Screening for kidney failure with retinal scans and deep learning
A new technique involving retinal scans and deep learning might save lives by speeding the diagnosis time for severe kidney disease.
Pixabay license from Paul Diaconu at source.
In the paper, Association of Retinal Age Gap and Risk of Kidney Failure: A UK Biobank Study, a team of authors published on their novel technique for using retinal imaging to detect and monitor kidney disease. The Open Access article was published in the American Journal of Kidney Diseases and is licensed under a Creative Commons license (CC BY-NC-ND 4.0). It was summarized in yesterday's Medscape article, Can Eye Screening Help Predict Kidney Failure Risk?.
The paper builds on earlier work from Mingguang He at the University of Melbourne's Centre for Eye Research and his colleagues. In previous work, He and colleagues had created and validated a technique that uses deep learning to accurately predict chronological ages in a population of healthy people. They had also extended that work to use the "retinal age gap" - the difference between actual age and modeled age - in order to predict things like mortality or susceptibility to neurogenerative diseases like Parkinson's Disease.
The new capability for investigating kidney disease takes advantage of the insight that the retinal age gap could also be a biomarker for vascular aging, including the kidney. To test that insight, the team pursued the latest study in order to determine the relationship between retinal age gap and future kidney failure in a population of 35,864 participants with no end stage kidney disease (ESKD) at the time the study started. The analysis revealed that each year in retinal age gap is associated with a 10% increase in risk of an ESKD incident. When the data were divided into quartiles, it was shown that the top quartile was at roughly twice the risk vs. the bottom quartile, with a higher risk for females than males.
According to the Medscape article, this makes sense because the eye has long been understood as a "window to the kidney". Because of shared microvascular structures and pathways, the eye and kidney are inseparably linked in many diseases.
At present, diagnosis rates for ESKD are low and mortality is high when treatement is delayed, so this capability could be an important new arrow in the quiver. Although there are already other known biomarkers for a decline in kidney health, retinal scanning coupled with deep learning has the advantage that it is cost effective, accessible, and non-invasive. As the authors put it,
Consistent evidence has demonstrated the strong association of retinal microvascular changes, including venular dilatation and arteriolar narrowing with ESKD, which opens the door for retinal imaging, as a fast, safe, non-invasive and cost-effective method, to supplement CKD screening,
I assume that the retinal scanning that they're talking about here is at a much higher resolution than a typical cell phone photograph, but this all reminds me of the CRADLE White Eye Detector, which is described in Bryan Shaw's TEDx talk, Can smartphones and facebook help kids survive eye cancer?:
That app can be used to detect "white eyes" in digital photographs. When these are observed, it can be a sign of a serious disease like Coats' Disease or retinoblastoma.
After reading the Medscape article, I wonder if a similar app might someday be available for things like Parkinson's Disease and kidney disease.
Thank you for your time and attention.
As a general rule, I up-vote comments that demonstrate "proof of reading".
Steve Palmer is an IT professional with three decades of professional experience in data communications and information systems. He holds a bachelor's degree in mathematics, a master's degree in computer science, and a master's degree in information systems and technology management. He has been awarded 3 US patents.
Pixabay license, source
Reminder
Pixabay license, source
Reminder
Visit the /promoted page and #burnsteem25 to support the inflation-fighters who are helping to enable decentralized regulation of Steem token supply growth.
This topic moves me, a 48-year-old man lives near my house, occasionally I see him looking at his cell phone, but he brings it too close, his wife tells him, he wears glasses, he answers, I don't like them, the point is, some people they are too stubborn, bringing the cell phone closer and exposing themselves to the sun while reading is very bad, he knows it and does it, I hope this system attracts the attention of many and of this man, whether in the short or long term, he point is that I leave the stubbornness and take care of one of the most important senses we have
Thanks for the information, it's interesting that everything is interconnected in the body. For example, if there is an omission of internal organs, it affects the diaphragm and the neck of a person. Thank you for the informative article.