Researchers at Columbia University Vagelos College of Physicians and Surgeons have developed an algorithm that automatically scours a patient’s electronic medical record for results of blood and urine tests and, using a mix of established equations and machine learning to process the data, can alert physicians to patients in the earliest stages of Chronic Kidney Disease.
Diagnosing chronic kidney disease often goes undetected until it causes irreversible damage. The new algorithm seeks to ensure chronic kidney disease is detected in its earliest stages.
In the study, the researchers said Chronic Kidney Disease (CKD) represents a slowly progressive disorder that is typically silent until late stages, but early intervention can significantly delay its progression.
“Identifying kidney disease early is of paramount importance because we have treatments that can slow disease progression before the damage becomes irreversible. Chronic kidney disease can cause multiple serious problems, including heart disease, anemia, or bone disease, and can lead to an early death, but its early stages are frequently under-recognized and undertreated,” said study leader Krzysztof Kiryluk, MD, associate professor of medicine at Columbia University Vagelos College of Physicians and Surgeons.
The study, which is titled “Medical records-based chronic kidney disease phenotype for clinical care and ‘big data’ observational and genetic studies” was released in April 2021.
The algorithm automatically trawls electronic medical records. It works as an experienced nephrologist. When tested using electronic health records of 451 patients, the algorithm correctly diagnosed kidney disease in 95 percent of patients with kidney disease identified by two experienced nephrologists and correctly ruled out kidney disease in 97% of healthy controls.
This algorithm can be used in different types of electronic health recording systems, including millions of patients, and can be easily incorporated into clinical decision support systems that assist physicians by suggesting appropriate stage-specific drugs. The algorithm can be easily updated if the criteria for diagnosing kidney disease change in the future and become freely available to other institutions.
However, the researchers said one drawback of the algorithm is that it depends on the availability of relevant blood and urine tests in the medical record. The blood test is fairly routine, but the urine test is underutilized in clinical practice.
Kiryluk said despite these limitations, the algorithmic diagnosis could enhance awareness of kidney disease, Kiryluk says, and, with earlier treatment, potentially reduce the number of people who lose kidney function.
A statement accompanying the research results explained that the reasons for underdiagnosis are complex. This is because people in the early stages of chronic kidney disease usually have no symptoms, and primary care physicians may prioritize more immediate patient complaints. Furthermore, two tests, one that measures a kidney-filtered metabolite in blood and another that measures leakage of protein in urine, are needed to detect asymptomatic kidney disease.
“The interpretation of these tests is not always straightforward. Many patient characteristics, including age, sex, body mass, or nutritional status, need to be considered, and this is frequently under-appreciated by primary care physicians,” said Kiryluk.
Research into treating CKD has gained traction in the past few years.
A University of Chicago biotech startup was in 2018 awarded a $2.3 million grant to speed up the development of a first-of-its-kind drug to prevent kidney stones. The grant, from the National Institutes of Health (NIH), was given to Oxalo Therapeutics,
It is estimated that approximately one in every eight American adults is believed to have chronic kidney disease. However, only 10 percent of people in the disease’s early stages are aware of their condition. Among those who already have severely reduced kidney function, only 40 percent are aware of their diagnosis.
High blood pressure and diabetes are the main causes of CKD. Almost half of the individuals with CKD also have diabetes or self-reported cardiovascular disease (CVD). Furthermore, more than 661,000 Americans have kidney failure.
Of these, says the National Institute of Diabetes and Digestive and Kidney Diseases 468,000 individuals are on dialysis, and roughly 193,000 live with a functioning kidney transplant.