uremic cardiomyopathy include left ventricular hypertrophy, myocardial fibrosis, cardiac electrical dysregulation, capillary rarefaction, and microvascular dysfunction, which are triggered by increased cardiac preload, cardiac afterload, and preload and afterload-independent factors. The pathophysiological mechanisms underlying cardiac remodeling in CKD are multifactorial and include neurohormonal activation (with increased activation of the renin-angiotensin-aldosterone system, the sympathetic nervous system, and mineralocorticoid receptor signaling), cardiac steroid activation, mitochondrial dysfunction, inflammation, innate immune activation, and oxidative stress. Furthermore, disturbances in cardiac metabolism and calcium homeostasis, macrovascular and microvascular dysfunction, increased cellular profibrotic responses, the accumulation of uremic retention solutes, and mineral and bone disorders also contribute to cardiovascular disease and HF in CKD. Here, we review the current knowledge of HF in CKD, including the clinical characteristics and pathophysiological mechanisms revealed in animal studies. We also elaborate on the detrimental impact of comorbidities of CKD on HF using hypertension as an example and discuss the clinical characteristics of hypertensive heart disease and the genetic predisposition. Overall, this review aims to increase the understanding of HF in CKD to support future research and clinical translational approaches for improved diagnosis and therapy of this vulnerable patient population.

Validation of an Algorithm to Identify End-Stage Kidney Disease in Electronic Health Records Data

RATIONALE & OBJECTIVES

Accurate ascertainment of end-stage kidney disease (ESKD) in electronic health records (EHRs) data is important for much epidemiological research. This study aimed to develop and validate an algorithm using diagnosis and procedure codes to identify patients with ESKD (treated with maintenance dialysis or kidney transplantation) in EHRs data.

STUDY DESIGN

Study of diagnostic algorithms.

SETTING & PARTICIPANTS

The development cohort included 559,615 patients treated at the Geisinger Health System (January 1996-June 2018). The validation cohort included 767,186 patients treated at New York University Langone Health System (January 2018-December 2020).

ALGORITHMS COMPARED

An algorithm developed using diagnosis and procedure codes compared to a nominal gold standard designation within the United States Renal Data System (USRDS) data. The performance of the algorithm was characterized by sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The dates of incident ESKD between the algorithm and USRDS were compared in a subset of cases.

OUTCOMES

ESKD (maintenance dialysis, prior recipient of a kidney transplant, or kidney transplantation surgery) cases.

RESULTS

In Geisinger, we developed the ESKD algorithm that identified 4,766 (0.85%) ESKD cases, while there were 5,155 (0.92%) ESKD cases reported by the USRDS. The sensitivity, specificity, PPV, and NPV of the algorithm were 73.9% (95% CI, 72.7-75.1%), 99.83% (99.82-99.84%), 79.9% (78.9-81.0%), and 99.76% (99.75-99.77%), respectively. When applying the algorithm to New York University Langone Health System data, the sensitivity, specificity, PPV, and NPV were 71.8% (95% CI, 70.7-73.0%), 99.95% (99.95-99.96%), 91.6% (90.8-92.4%), and 99.79 (99.78-99.80%), respectively. The median (interquartile range) difference between dates of incident ESKD (algorithms minus USRDS) were -3 (-21 to 83) days in Geisinger and 0 (-12 to 69) days in New York University Langone Health.

LIMITATIONS

Use of structured EHRs data only.

CONCLUSIONS

Algorithms combining diagnosis and procedure codes show high specificity and modest sensitivity for identifying patients with ESKD, providing a research tool to inform future EHR-based studies.

Identifying a cohort of hospitalized chronic kidney disease patients using electronic health records: lessons learnt and implications for future research and clinical practice guidelines

Background

Safe medication prescribing for hospitalized chronic kidney disease (CKD) patients is challenging. Leveraging electronic health records (EHRs) offers potential for decision support. A first step is to capture the CKD cohort through so called electronic phenotypes (e-phenotypes). However, available e-phenotypes, defined by logical rules applied to EHR data, lack consensus and are often inconsistently aligned with the Kidney Disease - Improving Global Outcomes (KDIGO) guideline for CKD (KDIGO-CKD). Therefore, local analyses and formalization efforts are essential to derive logical rules for CKD cohort selection.

Methods

We analyzed routinely collected EHR data from adults hospitalized at Amsterdam University Medical Centre (2018-23). Six logical rules were investigated: four derived from KDIGO-CKD (reduced glomerular filtration rate, albuminuria, kidney replacement therapy, and other markers of kidney damage) and two from published studies (diagnosis codes and medications).

Results

The study included 108 854 hospitalized patients. Extensive efforts were needed to formalize the clinical CKD definition from KDIGO-CKD and adapt it to EHR data, including selecting appropriate CKD diagnosis codes, medications, and computable criteria. Pooling six logical rules resulted in identifying 17 805 hospitalized CKD patients (16.4%), showcasing varying CKD patient counts per rule (with proportions ranging from 2.1% to 8.4%). Nonetheless, baseline characteristics across cohorts were comparable. Over one-third of patients identified by decreased eGFR or albuminuria/proteinuria measurements lacked a corresponding diagnosis code.

Conclusions

Deriving and formalizing six logical rules required close collaboration between nephrologists, EHR data experts, and medical informaticians. Our study provides groundwork towards a computer-interpretable CKD definition to standardize cohort capture in EHR-based studies.

Emerging role of genetics in kidney transplantation

The advent of more affordable genomic analytical pipelines has facilitated the expansion of genetic studies in kidney transplantation. Advances in genetic sequencing have allowed for a greater understanding of the genetic basis of chronic kidney disease, which has helped to guide transplant management and address issues related to living donation in specific disease settings. Recent efforts have shown significant effects of genetic ancestry and donor APOL1 risk genotypes in determining worse allograft outcomes and increased donation risks. Genetic studies in kidney transplantation outcomes have started to assess the effects of donor and recipient genetics in primary disease recurrence and transplant-related comorbidities, while genome-wide donor-recipient genetic incompatibilities have been shown to represent an important determinant of alloimmunity. Future large-scale comprehensive studies will shed light on the clinical utility of integrative genomics in the kidney transplantation setting.

