Published November 18, 2019
Pinaki Sarder, PhD, assistant professor of pathology and anatomical sciences, and doctoral student Brandon G. Ginley have developed a new method that automates the classification of progressive diabetic kidney disease, reducing variability and boosting precision.
Described in a paper published online Sept. 5 in the Journal of the American Society of Nephrology, the advance is expected to minimize variability in diagnoses among pathologists. It may also lead to improvements in diagnosing other conditions, and eventually could allow clinicians to predict ahead of time which diabetic patients are at higher risk of developing kidney disease.
The new method extracts and classifies important tissue structures in renal biopsies similar to the way that a human pathologist does.
“We have developed the first fully automated digital pipeline that, with one click, can diagnose what class of kidney disease a patient is in — without human intervention,” says Sarder, senior author on the paper.
The diagnosis is based on the amount of disease-related changes observed in a renal biopsy.
The focus is on the glomerulus, a sac-like bundle of capillaries that does first-line filtration of blood in the kidneys and is one of the most important structures in the kidney for monitoring disease progression.
“Glomeruli in diabetic patients exhibit progressive deposition of scar tissue, which eventually prevent the glomeruli from functioning correctly to filter the blood,” says Ginley, the paper’s first author and a doctoral student in computational cell biology, anatomy and pathology.
The researchers compared results from their automated method to those of three renal pathologists, one of whom is considered a “gold standard” pathologist. They explained that the automated method agreed with the gold standard pathologist about 50 percent of the time, suggesting that it has learned how to diagnose the cases — because it agrees with the human clinician part of the time — and also learned to develop its own opinion.
“If the method had learned to predict 100 percent the same as the gold standard pathologist, that would be bad, because that would mean that the method is learning too specifically to be like that specific doctor, who might have bias in his or her approach,” explains Ginley, a researcher in the Sarder lab. “In this way, it is similar to a human diagnosis, but still generalized without over-learning the bias of one particular doctor. The ultimate goal is to create a program that is free from the bias of any one particular doctor.”
Currently, pathologists classify a patient’s stage of diabetic nephropathy primarily by visually observing glomeruli and estimating the amount of damage.
In order to improve and automate the precise classification of physical features in the glomeruli to better reflect disease progression, the researchers and colleagues created a set of computationally defined features that indicate the structural alterations in glomeruli that occur in diabetic nephropathy.
Ginley says the digital features are based on fixed mathematical measurements, which cannot be influenced by the person doing the analysis.
“If one pathologist runs the algorithm on a piece of biopsied tissue and another pathologist runs the algorithm on the same piece of tissue, both of them should get exactly the same result,” he says. “A pathologist can then take the classification that the algorithm has assigned to the patient tissue and use it to better inform his final diagnosis.”
Ginley says the algorithm is also flexible enough to accept any number of new or different features.
He noted that the human kidney can contain up to 1 million glomeruli, but only a small fraction of them are contained in a biopsy.
To get the most information out of these capillaries, the researchers created a type of neural network — algorithms designed to recognize complex patterns and relationships.
The information gathered from renal biopsies using this method could eventually allow clinicians to predict which diabetic patients are likely to develop more severe renal disease.
“If we train the algorithm on two groups — people who have mild disease, and those who have severe disease — we can pull out the features associated with severe disease. Then we can use those features in the future to predict which patients may develop severe disease later in life,” Ginley says.
In addition to Ginley and Sarder, other co-authors from the Jacobs School of Medicine and Biomedical Sciences are:
Gregory Wilding, PhD, professor and chair of biostatistics in the School of Public Health and Health Professions, is also a co-author.
Other co-authors are from Johns Hopkins University; University of California, Davis; University of California, San Francisco; Vanderbilt University Medical Center; and Washington University School of Medicine in St. Louis.
The research was funded by the National Institute of Diabetes and Digestive and Kidney Diseases of the National Institutes of Health and a UB IMPACT award.