Using a computer model based on artificial intelligence (AI) the ability to quantify the extent of kidney damage and predict the life remaining in the kidney, now is possible. Neuropathology is a specialization that analyzes kidney biopsy images.
While large clinical centers in the U.S. may significantly benefit by having ‘in-house’ nephropathologists, this isn’t the case in many parts of the country or around the world. As indicated by the study group, the application of machine learning systems such as convolutional neural networks (CNN) for object recognition tasks, is proving to be valuable for classification of diseases and in addition reliable for the analysis of radiology images including malignancies.
To test the feasibility of applying this technology to the analysis of routinely obtained kidney biopsies, the study group performed a proof of principle study on kidney biopsy sections with various amounts of kidney fibrosis (also commonly known as scarring of tissue).
The machine learning framework based on CNN depended on the pixel density of digitized pictures, while the severity of disease was determined by several clinical laboratory measures and renal survival.
CNN model performance then was compared and that of the models generated using the amount of fibrosis reported by a nephropathologist as the sole input and corresponding lab measures and renal survival as the outputs. For all scenarios, CNN models outperformed the other models.
“While according to expert pathologists can able to gauge the severity of disease and detect nuances of kidney damage with remarkable accuracy, such expertise isn’t available in all locations, especially at a worldwide level.
In addition, there is a critical need to institutionalize the measurement of kidney malady seriousness to such an extent that the efficacy of treatments developed in clinical trials can be applied to treat patients with equally severe disease in routine practice,” explained corresponding author Vijaya B. Kolachalama, PhD, assistant professor of medicine at Boston University School of Medicine.
“When implemented in the clinical setting, our work will allow pathologists to see things early and obtain insights that were not previously available,” said Kolachalama.
The research team believes their model has both diagnostic and prognostic applications and may lead to the development of a software application for diagnosing kidney disease and predicting kidney survival.
“If healthcare providers around the world can have the ability to classify kidney biopsy images with the accuracy of a nephropathologist right at the point-of-care, then this can significantly impact renal practice. In essence, our model has the potential to act as a surrogate nephropathologist, especially in resource-limited settings,” said Kolachalama.
Kolachalama said, “When implemented in the clinical setting, our work will allow pathologists to see things early and obtain insights that were not previously available”.
The study group believes their model has both diagnostic and prognostic applications and may lead the development of a software application for diagnosing kidney disease and predicting kidney survival.
Kolachalama said, “If healthcare providers around the world can be able to classify kidney biopsy images with the accuracy of a nephropathologist right at the point-of-care, at that point this can significantly impact renal practice.
Generally, our model can potentially go about as a surrogate nephropathologist, particularly in resource-limited settings”.