The computerized algorithm for renal assessment improves diagnostic accuracy of renal impairment in hospitalized patients

In hospitalized patients, acute kidney injury (AKI) is an important adverse event associated with high mortality and medical costs. Accurate diagnosis and timely management of AKI are essential for improving the outcomes of in-hospital AKI, and delayed diagnosis or misdiagnosis hinders advancements in AKI care. To ameliorate this problem, several electronic AKI alert systems have been proposed but have shown inconsistent effects on AKI outcomes. Before electronic systems can improve AKI outcomes, it is important to confirm their diagnostic accuracy. The purposes of the present study were to establish an easy-to-construct computerized algorithm for the diagnosis of renal impairment and to test its accuracy. The present study retrospectively included 1551 patients hospitalized in Wanfang Hospital with serum creatinine (SCr) levels > 1.3 mg/dL. A computerized algorithm was constructed to identify AKI events and chronic kidney disease (CKD) in these patients. Previous SCr tests were reviewed to define baseline SCr levels. A SCr level increased > 1.5 times from baseline was defined as AKI. An estimated glomerular filtration rate (eGFR) of < 60 mL/min/1.73 m2 for > 90 days was defined as CKD. Discharge diagnoses made by the attending physicians were defined as "clinician's diagnoses." The researcher's diagnoses, made by experienced nephrologists according to the same criteria, were the gold standard to which the computerized algorithms and the clinician's diagnoses were compared. The diagnoses made by the computerized algorithm and clinician were compared with the researcher's diagnoses to define their accuracy. Among the included patients, the mean age was 73.0 years; in-hospital mortality was 14.8%, and AKI was present in 28.6% of patients. Regarding the diagnostic accuracy for AKI, the computerized algorithm achieved a sensitivity of 85.6% and a specificity of 98.8%. The main cause of false-negative (FN) AKI diagnosis was AKI occurring prior to the outpatient visit, before the indexed hospitalization. Regarding the diagnostic accuracy for CKD, the computerized algorithm achieved a sensitivity of 94.7% and specificity of 100%. The main cause of FN CKD diagnosis was the lack of previous eGFR records. The computerized algorithm exhibited significantly superior accuracy compared to the clinician's diagnoses for both AKI (95.0% vs. 57.0%) and CKD (96.5% vs. 73.6%). We developed a simple and easy-to-construct computerized algorithm for the diagnosis of renal impairment that demonstrated significantly improved diagnostic accuracy for AKI and CKD compared to that of clinicians. In the future, an algorithmic approach for the differential diagnosis of AKI and a decision guide should be incorporated into this system.

GWAS highlights the neuronal contribution to multiple sclerosis susceptibility

Multiple Sclerosis (MS) is a chronic inflammatory and neurodegenerative disease affecting the brain and spinal cord. Genetic studies have identified many risk loci, that were thought to primarily impact immune cells and microglia. Here, we performed a multi-ancestry genome-wide association study with 20,831 MS and 729,220 control participants, identifying 236 susceptibility variants outside the Major Histocompatibility Complex, including four novel loci. We derived a polygenic score for MS and, optimized for European ancestry, it is informative for African-American and Latino participants. Integrating single-cell data from blood and brain tissue, we identified 76 genes affected by MS risk variants. Notably, while T cells showed the strongest enrichment, inhibitory neurons emerged as a key cell type. The expression of IL7 and STAT3 are affected only in inhibitory neurons, highlighting the importance of neuronal and glial dysfunction in MS susceptibility.

Polygenic scores and their applications in kidney disease

Genome-wide association studies (GWAS) have uncovered thousands of risk variants that individually have small effects on the risk of human diseases, including chronic kidney disease, type 2 diabetes, heart diseases and inflammatory disorders, but cumulatively explain a substantial fraction of disease risk, underscoring the complexity and pervasive polygenicity of common disorders. This complexity poses unique challenges to the clinical translation of GWAS findings. Polygenic scores combine small effects of individual GWAS risk variants across the genome to improve personalized risk prediction. Several polygenic scores have now been developed that exhibit sufficiently large effects to be considered clinically actionable. However, their clinical use is limited by their partial transferability across ancestries and a lack of validated models that combine polygenic, monogenic, family history and clinical risk factors. Moreover, prospective studies are still needed to demonstrate the clinical utility and cost-effectiveness of polygenic scores in clinical practice. Here, we discuss evolving methods for developing polygenic scores, best practices for validating and reporting their performance, and the study designs that will empower their clinical implementation. We specifically focus on the polygenic scores relevant to nephrology and other chronic, complex diseases and review their key limitations, necessary refinements and potential clinical applications.

GWAS highlights the neuronal contribution to multiple sclerosis susceptibility

Multiple Sclerosis (MS) is a chronic inflammatory and neurodegenerative disease affecting the brain and spinal cord. Genetic studies have identified many risk loci, that were thought to primarily impact immune cells and microglia. Here, we performed a multi-ancestry genome-wide association study with 20,831 MS and 729,220 control participants, identifying 236 susceptibility variants outside the Major Histocompatibility Complex, including four novel loci. We derived a polygenic score for MS and, optimized for European ancestry, it is informative for African-American and Latino participants. Integrating single-cell data from blood and brain tissue, we identified 76 genes affected by MS risk variants. Notably, while T cells showed the strongest enrichment, inhibitory neurons emerged as a key cell type, highlighting the importance of neuronal and glial dysfunction in MS susceptibility.

A novel method leveraging time series data to improve subphenotyping and application in critically ill patients with COVID-19

Computational subphenotyping, a data-driven approach to understanding disease subtypes, is a prominent topic in medical research. Numerous ongoing studies are dedicated to developing advanced computational subphenotyping methods for cross-sectional data. However, the potential of time-series data has been underexplored until now. Here, we propose a Multivariate Levenshtein Distance (MLD) that can account for address correlation in multiple discrete features over time-series data. Our algorithm has two distinct components: it integrates an optimal threshold score to enhance the sensitivity in discriminating between pairs of instances, and the MLD itself. We have applied the proposed distance metrics on the k-means clustering algorithm to derive temporal subphenotypes from time-series data of biomarkers and treatment administrations from 1039 critically ill patients with COVID-19 and compare its effectiveness to standard methods. In conclusion, the Multivariate Levenshtein Distance metric is a novel method to quantify the distance from multiple discrete features over time-series data and demonstrates superior clustering performance among competing time-series distance metrics.

Beyond the kidney biopsy: genomic approach to undetermined kidney diseases

Background

According to data from large national registries, almost 20%-25% of patients with end-stage kidney disease have an undetermined kidney disease (UKD). Recent data have shown that monogenic disease-causing variants are under-diagnosed. We performed exome sequencing (ES) on UKD patients in our center to improve the diagnosis rate.

