April 22, 2024

UCalgary researchers can now predict kidney failure more accurately

New digital tool helps better inform treatment decisions for chronic kidney disease
Two people stand in a lab
Ping Liu (left) and Pietro Ravani Kyle Marr

A digital tool created by University of Calgary scientists, with international research partners, is poised to become the new standard for accurately predicting the risks of kidney failure and death in adults with moderate-to-severe kidney disease.

The research led by Cumming School of Medicine (CSM) clinician scientist Dr. Pietro Ravani, MD, PhD, and study first author Dr. Ping Liu, PhD, included teams from Canada, Denmark and Scotland. The study used health data from almost 100,000 patients with newly diagnosed chronic kidney disease (CKD) to develop a predictive algorithm and digital dashboard, known as KDpredict.

“We’ve been able to show that KDpredict is consistently more accurate in predicting the risks of kidney failure and death in adults with moderate-to-severe chronic kidney disease than the risk prediction model currently in use,” says Ravani. He says researchers have worked on the tool for the past three years, including consultations with individuals living with CKD.

KDpredict calculates one- to five-year risks of kidney failure and death in people with moderate to severe CKD, using four variables readily available in clinic practice. The variables include a person’s age, sex, estimated glomerular filtration rate (eGFR), a measure of kidney function, and a person’s albuminuria number, a protein found in their blood. High levels of albuminuria in urine can be a sign of kidney problems. Additional information that can be used including comorbid conditions associated with CKD, such as diabetes and cardiovascular disease.

Ravani says the current benchmark tool, known as the kidney failure risk equation, lacks information on mortality and does not account for other health risks. The findings were published in the British Medical Journal in April and Ravani presented the research at the World Congress of Nephrology in Buenos Aires, Argentina earlier this month.

Kidney disease affects millions of Canadians

The Kidney Foundation of Canada estimates that one in 10 Canadians — about four million people — have CKD and the number of Canadians living with end-stage kidney disease is also increasing, up 35 per cent since 2009.

Liu says the tool’s ability to more accurately predict the risk of kidney failure, and the likelihood of death from it, can improve treatment.

A man gives a presentation

Pietro Ravani speaks at the World Congress of Nephrology in Buenos Aires, Argentina.

Courtesy Pietro Ravani

“For example, information from KDpredict could help reduce unnecessary referrals or missed treatment opportunities for elderly people, and it can help increase the awareness of non-kidney health risks, such as heart disease and other chronic diseases commonly associated with CKD and older age,” she says.

Liu says researchers believe KDpredict could one day be used in different clinical settings, including general practice and specialist clinics to help patients to decide how to treat kidney failure, whether that’s dialysis, kidney transplantation, conservative management without dialysis, or eligibility for clinical trials.

When making treatment decisions for CKD, many factors are difficult to incorporate into a prediction tool, including symptom burden, personal preferences and values. These are often as important as predicted risks. It is also significant to consider how patients, caregivers and providers wish to discuss the risks. Qualitative studies now underway at UCalgary are expected to help identify optimal ways to incorporate risk predictions into clinical decision aids.

Ravani says KDpredict could also be incorporated into electronic medical records. He admits there is much progress to be made on the tool — they plan to continue working to adapt to local needs of additional sites globally, and regularly revise the tool to incorporate future changes in the underlying health system and care processes.

He says a major strength of KDpredict is its digital flexibility — it can be redesigned and retrained regularly to optimize prediction performance as population characteristics or health practices change, or new potential predictors and treatments become available.

Ravani says he expects the tool and its digital codes to be available to other researchers so they can expand to other countries, noting the current limitations of using only three countries in the northern hemisphere with predominantly white populations.

Funding for the study was provided by Canadian Institutes for Health Research, Kidney Foundation of Canada, the Roy & Vi Baay Chair in Kidney Research and additional funding sources in Britian and Denmark. The CSM’s Centre for Health Informatics facilitated data access for the study.

The KDpredict calculator can be accessed here: http://kdpredict.com.

Ping Liu is an epidemiologist in the Department of Medicine at the Cumming School of Medicine (CSM). She is an adjunct assistant professor in the CSM’s Department of Community Health Sciences and member of the O’Brien Institute for Public Health. Her research is supported by the Kidney Research Scientist Core Education and National Training (KRESCENT) New Investigator Award, co-sponsored by the Kidney Foundation of Canada and Canadian Institutes of Health Research.

Pietro Ravani is a clinician-scientist and full professor in the Department of Medicine, Division of Nephrology, at the CSM. He is a member of the Libin Cardiovascular Institute and the O’Brien Institute for Public Health, Centre for Health Informatics, and holds the Roy & Vi Baay Chair in Kidney Research at UCalgary.

Sign up for UToday

Sign up for UToday

Delivered to your inbox — a daily roundup of news and events from across the University of Calgary's 14 faculties and dozens of units

Thank you for your submission.