Global Courant 2023-05-17 11:00:58
NEWYou can now listen to Fox News articles!
The more I learn about the growing use of artificial intelligence in healthcare, the more I become convinced of its essential place in not only the lab or radiology suite, but also in the doctor’s office. It could help usher in a world where tests and treatments are applied on an individual basis based on a patient’s unique history and predicament.
ChatGPT recently passed a radiology board-style exam, though it also informed one of my patients that his hemorrhoids may have been the result of sitting for a long time before I thought to mention that possibility to him. At the same time, it has recently been discovered that AI (a program called Sybil) aids earlier diagnosis of lung cancer by picking up abnormalities before a human eye could detect them. Another study showed that it can be used to measure multiple factors that predict pancreatic cancer up to three years before the usual diagnosis.
AI has the advantage of searching huge databases for comparison purposes, allowing it to use it in detecting differences that signal early pathology. Earlier diagnosis leads directly to earlier treatments and cures.
Dr. Miriam Bredella, a distinguished professor of radiology at Harvard, told me on Doctor Radio on SiriusXM that a critical goal of AI in radiology is to re-screen many thousands of exams (X-rays, CT scans, MRIs) that have failed for one reason and for one reason. Using an AI algorithm to find something else, like the amount of saturated fat in bone, which can correlate with other health problems, including insulin resistance, diabetes and osteoporosis.
AI TOOL HELPS DOCTORS UNDERSTAND CHAOTIC PATIENT DATA
A recent paper in the journal Nature pointed out that AI could help primary care providers by combining early diagnoses of certain conditions, including osteoporosis, with treatment recommendations. AI would serve as a co-pilot in this context, helping to inform busy physicians of relevant options. Doctors like me are already used to dealing with patients informed by Google searches. AI-driven information will be more accurate and as long as it doesn’t undermine the doctor-patient relationship, it will be useful in guiding patients.
In fact, a new report from the consulting firm Accenture showed advances in AI models for major languages could support or augment 40 percent of all healthcare work hours. Seminars on AI application in clinical practice are happening all over the country, from MIT to Stanford to the Mayo Clinic.
CLICK HERE TO RECEIVE THE OPINION NEWSLETTER
Last week in Doctor Radio Reports, Dr. Natalia Trayanova, head of the Alliance for Cardiovascular Diagnostic and Treatment Innovations at Johns Hopkins, described digital twins, a replica of something physical, such as the heart or another organ or an entire patient, a dynamic model based on personalized data that can be used to track how a system ages and provide information on how to replace a part subject to wear without stopping the process the part is doing. The information can be constantly updated with new data, using artificial intelligence to make predictions in terms of disease.
CLICK HERE TO GET THE FOX NEWS APP
Of course, AI technology is still evolving and highly dependent on the quality of the dataset/health records used to train it, but amid a massive shortage of health professionals, AI will clearly come in handy in a wide variety of areas, from preventive healthcare to pandemic preparedness, to drug discovery and development.
Do not get me wrong. I want medical decisions to still be entirely between a healthcare provider and his or her patients. But AI, when properly used and vetted, can certainly speed up, smooth and revolutionize the process.
CLICK HERE TO READ MORE FROM DR. MARC SIEGEL
Marc Siegel, MD is a professor of medicine and medical director of Doctor Radio at NYU Langone Medical Center. He is a medical analyst at Fox News and author of “COVID: The Politics of Fear and the Power of Science.” Follow him on Twitter @drmarcsiegel.
