Modern machine learning, a branch of artificial intelligence, may augment the traditional way of diagnosing kidney disease.
Pathologists often classify various kidney diseases based on visual assessments of biopsies from patients’ kidneys. However, machine learning has the potential to automate and augment the accuracy of classifications.
In a study, a team led by Brandon Ginley, from Jacobs School of Medicine and Biomedical Sciences at the University at Buffalo and Pinaki Sarder, PhD, developed a computational algorithm to detect the severity of diabetic kidney disease without human intervention.
Algorithm to analyse images
The algorithm examined a digital image of a patient’s kidney biopsy at the microscopic level and extracted information on glomeruli, the small blood vessels of the kidney that filter waste from the blood for excretion.
These structures are known to become progressively damaged and scarred over the course of diabetes, reported the study published in the journal of the American Society of Nephrology.
Invoking machine learning
In another article published in the same journal, a team led by Jeroen van der Laak and Meyke Hermsen, from Radboud University Medical Centre, Nijmegen, the Netherlands, applied machine learning to examine kidney transplant biopsies and went beyond glomeruli to assess multiple tissue classes in the kidney. The researchers developed a machine learning model called a ‘convolutional neural network’ (CNN) and found that it could be applied to tissues from multiple centres, for biopsies and nephrectomy samples, and for the analysis of both healthy and diseased tissues. They validated the CNN’s results with standard classification methods.
 |
| Artificial intelligence can facilitate kidney transplant research by yielding accurate data characterising disease processes |
 |
Singer Selena Gomez had a kidney transplant a few years ago |
No comments:
Post a Comment