Methods

ES was proposed in routine practice for patients with UKD including kidney biopsy from January 2019 to December 2021. Mutations were detected using a targeted bioinformatic customized kidney gene panel (675 genes). The pathogenicity was assessed using American College of Medical Genetics guidelines.

Results

We included 230 adult patients, median age 47.5 years. Consanguinity was reported by 25 patients. A family history of kidney disease was documented in 115 patients (50%). Kidney biopsies were either inconclusive in 69 patients (30.1%) or impossible in 71 (30.9%). We detected 28 monogenic renal disorders in 75 (32.6%) patients. Collagenopathies was the most common genetic kidney diagnosis (46.7%), with COL4A3 and COL4A4 accounting for 80% of these diagnoses. Tubulopathies (16%) and ciliopathies (14.7%) yielded, respectively, the second and third genetic kidney diagnosis category and UMOD-associated nephropathy as the main genetic findings for tubulopathies (7/11). Ten of the 22 patients having ES "first" eventually received a positive diagnosis, thereby avoiding 11 biopsies. Among the 44 patients with glomerular, tubulo-interstitial or vascular nephropathy, 13 (29.5%) were phenocopies. The diagnostic yield of ES was higher in female patients (P = .02) and in patients with a family history of kidney disease (P < .0001), reaching 56.8% when the patient had both first- and second-degree family history of renal disease.

Conclusion

Genetic diagnosis has provided new clinical insights by clarifying or reclassifying kidney disease etiology in over a third of UKD patients. Exome "first" may have a significant positive diagnostic yield, thus avoiding invasive kidney biopsy; moreover, the diagnostic yield remains elevated even when biopsy is impossible or inconclusive. ES provides a clinical benefit for routine nephrological healthcare in patients with UKD.

Polygenic risk alters the penetrance of monogenic kidney disease

Chronic kidney disease (CKD) is determined by an interplay of monogenic, polygenic, and environmental risks. Autosomal dominant polycystic kidney disease (ADPKD) and COL4A-associated nephropathy (COL4A-AN) represent the most common forms of monogenic kidney diseases. These disorders have incomplete penetrance and variable expressivity, and we hypothesize that polygenic factors explain some of this variability. By combining SNP array, exome/genome sequence, and electronic health record data from the UK Biobank and All-of-Us cohorts, we demonstrate that the genome-wide polygenic score (GPS) significantly predicts CKD among ADPKD monogenic variant carriers. Compared to the middle tertile of the GPS for noncarriers, ADPKD variant carriers in the top tertile have a 54-fold increased risk of CKD, while ADPKD variant carriers in the bottom tertile have only a 3-fold increased risk of CKD. Similarly, the GPS significantly predicts CKD in COL4A-AN carriers. The carriers in the top tertile of the GPS have a 2.5-fold higher risk of CKD, while the risk for carriers in the bottom tertile is not different from the average population risk. These results suggest that accounting for polygenic risk improves risk stratification in monogenic kidney disease.

Electronic Phenotype for Advanced Chronic Kidney Disease in a Veteran Health Care System Clinical Database: Systems-Based Strategy for Model Development and Evaluation

BACKGROUND

Identifying advanced (stages 4 and 5) chronic kidney disease (CKD) cohorts in clinical databases is complicated and often unreliable. Accurately identifying these patients can allow targeting this population for their specialized clinical and research needs.

OBJECTIVE

This study was conducted as a system-based strategy to identify all prevalent Veterans with advanced CKD for subsequent enrollment in a clinical trial. We aimed to examine the prevalence and accuracy of conventionally used diagnosis codes and estimated glomerular filtration rate (eGFR)-based phenotypes for advanced CKD in an electronic health record (EHR) database. We sought to develop a pragmatic EHR phenotype capable of improving the real-time identification of advanced CKD cohorts in a regional Veterans health care system.

METHODS

Using the Veterans Affairs Informatics and Computing Infrastructure services, we extracted the source cohort of Veterans with advanced CKD based on a combination of the latest eGFR value ≤30 ml·min-1·1.73 m-2 or existing International Classification of Diseases (ICD)-10 diagnosis codes for advanced CKD (N18.4 and N18.5) in the last 12 months. We estimated the prevalence of advanced CKD using various prior published EHR phenotypes (ie, advanced CKD diagnosis codes, using the latest single eGFR <30 ml·min-1·1.73 m-2, utilizing two eGFR values) and our operational EHR phenotypes of a high-, intermediate-, and low-risk advanced CKD cohort. We evaluated the accuracy of these phenotypes by examining the likelihood of a sustained reduction of eGFR <30 ml·min-1·1.73 m-2 over a 6-month follow-up period.

RESULTS

Of the 133,756 active Veteran enrollees at North Florida/South Georgia Veterans Health System (NF/SG VHS), we identified a source cohort of 1759 Veterans with advanced nondialysis CKD. Among these, 1102 (62.9%) Veterans had diagnosis codes for advanced CKD; 1391(79.1%) had the index eGFR <30 ml·min-1·1.73 m-2; and 928 (52.7%), 480 (27.2%), and 315 (17.9%) Veterans had high-, intermediate-, and low-risk advanced CKD, respectively. The prevalence of advanced CKD among Veterans at NF/SG VHS varied between 1% and 1.5% depending on the EHR phenotype. At the 6-month follow-up, the probability of Veterans remaining in the advanced CKD stage was 65.3% in the group defined by the ICD-10 codes and 90% in the groups defined by eGFR values. Based on our phenotype, 94.2% of high-risk, 71% of intermediate-risk, and 16.1% of low-risk groups remained in the advanced CKD category.

CONCLUSIONS

While the prevalence of advanced CKD has limited variation between different EHR phenotypes, the accuracy can be improved by utilizing two eGFR values in a stratified manner. We report the development of a pragmatic EHR-based model to identify advanced CKD within a regional Veterans health care system in real time with a tiered approach that allows targeting the needs of the groups at risk of progression to end-stage kidney disease.

