Systemic lupus erythematosus (SLE) is a systemic, inflammatory, chronic autoimmune disease that can affect multiple organs simultaneously or sequentially, with a relapsing and remitting nature. While SLE can affect multiple major organ systems in the body, one of its most severe manifestations is renal (kidney) involvement, known as lupus nephritis (LN). Although LN can be detected via blood or urine tests, kidney biopsy is considered to be the most precise diagnostic approach. However, challenges arise in interpreting biopsy reports due to discrepancies in pathologists’ interpretations. Two faculty members from the University of Houston (UH) Cullen College of Engineering, Drs Chandra Mohan and Hien Van Nguyen, aspire to improve the LN diagnosis process by leveraging the use of artificial intelligence (AI).
In September 2023, Drs Mohan and Van Nguyen were awarded a $3m grant from the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) to develop an AI program to aid in the diagnosis of LN. This funding enables the team to train a “neural network” to read and classify LN biopsy slides. The research team’s initiative involves building a dedicated computer vision pipeline for classifying LN through the analysis of histopathology imaging data. Collaborating closely with renal pathologists, including experts from various institutions worldwide, the UH team aims to establish a computer-aided diagnosis system for LN, providing clinical decision support akin to renal pathologists.
If successful, the researchers plan to use insights from this program to develop independent AI systems as alternatives to clinician-based diagnoses. Beyond streamlining LN diagnoses, this approach may enable clinicians to diagnose LN earlier and alleviate the burden on specialists amid the increasing prevalence of lupus. While this research aligns with the broader efforts to enhance lupus care through advanced analytics technologies, machine learning is still in its early adoption stages. Therefore, it remains to be when and how AI programs such as this one will be used more widely to deliver precise diagnoses, streamline clinical processes, reduce healthcare-related costs, and ultimately save lives.