The iris reveals it all
William Shakespeare once said, “The eyes are the window to your soul.” The Bible in Proverbs 30:17 instructs us that a “look in the eye” can tell you a lot about what is going on in the soul and spirit of a man.
Apparently, your iris can also tell a lot about your state of health. The website of Kaiser Permanente says “when your eye doctor peeks at your eyes, they are also looking to see whether you have other health problems, such as high blood pressure, diabetes, thyroid disease and even cancer. When we perform an eye exam, we truly have an up-close, microscopic view into your blood vessels and tissue, giving us clues about other health conditions you may have before you even know you have them.”
No wonder my late cardiologist, Dr Raul Jara, when I first consulted him about my hypertension some decades ago, sent me to the ophthalmologist a floor above his clinic. He explained that he wanted to get a good picture of my overall state of health. And, he said, a trained ophthalmologist can tell him a lot about the condition of my heart and my entire cardiovascular system.
Google claims that a single retinal scan can predict heart disease. The principle is grounded in the fact that the retina, a thin layer at the back of the eye, is rich in blood vessels. Its condition reflects the overall cardiovascular health of an individual. By analyzing the details of these vessels, such as their width and how they branch, AI algorithms can predict an individual’s likelihood of developing cardiovascular diseases.
Google is making a powerful claim. Google is saying they have achieved a breakthrough in this form of medical diagnostics through AI. If true, this is indeed cutting-edge technology with the power to transform traditional diagnostic approaches such as CT scans, MRIs and X-rays in screening.
The potential for non-invasive and cost-effective early detection and intervention offered by Google AI is a very significant and good application of AI. Google’s technology holds the promise of improved patient outcomes and a transformative influence on cardiovascular healthcare. An ophthalmologist in New Delhi observed that this is a beacon of hope, offering enhanced possibilities for diagnosing and treating cardiovascular conditions.
“The implications of Google’s AI technology in cardiovascular healthcare are far-reaching. Correlating retinal vasculature with atherosclerotic phenomenon is well known. Rates of retinal artery to retinal venous vasculature changes well in caliber of retinal arteries, venous changes, A-V junction changes, cholesterol deposits, thromboembolic phenomenon, hemorrhages are some of the parameters that are screened at the retina clinic in patients with abnormal lipid profile, stroke, intracranial hemorrhage, heart attacks, hematological diseases… Correlating clinical findings with AI will help in screening high-risk individuals who are predisposed to cardiovascular events, thus helping in early diagnoses and saving lives.”
Google scientists are using machine learning to analyze a medical dataset of nearly 300,000 patients. This data included eye scans as well as general medical data. Neural networks were then used to mine this information for patterns, learning to associate telltale signs in the eye scans with the metrics needed to predict cardiovascular risk, such as age and blood pressure.
Google also introduced an algorithm capable of identifying a person’s sex, smoking status and predicting the five-year risk of a heart attack, all based on retinal imagery. The AI has the ability for early detection of other diseases such as dementia, multiple sclerosis, Parkinson’s, Alzheimer’s and even schizophrenia.
Google says it is their mission to research “robust new AI-enabled tools focused on diagnostics to assist clinicians. Drawing from diverse datasets, high-quality labels and stateof-the-art deep learning techniques, we are making models that we hope will eventually support medical specialists in diagnosing disease. We’re excited to further develop this research toward new frontiers – and to demonstrate that AI has the ability to enable novel, transformative diagnostics.”
That should be a big help for countries like ours. It will be easier to extend the reach of our healthcare system to cover remote rural areas. Using the potential of AI medical diagnostics, our public health system will be able to provide timely care in areas where there are not too many doctors, or where the doctors are not as well-trained.
Regular medical missions can be dispatched to do retinal examination of the population with data being sent back to Manila for analysis and subsequent follow up. Nothing can be as cost effective as a single retina scan that can help DOH measure the health condition of people in isolated communities and devise a strategy for their medical care as required.
The DOH can even ask Google to do some of their clinical trials of this AI technology here. This will enable us to get a good idea of the state of health of our people at no cost to us.
This is an example of the good use of AI to benefit humanity. AI should stay away from the creative arts because that involves thoughts and feelings only a human, not a machine, can have. An AI-written novel or an AI-generated painting do not provide the meanings we feel for such creations because it is not an original product of a human being. But analyzing tons of data to help humans detect and find cure for diseases, is something only AI can do. The iris reveals it all.