24-h Urinary Calcium Excretion and Renal Outcomes in Hospitalized Patients with and without Chronic Kidney Disease

This study investigated the impact of 24-h urinary calcium excretion (UCaE) on renal function decline in hospitalized patients with and without chronic kidney disease (CKD). This study enrolled 3815 CKD patients in stages 1-4 and 1133 non-CKD patients admitted to the First Center of the Chinese PLA General Hospital between January 2014 and July 2022. The primary outcome for CKD patients was a composite of CKD progression, defined as a 40% decline in estimated glomerular filtration rate (eGFR) or end-stage kidney disease. Annual eGFR change was the secondary outcome. For non-CKD patients, the primary outcome was an eGFR decline of ≥20% or CKD incidence, while annual eGFR change was the secondary outcome. The association between UCaE and kidney function decline was assessed using Cox proportional hazards and generalized linear models. Primary outcomes were observed in 813 CKD patients and 109 non-CKD patients over a median follow-up of 3.0 and 4.1 years, respectively. For CKD patients, every 1-mmol/d increase in UCaE was associated with a 15% decreased risk of CKD progression. The hazard ratio (HR) was 0.85, with a 95% confidence interval (CI) of 0.77-0.93. For non-CKD patients, the risk of renal function decline decreased by 11%. The multivariate models indicated that there was an annual decrease in eGFR in both CKD and non-CKD patients, with a reduction of 0.122 mL/min/1.73 m²/year (p < 0.001) and 0.046 mL/min/1.73 m²/year (p = 0.004), respectively, for every 1-mmol/d increase in UCaE. CKD experiences a decrease in 24-h UCaE as early as stage 1, with a significant decline in stage 4. CKD and non-CKD patients with lower UCaE levels are at an increased risk of renal decline, regardless of other variables.

Multiview Clustering to Identify Novel Kidney Donor Phenotypes for Assessing Graft Survival in Older Transplant Recipients

Key Points

An unsupervised machine learning clustering algorithm identified distinct deceased kidney donor phenotypes among older recipients. Recipients of certain donor phenotypes were at a relatively higher risk of all-cause graft loss even after accounting for recipient factors. The use of unsupervised clustering to support kidney allocation systems may be an important area for future study.

Background

Older transplant recipients are at a relatively increased risk of graft failure after transplantation, and some of this risk may relate to donor characteristics. Unsupervised clustering using machine learning may be a novel approach to identify donor phenotypes that may then be used to evaluate outcomes for older recipients. Using a cohort of older recipients, the purpose of this study was to (1 ) use unsupervised clustering to identify donor phenotypes and (2 ) determine the risk of death/graft failure for recipients of each donor phenotype.

Methods

We analyzed a nationally representative cohort of kidney transplant recipients aged 65 years or older captured using the Scientific Registry of Transplant Recipients between 2000 and 2017. Unsupervised clustering was used to generate phenotypes using donor characteristics inclusive of variables in the kidney donor risk index (KDRI). Cluster assignment was internally validated. Outcomes included all-cause graft failure (including mortality) and delayed graft function. Differences in the distribution of KDRI scores were also compared across the clusters. All-cause graft failure was compared for recipients of donor kidneys from each cluster using a multivariable Cox survival analysis.

Results

Overall, 23,558 donors were separated into five clusters. The area under the curve for internal validation of cluster assignment was 0.89. Recipients of donor kidneys from two clusters were found to be at high risk of all-cause graft failure relative to the lowest risk cluster (adjusted hazards ratio, 1.86; 95% confidence interval, 1.69 to 2.05 and 1.73; 95% confidence interval, 1.61 to 1.87). Only one of these high-risk clusters had high proportions of donors with established risk factors (i.e. , hypertension, diabetes). KDRI scores were similar for the highest and lowest risk clusters (1.40 [1.18–1.67] and 1.37 [1.15–1.65], respectively).

Conclusions

Unsupervised clustering can identify novel donor phenotypes comprising established donor characteristics that, in turn, may be associated with different risks of graft loss for older transplant recipients.

Polygenic risk affects the penetrance of monogenic kidney disease

Background

Chronic kidney disease (CKD) is a genetically complex disease determined by an interplay of monogenic, polygenic, and environmental risks. Most forms of monogenic kidney diseases have incomplete penetrance and variable expressivity. It is presently unknown if some of the variability in penetrance can be attributed to polygenic factors.

Methods

Using the UK Biobank (N=469,835 participants) and the All of Us (N=98,622 participants) datasets, we examined two most common forms of monogenic kidney disorders, autosomal dominant polycystic kidney disease (ADPKD) caused by deleterious variants in the PKD1 or PKD2 genes, and COL4A-associated nephropathy (COL4A-AN caused by deleterious variants in COL4A3, COL4A4, or COL4A5 genes). We used the eMERGE-III electronic CKD phenotype to define cases (estimated glomerular filtration rate (eGFR) <60 mL/min/1.73m2 or kidney failure) and controls (eGFR >90 mL/min/1.73m2 in the absence of kidney disease diagnoses). The effects of the genome-wide polygenic score (GPS) for CKD were tested in monogenic variant carriers and non-carriers using logistic regression controlling for age, sex, diabetes, and genetic ancestry.

Results

As expected, the carriers of known pathogenic and rare predicted loss-of-function variants in PKD1 or PKD2 had a high risk of CKD (ORmeta=17.1, 95% CI: 11.1-26.4, P=1.8E-37). The GPS was comparably predictive of CKD in both ADPKD variant carriers (ORmeta=2.28 per SD, 95%CI: 1.55-3.37, P=2.6E-05) and non-carriers (ORmeta=1.72 per SD, 95% CI=1.69-1.76, P< E-300) independent of age, sex, diabetes, and genetic ancestry. Compared to the middle tertile of the GPS distribution for non-carriers, ADPKD variant carriers in the top tertile had a 54-fold increased risk of CKD, while ADPKD variant carriers in the bottom tertile had only a 3-fold increased risk of CKD. Similarly, the GPS was predictive of CKD in both COL4-AN variant carriers (ORmeta=1.78, 95% CI=1.22-2.58, P=2.38E-03) and non-carriers (ORmeta=1.70, 95%CI: 1.68-1.73 P

Conclusions

Variable penetrance of kidney disease in ADPKD and COL4-AN is partially explained by differences in polygenic risk profiles. Accounting for polygenic factors has the potential to improve risk stratification in monogenic kidney disease and may have implications for genetic counseling.

