Artificial intelligence tools have opened new avenues for doctors and researchers to provide patient care and further medical discovery. Dr. Mark Cohen, dean of the Carle Illinois College of Medicine at the University of Illinois at Urbana-Champaign, will discuss the use of AI tools in health care and medical discovery with Liz Ahlberg Touchstone, newsroom biomedical editor. We talked about risks and benefits.
How can AI help doctors care for their patients?
Dr. Mark Cohen
Photo credit: Michelle Hassell
Edit the embedded media in the (File) tab and reinsert it if necessary.
There are several ways that AI can benefit physicians when it comes to patient care. Using AI as a tool can provide doctors with more information in real-time, saving them time in the clinic by eliminating the need to consult multiple sources. There are also many areas around clinic documentation where AI tools can be extremely useful, as they can organize information in a more visually pleasing and understandable way. For example, if you have an AI tool that listens to a conversation between a healthcare provider and a patient, that conversation can be summarized into a medical note that can be reviewed and recorded.
In addition, AI tools can also help diagnose other areas of medicine. One example is image processing. Image processing allows healthcare providers to review lung X-rays and utilize AI tools to better identify lesions and abnormalities. As these tools continue to develop, they will be able to take an image of a patient’s X-ray or CT scan and convert it into a three-dimensional object. I can see it right in front of my eyes, but someone 3,000 miles away, who may be an expert in that disease world, can instantly see the same object in real time and tell my patient We can have a conversation about how best to care for you. This could be transformative for rural and underserved areas. We’ll be able to bring our expertise right where it’s needed, whether it’s at the bedside or your local emergency department, when it can actually save lives. We look at the delivery of that care and how these tools can really help address issues such as access to specialized care, which are serious issues both in rural Illinois and around the world. I’m starting to think about it.
Does using AI risk losing the human connection between doctor and patient?
We need to think of AI as a tool rather than a care provider. AI will not replace doctors. It’s a tool that helps doctors and other healthcare professionals do their jobs more efficiently. Therefore, if we consider medicine as a tool, it will always require a human element to build patient trust and relationships in the treatment process. As AI adoption increases, it will help collect information and organize more information into options available to physicians, but it will not replace humanity or the human element of medicine.
CI Med students use AI and virtual reality tools to examine virtual patients with varying demographics and symptoms, presenting different symptoms of the same condition.
Photo credit: Fred Zwicki
Edit the embedded media in the (File) tab and reinsert it if necessary.
What are the risks of relying on AI for medical information? Can it be trusted?
That was a big question. Obviously, protected health information is critical to maintaining data security and maintaining that level of trust. When I look at how AI tools are being utilized in clinical settings, I think it’s really important to think about data safety to ensure that protected health information is protected.
Reliability must also be considered. When AI searches a database, the answers it gives are only as good as the data that exists in the database. As long as that data is reliable, you can rely on it as a good tool. The question then becomes, how can you be sure that the data being searched is verified, verified, and trusted data, and that the data you retrieve is truly helping providers make better decisions? Is this something you should check?
Similarly, when a patient asks an AI chatbot for medical information or advice, one of the challenges when querying a broader engine like Chat GPT is searching everything on the internet. There is some good information out there, but there is also a lot of unreliable information. How AI derives that information and determines its quality and reliability is critical.
How can AI help with medical discovery, including drug and device development?
I really enjoy thinking about how to use data more effectively. We already have data from your electronic medical record, data from the various tests and results you’ve had over the years, and data from your genetics. What if an AI tool could take all of these datasets and create a digital version of you that could be evaluated? When considering a new drug, is it the right one for your particular condition? You may ask, does it work well for you based on your genetics and medical history? It can run through thousands of probabilities and risks, all in seconds, to determine whether this drug is right for you or recommend what your next best option is.
Another area where AI can help is drug discovery. AI can analyze millions of different types of chemical formulas and create new molecules with medicinal properties. As with any device, thousands of variants can be virtually prototyped to optimize parameters and explore how new devices can be applied to patients. AI tools can be very helpful in not only defining potential new options and paths of discovery, but also accelerating some of that evaluation process.
Last year, we at CI Med brought together medical schools, engineering schools, businesses, government agencies, and regulators to explore how we can innovate and engineer medicine as a large, diverse, and interdisciplinary group. Thinking, we have established a new global consortium for innovation and engineering in medicine. Let’s solve big data problems together. One of these is the creation of a global anonymized data warehouse, which could be an amazing tool. AI solutions can reach 500 million patients, not just 1,000 patients or 1 million patients around the world, and treat rare diseases, cancers, or even just a few that we have only scratched the surface with limited data. What if we could solve some real problems with chronic illness? ?By leveraging new tools like quantum and other ways to ensure data security and encryption, these efforts are changing the way we think about healthcare solutions and how we collaborate around the world. It could take you to the next level.
How is CI Med leveraging AI to develop future physician innovators?
As a medical school, we have an urgent need to think about the next generation, and technology is becoming increasingly involved in how we think about the future of medicine. If we are not training the next generation to use these technologies more effectively, we are doing our future a disservice.
CI Med is the world’s first engineering medical school. We believe this intersection of technology and engineering is an important part of how we teach medical students how to become future physician innovators who can lead interdisciplinary teams and think about how to solve bigger problems in health care. It was founded on the principle of being a part. We’ve been very active in thinking about how to better educate medical students to use tools like AI in all of these different areas.
