This article is more than 5 years old. Information may no longer be current.
EHR-based tool may accurately identify patients likely to have CKD
Click Here to Manage Email Alerts
A tool that used data from electronic health records accurately diagnosed chronic kidney disease in patients treated at five diverse health care organizations, according to a published study.
“A major barrier to appropriate CKD management is delayed identification of individuals with the disease,” Jenna M. Norton, of the National Kidney Disease Education Program at the NIH in Maryland, and colleagues wrote. “National estimates indicate that only 8% of people with CKD are aware of their condition. Because CKD is often asymptomatic in its early stages, it frequently goes undiagnosed until the disease is very advanced. An electronic CKD phenotype using data widely available in the electronic health record could facilitate identification of patients likely to have CKD.”
The tool was developed by a working group from the National Kidney Disease Education Program. CKD was said to be present if the most recent eGFR was less than 60 mL/min/1.73m2 and/or the most recent urine albumin-to-creatine ratio was at least 30 mg/g. In addition, patients must have had another eGFR less than 60 mL/min/1.73m2 and/or urine albumin-to-creatinine ratio at least 30 mg/g in more than 90 days before the most recent measurements.
The tool was implemented among 2,082,017 patients with varying ranges of CKD or ESKD and who received in- or out-patient care at five health care organizations that each used distinct EHR data. The time the organizations used the tool ranged from 20 to 223 hours.
For identifying CKD, researchers found the sensitivity, specificity and diagnostic accuracy of the tool were 99%, 99% and 98%, respectively.
For dialysis, sensitivity was 94% and specificity was 89%. For transplant, sensitivity was 97% and specificity was 91%.
“Individuals with CKD cannot be accurately identified from the EHR using diagnosis codes alone,” the researchers wrote. “Using laboratory data available in the EHR to automate identification of patients with CKD may facilitate population health management, surveillance and research. The NKDEP CKD e-phenotype provides a pragmatic and accurate method for EHR-based identification of patients likely to have CKD.”
In a related editorial, Sri Lekha Tummalapalli, MD, MBA, and Carmen A. Peralta, MD, MAS, both of the University of California, San Francisco, pointed out that the NKDEP e-phenotype is limited in its ability to accurately identify CKD status in all individuals with the condition. One reason they suggest for this is that, since the e-phenotype relies on data collected during routine clinical care, patients with CKD with inadequate access to care will be missed.
Still, they wrote, “The catalyst to change the current status quo of kidney care is here. The task of the next decade will be to design and implement interventions that improve CKD care in a reliable, efficient and scalable manner. The entire ecosystem of kidney health will benefit from efforts like those of the NKDEP group, and our community must continue the support of these important steps forward.” – by Melissa J. Webb
Disclosures: Norton reports no relevant financial disclosures. Please see the study for all other authors’ relevant financial disclosures.
Read more about
Click Here to Manage Email Alerts