Collapse

Key Words

• APOL1
• GWAS
• chronic kidney disease (CKD)
• polygenic risk score (PRS)

Collapse

MESH Headings Collapse

Grants

• OT2 OD026556 NIH HHS
• U2C OD023196 NIH HHS
• OT2 OD026551 NIH HHS
• U24 OD023121 NIH HHS
• OT2 OD026552 NIH HHS
• OT2 OD026549 NIH HHS
• OT2 OD025337 NIH HHS
• OT2 OD025277 NIH HHS
• OT2 OD026555 NIH HHS
• OT2 OD026550 NIH HHS
• OT2 OD026553 NIH HHS
• OT2 OD023205 NIH HHS
• U01 HG008680 NHGRI NIH HHS
• OT2 OD025276 NIH HHS
• OT2 OD026557 NIH HHS
• U24 OD023163 NIH HHS
• OT2 OD023206 NIH HHS
• R01 LM013061 NLM NIH HHS
• U24 OD023176 NIH HHS
• OT2 OD026548 NIH HHS
• OT2 OD025315 NIH HHS
• K25 DK128563 NIDDK NIH HHS
• OT2 OD026554 NIH HHS
• UL1 TR001873 NCATS NIH HHS

Collapse

Affiliation(s)

Atlas Khan Division of Nephrology, Dept of Medicine, Vagelos College of Physicians & Surgeons, Columbia University, New York, NY
Ning Shang Division of Nephrology, Dept of Medicine, Vagelos College of Physicians & Surgeons, Columbia University, New York, NY
Jordan G. Nestor Division of Nephrology, Dept of Medicine, Vagelos College of Physicians & Surgeons, Columbia University, New York, NY
Chunhua Weng Department of Biomedical Informatics, Vagelos College of Physicians & Surgeons, Columbia University, New York, NY, USA
George Hripcsak Department of Biomedical Informatics, Vagelos College of Physicians & Surgeons, Columbia University, New York, NY, USA
Peter C. Harris Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota 55905, USA
Ali G. Gharavi Division of Nephrology, Dept of Medicine, Vagelos College of Physicians & Surgeons, Columbia University, New York, NY
Krzysztof Kiryluk Division of Nephrology, Dept of Medicine, Vagelos College of Physicians & Surgeons, Columbia University, New York, NY

Collapse

Collaborators Collapse

Use of Computation Ecosystems to Analyze the Kidney-Heart Crosstalk

The identification of mediators for physiologic processes, correlation of molecular processes, or even pathophysiological processes within a single organ such as the kidney or heart has been extensively studied to answer specific research questions using organ-centered approaches in the past 50 years. However, it has become evident that these approaches do not adequately complement each other and display a distorted single-disease progression, lacking holistic multilevel/multidimensional correlations. Holistic approaches have become increasingly significant in understanding and uncovering high dimensional interactions and molecular overlaps between different organ systems in the pathophysiology of multimorbid and systemic diseases like cardiorenal syndrome because of pathological heart-kidney crosstalk. Holistic approaches to unraveling multimorbid diseases are based on the integration, merging, and correlation of extensive, heterogeneous, and multidimensional data from different data sources, both -omics and nonomics databases. These approaches aimed at generating viable and translatable disease models using mathematical, statistical, and computational tools, thereby creating first computational ecosystems. As part of these computational ecosystems, systems medicine solutions focus on the analysis of -omics data in single-organ diseases. However, the data-scientific requirements to address the complexity of multimodality and multimorbidity reach far beyond what is currently available and require multiphased and cross-sectional approaches. These approaches break down complexity into small and comprehensible challenges. Such holistic computational ecosystems encompass data, methods, processes, and interdisciplinary knowledge to manage the complexity of multiorgan crosstalk. Therefore, this review summarizes the current knowledge of kidney-heart crosstalk, along with methods and opportunities that arise from the novel application of computational ecosystems providing a holistic analysis on the example of kidney-heart crosstalk.

Big Data in Chronic Kidney Disease: Evolution or Revolution?

Digital information storage capacity and biomedical technology advancements in recent decades have stimulated the maturity and popularization of “big data” in medicine. The value of utilizing big data as a diagnostic and prognostic tool has continued to rise given its potential to provide accurate and insightful predictions of future health events and probable outcomes for individuals and populations, which may aid early identification of disease and timely treatment interventions. Whilst the implementation of big data methods for this purpose is more well-established in specialties such as oncology, cardiology, ophthalmology, and dermatology, big data use in nephrology and specifically chronic kidney disease (CKD) remains relatively novel at present. Nevertheless, increased efforts in the application of big data in CKD have been observed over recent years, with aims to achieve a more personalized approach to treatment for individuals and improved CKD screening strategies for the general population. Considering recent developments, we provide a focused perspective on the current state of big data and its application in CKD and nephrology, with hope that its ongoing evolution and revolution will gradually identify more solutions to improve strategies for CKD prevention and optimize the care of patients with CKD.

Predict, diagnose, and treat chronic kidney disease with machine learning: a systematic literature review

OBJECTIVES

In this systematic review we aimed at assessing how artificial intelligence (AI), including machine learning (ML) techniques have been deployed to predict, diagnose, and treat chronic kidney disease (CKD). We systematically reviewed the available evidence on these innovative techniques to improve CKD diagnosis and patient management.

METHODS

We included English language studies retrieved from PubMed. The review is therefore to be classified as a "rapid review", since it includes one database only, and has language restrictions; the novelty and importance of the issue make missing relevant papers unlikely. We extracted 16 variables, including: main aim, studied population, data source, sample size, problem type (regression, classification), predictors used, and performance metrics. We followed the Preferred Reporting Items for Systematic Reviews (PRISMA) approach; all main steps were done in duplicate.

RESULTS

From a total of 648 studies initially retrieved, 68 articles met the inclusion criteria. Models, as reported by authors, performed well, but the reported metrics were not homogeneous across articles and therefore direct comparison was not feasible. The most common aim was prediction of prognosis, followed by diagnosis of CKD. Algorithm generalizability, and testing on diverse populations was rarely taken into account. Furthermore, the clinical evaluation and validation of the models/algorithms was perused; only a fraction of the included studies, 6 out of 68, were performed in a clinical context.

CONCLUSIONS

Machine learning is a promising tool for the prediction of risk, diagnosis, and therapy management for CKD patients. Nonetheless, future work is needed to address the interpretability, generalizability, and fairness of the models to ensure the safe application of such technologies in routine clinical practice.

Genetics of Kidney Disease: The Unexpected Role of Rare Disorders

Hundreds of different genetic causes of chronic kidney disease are now recognized, and while individually rare, taken together they are significant contributors to both adult and pediatric diseases. Traditional genetics approaches relied heavily on the identification of large families with multiple affected members and have been fundamental to the identification of genetic kidney diseases. With the increased utilization of massively parallel sequencing and improvements to genotype imputation, we can analyze rare variants in large cohorts of unrelated individuals, leading to personalized care for patients and significant research advancements. This review evaluates the contribution of rare disorders to patient care and the study of genetic kidney diseases and highlights key advancements that utilize new techniques to improve our ability to identify new gene-disease associations.

