AI-based method shows promise for pathological diagnosis of hereditary kidney diseases microbiologystudy

Alport syndrome is a genetic disorder associated with kidney dysfunction, sensorineural hearing loss, and ocular abnormalities. In the kidneys, hematuria occurs in the early stages of the disease, followed gradually by proteinuria and, ultimately, end-stage renal failure, which requires renal replacement therapy such as dialysis or kidney transplantation.

The exact prevalence of Alport syndrome is unknown; however, the X-linked form of inheritance (caused by a mutation of a gene on the X chromosome) is the most common. Male patients with a single X chromosome (XY) are more severely affected than female patients with two X chromosomes (XX).

While female patients with X-linked Alport syndrome are generally considered to have a milder form of the disease, clinical research in the United States and Japan has reported that approximately 15% of these patients will reach end-stage renal failure by the age of 40 years.

Diagnosis of Alport syndrome requires genetic analysis and pathological examination of kidney tissue. However, predicting the renal prognosis of female patients is challenging, highlighting the need for indicators to assess the efficacy of renal protective treatment interventions, such as antihypertensive drugs, which have been reported to improve prognosis.

In a new study published in The American Journal of Pathology, a research group used a mouse model that mimics Alport syndrome to compare male and female patients and investigate the details of kidney lesions in female patients.

They developed a modified periodic acid methenamine silver stain for observing basement membrane lesions in regions where type IV collagen α5 is preserved and in areas where it is deficient, which are characteristic of female patients. Furthermore, artificial intelligence (AI) automatically detected these lesions through deep learning.

As the quantitative values of kidney lesions in female mice diagnosed by the AI imaging software showed a positive correlation with proteinuria concentration, this method is expected to help predict the prognosis of kidney function in female patients with Alport syndrome.