EHRs And Disease Prediction
By Megan Williams, contributing writer
Much of the chatter around electronic health records (EHRs) revolves around efficiency and cost cutting in clinical practice. There is even a bit of discussion about the use of EHRS to improve population health. But is there more benefit to be found in individual patient health?
Perhaps the greatest potential of the EHR, (and the concept applied to a broader application, the EMR) lies in the role it can play in predicting clinical outcomes around a range of diseases and conditions.
This application is still very much in its fledgling stage, but here are just a few examples of how data analytics, when applied to EHRs in mindful ways, can bring about positive changes in patient health.
One of the most recent examples we saw came out of UC Davis. Researchers there found that, by compiling and analyzing routine information — blood pressure, respiratory rate, temperature, and white blood cell count — as pulled from EHRs, they were able to predict early stages of sepsis, a condition that is a leading cause of hospitalization and death in the U.S. It took them only three measures — lactate level, blood pressure, and respiratory rate — to calculate the likelihood that a patient would die from the condition.
As of March of this year, the research team was working on a specific, sepsis-risk algorithm that would automatically be calculated in the EHR.
Progressing Kidney Disease
Data from EHRs has also played a key role in predicting the need for dialysis after a patient with chronic kidney disease progresses into kidney failure.
The Journal Of The American Medical Association in 2011 studied patients who were referred to nephrologists between April 1, 2001, and December 31, 2008, in an effort to develop and validate predictive models for the progression of chronic kidney disease.
According to the study, “Our models use laboratory data that are obtained routinely in patients with CKD and could be easily integrated into a laboratory information system or a clinic EHR.” It also notes that emerging literature suggests that the methods lead to “improved patient outcomes with individualized risk prediction and with advances in information technology that allow for easy implementation of risk prediction models as components of EHRs.”
All data for the study where pulled from nephrology clinic EHRs. Researchers found the use of routinely obtained laboratory tests can accurately predict progression to kidney failure in patients with chronic kidney disease between stages three and five.
EHRs have also been used to improve cardiovascular risk prediction. A study (available from the National Institutes Of Health), analyzed whether internal EHR data (using flexible, adaptive statistical methods) could improve clinical risk prediction. The study used the fact that EHRs have been extensively implemented in the VA system as an opportunity for exploration.
It found that, “despite the EHR lacking some risk factors and its imperfect data quality, health care systems may be able to substantially improve risk prediction for their patients by using internally developed EHR-derived models and flexible statistical methodology.”
Another prevalent health issue in the U.S., hypertension, has seen researchers apply predictive analytics using EHR data to gain more insight into the disease. This study, from the Journal Of Informatics In Health And Biomedicine, sought to identify transition points at which hypertension is brought in, as well as pushed out of, control, through the use of EHR data.
The study of 1294 patients with hypertension (who were enrolled in a chronic disease management program at the Vanderbilt University Medical Center) found that accurate prediction of transition points from a control status could be achieved.
The most notable takeaway from all these examples is that in each one, EHRs were found to not only be a reliable and beneficial method in predicting patient outcomes, but that the analytics themselves were simple to perform and most likely easy to implement on a larger scale. These results spell opportunities for all solutions providers who work in using data analytics to bring improved results to their clients.