Integration of artificial intelligence and multi-omics in kidney diseases

Kidney disease is a leading cause of death worldwide. Currently, the diagnosis of kidney diseases and the grading of their severity are mainly based on clinical features, which do not reveal the underlying molecular pathways. More recent surge of ∼omics studies has greatly catalyzed disease research. The advent of artificial intelligence (AI) has opened the avenue for the efficient integration and interpretation of big datasets for discovering clinically actionable knowledge. This review discusses how AI and multi-omics can be applied and integrated, to offer opportunities to develop novel diagnostic and therapeutic means in kidney diseases. The combination of new technology and novel analysis pipelines can lead to breakthroughs in expanding our understanding of disease pathogenesis, shedding new light on biomarkers and disease classification, as well as providing possibilities of precise treatment.

Genetic regulation of serum IgA levels and susceptibility to common immune, infectious, kidney, and cardio-metabolic traits

Immunoglobulin A (IgA) mediates mucosal responses to food antigens and the intestinal microbiome and is involved in susceptibility to mucosal pathogens, celiac disease, inflammatory bowel disease, and IgA nephropathy. We performed a genome-wide association study of serum IgA levels in 41,263 individuals of diverse ancestries and identified 20 genome-wide significant loci, including 9 known and 11 novel loci. Co-localization analyses with expression QTLs prioritized candidate genes for 14 of 20 significant loci. Most loci encoded genes that produced immune defects and IgA abnormalities when genetically manipulated in mice. We also observed positive genetic correlations of serum IgA levels with IgA nephropathy, type 2 diabetes, and body mass index, and negative correlations with celiac disease, inflammatory bowel disease, and several infections. Mendelian randomization supported elevated serum IgA as a causal factor in IgA nephropathy. African ancestry was consistently associated with higher serum IgA levels and greater frequency of IgA-increasing alleles compared to other ancestries. Our findings provide novel insights into the genetic regulation of IgA levels and its potential role in human disease.

Which patients with CKD will benefit from genomic sequencing? Synthesizing progress to illuminate the future

PURPOSE OF REVIEW

This review will summarize and synthesize recent findings in regard to monogenic kidney disorders, including how that evidence is being translated into practice. It will add to existing key knowledge to provide context for clinicians in consolidating existing practice and approaches.

RECENT FINDINGS

Whilst there are long established factors, which indicate increased likelihood of identifying a monogenic cause for kidney disease, these can now be framed in terms of the identification of new genes, new indications for genomic testing and new evidence for clinical utility of genomic testing in nephrology. Further, inherent in the use of genomics in nephrology are key concepts including robust informed consent, variant interpretation and return of results. Recent findings of variants in genes related to complex or broader kidney phenotypes are emerging in addition to understanding of de novo variants. Phenocopy phenomena are indicating a more pragmatic use of broader gene panels whilst evidence is emerging of a role in unexplained kidney disease. Clinical utility is evolving but is being successfully demonstrated across multiple domains of outcome and practice.

SUMMARY

We provide an updated framework of evidence to guide application of genomic testing in chronic kidney disease (CKD), building upon existing principles and knowledge to indicate how the practice and implementation of this can be applied today. There are clearly established roles for genomic testing for some patients with CKD, largely those with suspected heritable forms, with these continuing to expand as new evidence emerges.

Development and validation of algorithms to identify patients with chronic kidney disease and related chronic diseases across the Northern Territory, Australia

BACKGROUND

Electronic health records can be used for population-wide identification and monitoring of disease. The Territory Kidney Care project developed algorithms to identify individuals with chronic kidney disease (CKD) and several commonly comorbid chronic diseases. This study aims to describe the development and validation of our algorithms for CKD, diabetes, hypertension, and cardiovascular disease. A secondary aim of the study was to describe data completeness of the Territory Kidney Care database.

METHODS

The Territory Kidney Care database consolidates electronic health records from multiple health services including public hospitals (n = 6) and primary care health services (> 60) across the Northern Territory, Australia. Using the database (n = 48,569) we selected a stratified random sample of patients (n = 288), which included individuals with mild to end-stage CKD. Diagnostic accuracy of the algorithms was tested against blinded manual chart reviews. Data completeness of the database was also described.

RESULTS

For CKD defined as CKD stage 1 or higher (eGFR of any level with albuminuria or persistent eGFR < 60 ml/min/1.732, including renal replacement therapy) overall algorithm sensitivity was 93% (95%CI 89 to 96%) and specificity was 73% (95%CI 64 to 82%). For CKD defined as CKD stage 3a or higher (eGFR < 60 ml/min/1.732) algorithm sensitivity and specificity were 93% and 97% respectively. Among the CKD 1 to 5 staging algorithms, the CKD stage 5 algorithm was most accurate with > 99% sensitivity and specificity. For related comorbidities - algorithm sensitivity and specificity results were 75% and 97% for diabetes; 85% and 88% for hypertension; and 79% and 96% for cardiovascular disease.

CONCLUSIONS

We developed and validated algorithms to identify CKD and related chronic diseases within electronic health records. Validation results showed that CKD algorithms have a high degree of diagnostic accuracy compared to traditional administrative codes. Our highly accurate algorithms present new opportunities in early kidney disease detection, monitoring, and epidemiological research.

Kidney disease progression and collider bias in GWAS

New genome-wide meta-analysis for longitudinal kidney function decline identified several genetic loci related to kidney disease progression. The study illustrated the complexity of modeling longitudinal traits in genome-wide association studies and highlighted the issue of a collider bias that can be introduced when a kidney disease progression phenotype is adjusted for baseline kidney function. Herein, we briefly outline the key findings of this study, their limitations, and implications for future studies.

