NIDDK awards $3M grant to study using AI to diagnose lupus nephritis

Project will automate classification of biopsy samples to aid diagnostic accuracy

Andrea Lobo, PhD avatar

by Andrea Lobo, PhD |

Share this article:

Share article via email
Two researchers hold up a giant check that signifies an award as balloons float beside them and confetti falls around them.

The National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) has awarded $3 million to a research team that’s using artificial intelligence (AI) to diagnose lupus nephritis, one of the most severe complications of lupus that’s marked by kidney inflammation and damage.

The award will support the research of Chandra Mohan, MD, PhD, a professor of biomedical engineering, and Hien Van Nguyen, PhD, an associate professor of electrical and computer engineering, at the University of Houston.

“This collaborative effort exemplifies how AI and medical expertise can intersect to drive innovation and I want to extend my gratitude to the hardworking team members who are committed to pushing the boundaries of what AI can do in the field of lupus nephritis,” Nguyen said in a university news release.

Recommended Reading
An illustration of a person's kidneys, shown from the back, of a person drinking from a glass.

At-home urine test may allow for earlier lupus nephritis diagnosis

Increasing diagnostic accuracy with AI

Lupus is caused by the immune system mistakenly attacking healthy tissues. In lupus nephritis, which affects up to 60% of adults and 80% of children with lupus, the immune system attacks the kidneys.

Diagnosing the condition, which typically requires a kidney biopsy, can be challenging. In a kidney biopsy, a small piece of kidney tissue is collected from a patient and examined for signs of inflammation and damage. It frequently provides imprecise results and there are often significant discrepancies among specialists.

“Given that this critical diagnostic step, which is important for planning treatment, is highly variable and imprecise, we sought out alternative approaches,” Mohan said.

The project will use AI to classify biopsy samples in an automated fashion to increase the diagnostic accuracy of lupus nephritis.

“This funding allows us to use artificial intelligence approaches to train a ‘neural network’ to learn how to read and classify lupus nephritis biopsy slides,” Mohan said.

Using AI for diagnosing lupus nephritis may translate into better treatment.

While Mohan is internationally recognized for his work on lupus nephritis, particularly in understanding the cellular, molecular, and genetic mechanisms that are critical in the condition, Nguyen is leading projects to study the benefits of AI for improving medical diagnoses.

The researchers will work closely with kidney biopsy specialists Jan Becker, MD, Cologne, Germany, Luan Truong, MD, and Sadhna Dhingra, MD, from Houston Methodist; Qi Cai, MD, PhD, from the University of Texas; and Surya Seshan from Cornell University.

“By leveraging the power of computer vision and deep learning, a branch of machine learning, we will build classifiers that rival the best [kidney biopsy specialists] in making a diagnosis using current criteria. This could dramatically improve patient management and long-term renal and patient outcome,” Mohan said.