Artificial intelligence (AI) may never be able to adopt the comforting ‘bedside manner’ that good doctors are known for, but it may be better equipped to accurately diagnose your ailments.
Machine Learning (ML) is a subdivision of AI. ML is the “training” system for computers by feeding them large amounts of data and images and programming them to detect signs of potential danger, such as harmful cells showing up on a scan.
Already widely used in the pathology and oncology fields, LM diagnosis has been shown to have levels of accuracy comparable to that of experienced clinicians. In some studies, ML has even been shown to exceed the ability of humans to correctly diagnose disease.
“There are many different uses of AI,” says Ali Hashemi, president and co-founder of the GluCare Integrated Diabetes Center in Dubai. “The key is how to put it all together in a way that makes sense and [gives] actionable information for both the care team and the physician. AI is not the end point. It’s a tool in your toolbox. What matters is how you use these tools to generate actionable insights for clinicians and patients.”
Both common and dangerous, diabetes is a metabolic disease that causes high blood sugar levels. High blood sugar levels caused by diabetes can damage the nervous system, eyes, and organs, most commonly the kidneys. Today, AI wearable devices like wireless wearable monitors like the Fitbit help patients monitor their blood sugar levels.
The FreeStyle Libre 2 Flash Glucose Monitoring System, which is currently being delivered to diabetics by the UK’s NHS, is one example of a continuous glucose monitoring (CGM) device that provides real-time alarms for the user when sugar levels are about to drop or spike.
“The range of wearable digital biometrics or biomarkers [devices] they can collect is constantly expanding,” says Hashemi. “Those ideas give me superhuman abilities as a doctor to have an incredible impact on my patients.”
AI is also being used to help prevent blindness in people with diabetes. At her clinic, Hashemi uses an AI-powered ophthalmoscope to detect a condition called diabetic retinopathy. “Diabetics, especially those that have been poorly controlled for quite some time, can end up with diabetic retinopathy, which is a degeneration of the retina that can lead to blindness,” Hashemi explains. “The level of accuracy or precision of this device is as good as being done by an ophthalmologist. It has a sensitivity of about 96%.”
Hashemi also points out that in addition to aiding in the accurate diagnosis and detection of diseases, AI is often much more cost-effective than manual medical care. Therefore, its development could make treatment and medical care possible for more people, including those in developing countries, at a lower cost.
Data governance remains one of the biggest challenges in integrating AI and healthcare. AI is based on personal medical data and, in most countries, access is still prohibited to third parties. However, the Covid-19 outbreak and the ensuing need to prevent it from spreading has helped change opinion regarding health data governance. According to a survey by the Wellcome Trust in the UK, only 17% of the public are now against sharing their medical information in the post-pandemic world.
Hashemi welcomes the change, saying, “AI makes everyone more efficient and allows us to make better use of humans, and this is the really important point.”
For more information, visit the Destination Dubai hub at Euronews.com