Predicting Race And Ethnicity To Ensure Equitable Algorithms For Health Care Decision Making

Algorithms are currently used to assist in a wide array of health care decisions. Despite the general utility of these health care algorithms, there is growing recognition that they may lead to unintended racially discriminatory practices, raising concerns about the potential for algorithmic bias. An intuitive precaution against such bias is to remove race and ethnicity information as an input to health care algorithms, mimicking the idea of "race-blind" decisions. However, we argue that this approach is misguided. Knowledge, not ignorance, of race and ethnicity is necessary to combat algorithmic bias. When race and ethnicity are observed, many methodological approaches can be used to enforce equitable algorithmic performance. When race and ethnicity information is unavailable, which is often the case, imputing them can expand opportunities to not only identify and assess algorithmic bias but also combat it in both clinical and nonclinical settings. A valid imputation method, such as Bayesian Improved Surname Geocoding, can be applied to standard data collected by public and private payers and provider entities. We describe two applications in which imputation of race and ethnicity can help mitigate potential algorithmic biases: equitable disease screening algorithms using machine learning and equitable pay-for-performance incentives.

Phenome-Wide Association Study of UMOD Gene Variants and Differential Associations With Clinical Outcomes Across Populations in the Million Veteran Program a Multiethnic Biobank

Introduction

Common variants in the UMOD gene are considered an evolutionary adaptation against urinary tract infections (UTIs) and have been implicated in kidney stone formation, chronic kidney disease (CKD), and hypertension. However, differences in UMOD variant-phenotype associations across population groups are unclear.

Methods

We tested associations between UMOD/PDILT variants and up to 1528 clinical diagnosis codes mapped to phenotype groups in the Million Veteran Program (MVP), using published phenome-wide association study (PheWAS) methodology. Associations were tested using logistic regression adjusted for age, sex, and 10 principal components of ancestry. Bonferroni correction for multiple comparisons was applied.

Results

Among 648,593 veterans, mean (SD) age was 62 (14) years; 9% were female, 19% Black, and 8% Hispanic. In White patients, the rs4293393 UMOD risk variant associated with increased uromodulin was associated with increased odds of CKD (odds ratio [OR]: 1.22, 95% CI: 1.20-1.24, P = 5.90 × 10-111), end-stage kidney disease (OR: 1.17, 95% CI: 1.11-1.24, P = 2.40 × 10-09), and hypertension (OR: 1.03, 95% CI: 1.05-1.05, P = 2.11 × 10-06) and significantly lower odds of UTIs (OR: 0.94, 95% CI: 0.92-0.96, P = 1.21 × 10-10) and kidney calculus (OR: 0.85, 95% CI: 0.83-0.86, P = 4.27 × 10-69). Similar findings were observed across UMOD/PDILT variants. The rs77924615 PDILT variant had stronger associations with acute cystitis in White female (OR: 0.73, 95% CI: 0.59-0.91, P = 4.98 × 10-03) versus male (OR: 0.99, 95% CI: 0.89-1.11, P = 8.80 × 10-01) (P interaction = 0.01) patients. In Black patients, the rs77924615 PDILT variant was significantly associated with pyelonephritis (OR: 0.65, 95% CI: 0.54-0.79, P = 1.05 × 10-05), whereas associations with UMOD promoter variants were attenuated.

Conclusion

Robust associations were observed between UMOD/PDILT variants linked with increased uromodulin expression and lower odds of UTIs and calculus and increased odds of CKD and hypertension. However, these associations varied significantly across ancestry groups and sex.

Genome-wide polygenic score to predict chronic kidney disease across ancestries

Chronic kidney disease (CKD) is a common complex condition associated with high morbidity and mortality. Polygenic prediction could enhance CKD screening and prevention; however, this approach has not been optimized for ancestrally diverse populations. By combining APOL1 risk genotypes with genome-wide association studies (GWAS) of kidney function, we designed, optimized and validated a genome-wide polygenic score (GPS) for CKD. The new GPS was tested in 15 independent cohorts, including 3 cohorts of European ancestry (n = 97,050), 6 cohorts of African ancestry (n = 14,544), 4 cohorts of Asian ancestry (n = 8,625) and 2 admixed Latinx cohorts (n = 3,625). We demonstrated score transferability with reproducible performance across all tested cohorts. The top 2% of the GPS was associated with nearly threefold increased risk of CKD across ancestries. In African ancestry cohorts, the APOL1 risk genotype and polygenic component of the GPS had additive effects on the risk of CKD.

Harnessing the Full Potential of Multi-Omic Analyses to Advance the Study and Treatment of Chronic Kidney Disease

Chronic kidney disease (CKD) was the 12th leading cause of death globally in 2017 with the prevalence of CKD estimated at ~9%. Early detection and intervention for CKD may improve patient outcomes, but standard testing approaches even in developed countries do not facilitate identification of patients at high risk of developing CKD, nor those progressing to end-stage kidney disease (ESKD). Recent advances in CKD research are moving towards a more personalised approach for CKD. Heritability for CKD ranges from 30% to 75%, yet identified genetic risk factors account for only a small proportion of the inherited contribution to CKD. More in depth analysis of genomic sequencing data in large cohorts is revealing new genetic risk factors for common diagnoses of CKD and providing novel diagnoses for rare forms of CKD. Multi-omic approaches are now being harnessed to improve our understanding of CKD and explain some of the so-called 'missing heritability'. The most common omic analyses employed for CKD are genomics, epigenomics, transcriptomics, metabolomics, proteomics and phenomics. While each of these omics have been reviewed individually, considering integrated multi-omic analysis offers considerable scope to improve our understanding and treatment of CKD. This narrative review summarises current understanding of multi-omic research alongside recent experimental and analytical approaches, discusses current challenges and future perspectives, and offers new insights for CKD.

Invasive Versus Medical Management in Patients With Chronic Kidney Disease and Non-ST-Segment-Elevation Myocardial Infarction

Background The role of invasive management compared with medical management in patients with non-ST-segment-elevation myocardial infarction (NSTEMI) and advanced chronic kidney disease (CKD) is uncertain, given the increased risk of procedural complications in patients with CKD. We aimed to compare clinical outcomes of invasive management with medical management in patients with NSTEMI-CKD. Methods and Results We identified NSTEMI and CKD stages 3, 4, 5, and end-stage renal disease admissions using International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes from the Nationwide Readmission Database 2016 to 2018. Patients were stratified into invasive and medical management. Primary outcome was mortality (in-hospital and 6 months after discharge). Secondary outcomes were in-hospital postprocedural complications (acute kidney injury requiring dialysis, major bleeding) and postdischarge 6-month safety and major adverse cardiovascular events. Out of 141 052 patients with NSTEMI-CKD, 85 875 (60.9%) were treated with invasive management, whereas 55 177 (39.1%) patients were managed medically. In propensity-score matched cohorts, invasive strategy was associated with lower in-hospital (CKD 3: odds ratio [OR], 0.47 [95% CI, 0.43-0.51]; P<0.001; CKD 4: OR, 0.79 [95% CI, 0.69-0.89]; P<0.001; CKD 5: OR, 0.72 [95% CI, 0.49-1.06]; P=0.096; end-stage renal disease: OR, 0.51 [95% CI, 0.46-0.56]; P<0.001) and 6-month mortality. Invasive management was associated with higher in-hospital postprocedural complications but no difference in postdischarge safety outcomes. Invasive management was associated with a lower hazard of major adverse cardiovascular events at 6 months in all CKD groups compared with medical management. Conclusions Invasive management was associated with lower mortality and major adverse cardiovascular events but minimal increased in-hospital complications in patients with NSTEMI-CKD compared with medical management, suggesting patients with NSTEMI-CKD should be offered invasive management.

Genetics in chronic kidney disease: conclusions from a Kidney Disease: Improving Global Outcomes (KDIGO) Controversies Conference

Numerous genes for monogenic kidney diseases with classical patterns of inheritance, as well as genes for complex kidney diseases that manifest in combination with environmental factors, have been discovered. Genetic findings are increasingly used to inform clinical management of nephropathies, and have led to improved diagnostics, disease surveillance, choice of therapy, and family counseling. All of these steps rely on accurate interpretation of genetic data, which can be outpaced by current rates of data collection. In March of 2021, Kidney Diseases: Improving Global Outcomes (KDIGO) held a Controversies Conference on "Genetics in Chronic Kidney Disease (CKD)" to review the current state of understanding of monogenic and complex (polygenic) kidney diseases, processes for applying genetic findings in clinical medicine, and use of genomics for defining and stratifying CKD. Given the important contribution of genetic variants to CKD, practitioners with CKD patients are advised to "think genetic," which specifically involves obtaining a family history, collecting detailed information on age of CKD onset, performing clinical examination for extrarenal symptoms, and considering genetic testing. To improve the use of genetics in nephrology, meeting participants advised developing an advanced training or subspecialty track for nephrologists, crafting guidelines for testing and treatment, and educating patients, students, and practitioners. Key areas of future research, including clinical interpretation of genome variation, electronic phenotyping, global representation, kidney-specific molecular data, polygenic scores, translational epidemiology, and open data resources, were also identified.

Leveraging electronic health record data for clinical trial planning by assessing eligibility criteria's impact on patient count and safety

OBJECTIVE

To present an approach on using electronic health record (EHR) data that assesses how different eligibility criteria, either individually or in combination, can impact patient count and safety (exemplified by all-cause hospitalization risk) and further assist with criteria selection for prospective clinical trials.

MATERIALS AND METHODS

Trials in three disease domains - relapsed/refractory (r/r) lymphoma/leukemia; hepatitis C virus (HCV); stages 3 and 4 chronic kidney disease (CKD) - were analyzed as case studies for this approach. For each disease domain, criteria were identified and all criteria combinations were used to create EHR cohorts. Per combination, two values were derived: (1) number of eligible patients meeting the selected criteria; (2) hospitalization risk, measured as the hazard ratio between those that qualified and those that did not. From these values, k-means clustering was applied to derive which criteria combinations maximized patient counts but minimized hospitalization risk.

RESULTS

Criteria combinations that reduced hospitalization risk without substantial reductions on patient counts were as follows: for r/r lymphoma/leukemia (23 trials; 9 criteria; 623 patients), applying no infection and adequate absolute neutrophil count while forgoing no prior malignancy; for HCV (15; 7; 751), applying no human immunodeficiency virus and no hepatocellular carcinoma while forgoing no decompensated liver disease/cirrhosis; for CKD (10; 9; 23893), applying no congestive heart failure.

CONCLUSIONS

Within each disease domain, the more drastic effects were generally driven by a few criteria. Similar criteria across different disease domains introduce different changes. Although results are contingent on the trial sample and the EHR data used, this approach demonstrates how EHR data can inform the impact on safety and available patients when exploring different criteria combinations for designing clinical trials.

Early Detection of Pancreatic Cancer: Applying Artificial Intelligence to Electronic Health Records

ABSTRACT

The potential of artificial intelligence (AI) applied to clinical data from electronic health records (EHRs) to improve early detection for pancreatic and other cancers remains underexplored. The Kenner Family Research Fund, in collaboration with the Cancer Biomarker Research Group at the National Cancer Institute, organized the workshop entitled: "Early Detection of Pancreatic Cancer: Opportunities and Challenges in Utilizing Electronic Health Records (EHR)" in March 2021. The workshop included a select group of panelists with expertise in pancreatic cancer, EHR data mining, and AI-based modeling. This review article reflects the findings from the workshop and assesses the feasibility of AI-based data extraction and modeling applied to EHRs. It highlights the increasing role of data sharing networks and common data models in improving the secondary use of EHR data. Current efforts using EHR data for AI-based modeling to enhance early detection of pancreatic cancer show promise. Specific challenges (biology, limited data, standards, compatibility, legal, quality, AI chasm, incentives) are identified, with mitigation strategies summarized and next steps identified.

Quantitative disease risk scores from EHR with applications to clinical risk stratification and genetic studies

Labeling clinical data from electronic health records (EHR) in health systems requires extensive knowledge of human expert, and painstaking review by clinicians. Furthermore, existing phenotyping algorithms are not uniformly applied across large datasets and can suffer from inconsistencies in case definitions across different algorithms. We describe here quantitative disease risk scores based on almost unsupervised methods that require minimal input from clinicians, can be applied to large datasets, and alleviate some of the main weaknesses of existing phenotyping algorithms. We show applications to phenotypic data on approximately 100,000 individuals in eMERGE, and focus on several complex diseases, including Chronic Kidney Disease, Coronary Artery Disease, Type 2 Diabetes, Heart Failure, and a few others. We demonstrate that relative to existing approaches, the proposed methods have higher prediction accuracy, can better identify phenotypic features relevant to the disease under consideration, can perform better at clinical risk stratification, and can identify undiagnosed cases based on phenotypic features available in the EHR. Using genetic data from the eMERGE-seq panel that includes sequencing data for 109 genes on 21,363 individuals from multiple ethnicities, we also show how the new quantitative disease risk scores help improve the power of genetic association studies relative to the standard use of disease phenotypes. The results demonstrate the effectiveness of quantitative disease risk scores derived from rich phenotypic EHR databases to provide a more meaningful characterization of clinical risk for diseases of interest beyond the prevalent binary (case-control) classification.