Science Friday - From Scans To Office Visits: How Will AI Shape Medicine?

Episode Date: January 22, 2024

Researchers continue to test out new ways to use artificial intelligence in medicine.Some research shows that AI is better at reading mammograms than radiologists. AI can predict and diagnose disease by analyzing the retina, and there’s even some evidence that GPT-4 might be helpful in making challenging diagnoses, ones missed by doctors.However, these applications can come with trade-offs in security, privacy, cost, and the potential for AI to make medical mistakes.Ira and guest host Sophie Bushwick talk about the role of AI in medicine and take listener calls with Dr. Eric Topol, founder and director of the Scripps Research Translational Institute and professor of molecular medicine, based in La Jolla, California.Transcripts for each segment will be available after the show airs on sciencefriday.com. Subscribe to this podcast. Plus, to stay updated on all things science, sign up for Science Friday's newsletters.

How will AI shape the future of medicine? Whether it's CT scans, MRI, ultrasound, we can see AI do at least as well, if not better, than expert physicians. It's Monday, January 22nd, and today, just like every day, is Science Friday. I'm SciFri producer Shoshana Buxbaum. There's a bounty of new research showing that artificial intelligence might improve medicine. It's better at reading mammograms and radiologists. And there's even a study showing that AI chatbots might be helpful in making diagnoses for complex disorders, ones that are missed by doctors. Iroflato and guest host Sophie Bushwick talk with author and cardiologist Eric Topol about the role of AI in medicine, its potential downsides and take listener calls.

Artificial intelligence, AI, has crept into so many different corners of society, especially medicine. Yeah, while people have been fearful of what nefarious uses could befall AI, I have been fascinated about new studies showing the benefits of AI in medicine, like being better at reading mammograms than radiologists, how AI can predict and diagnose diseases by analyzing the retina. Wow. And we're going to talk about that. There's even research showing that AI chatbots might be helpful in making diagnoses of. of rare disorders, people using them themselves, and ones that they are even missed by doctors. But of course, none of this comes without tradeoffs about security, privacy, cost, and the potential for AI to make medical mistakes. Yes, that's, of course, and our next guest has

been following the future of AI very closely. Welcome back, Dr. Eric Topol, a cardiologist and founder and director of the Scripps Research Translational Institute, Professor of Molecular Medicine and Executive Vice President of Scripps Research based in La Jolla, California. Dr. Topal, welcome back to Science Friday. Oh, thanks so much, Ira. Great to be with you again. Nice to have you back. And I want to tell our listeners, you want to hear from you. What questions do you have about how AI can be used in medicine? Maybe you work in the healthcare industry.

Are the uses for AI that you're looking forward to for using in the future? Uses for AI also, does it worry you? Our number 844-724-8255. That's 844-Sight-Tock or tweet us at SciFRI. Let's go right into this, Dr. Topol. I'd like to start with what we know about using AI to read X-rays or MRIs. How effective is AI versus an experienced radiologist? Well, right, Sylvie.

That has been several years of occurring throughout all the types of scans, whether it's x-rays, MRIs, you name it, you know, CT scans, that when you take tens of thousands or hundreds of thousands of these images and you use what's so-called supervised learning where you have experts with ground truths of what they show. You can train the model, the A-M model, these are so-called unimodal because it's just images, to be as good or better than expert physicians. physicians, radiologists, also pathologists, and across the board. So this has been the one area

that's been firmed up over the years is superior image interpretation, you know, at least as good, if not better, than clinicians. That's incredible. And speaking of incredible, I was incredibly intrigued by a TED talk that you gave recently in which you talked about how AI can detect and even even predict the onset of different diseases by analyzing the retina. Wow, how does that work? Yeah, this is really striking. And so as opposed to what we were just talking about interpreting the image with machine eyes, what wasn't predicted, Ira, was that machines could see things that will never see. And so with the retina is probably the prototypic example. who would have thought that by having an AI look at the retina, you could predict Parkinson's

disease five to seven years before it appears, any symptoms, Alzheimer's disease, kidney disease, heart and stroke risk, the hepatobiliary disease, the control of diabetes, control of blood pressure, all these things from a retinal picture. pretty darn striking. That sounds amazing, but can you explain how it works? What is the AI seeing that we humans can't? Right. That's the key, Sylvia, is that we don't have full explainability for this capability, which of course extends to other things like the electrocardogram or chest x-rays or so many of these images. We have had some work to try to get to explaining the features that the machine eyes pick up the so-called saliency maps and also recent work so-called counterfactuals.

But we still have ways to go to fully explain the power of machine eyes, which are almost, you could use our imagination of what you could think they could do in the years ahead. And could there be other diseases in the retina that we, you know, using the retina that we don't know about? Oh, sure. I mean, I think we might have thought, course, that the retina because its brain tissue would give us insight about neurodegenerative diseases, but you're absolutely right. There's probably a lot more that are going to pick up. This is just at the moment scratching the surface of where this is headed. Someday we'll likely be doing self-imaging of our retina for checkups through our smartphone. Wow. One of the places where

AI is currently being used is mammography. There was a piece in KFF-N. news last week about how patients are charged an additional 40 bucks for an AI reading of their mammogram. I mean, this raises some big questions of inequity, right? Absolutely. I think this is unconscionable. We're not at a stage that patients should be charged for AI. You know, we're kind of in the research mode with little implementation. If this is a frontrunner for where we're headed, where we're going to shunt the costs of getting these systems in clinics to patients, that would be horrible. And as you say, that is going to worsen inequities.

And I mean, other than this particular case, radiologists are still the ones interpreting our scans, not AI. But what do you think it would take for AI to be used regularly for this? Yeah, I think what we want to have is compelling evidence. So, for example, you know, in Sweden, they had an 80,000. thousand women were randomized to having their mammograms read by the radiologists and the AI compared to just the radiologist. And it showed marked superiority for accuracy at a considerable savings of time. So that system, interestingly, would be suitable. It has the kind of compelling evidence,

not generally used in many places here in the U.S., but it's the kind of of data that we don't have across many of the other types of medical imaging that's done. Lots of people, of course, the phones are lighting up about this topic. Let's see if we can get a few in. Let's go to Jeff in Chicago. Hi, Jeff. Welcome to Science Friday. Thanks for taking my call. Hi, go ahead. Well, I've been struggling with insomnia for many, many years, and I go to, you know, like acupuncture, he'll go, well, there's many, many reasons for insomnia. And I'd like to know if AI could take a list of, you know, characteristic symptoms and come up with a probable diagnosis for what might be wrong as far as insomnia goes.

Thanks for the call. So it's not like analyzing a retina or something. It's more like analyzing a list of symptoms or. Yeah. Eric? Yeah, I think this is where we've seen good evidence that when patients put in their list of symptoms, lab tests, you know, any findings that they have to chat GPT or even better GPT4, they may get very meaningful output of what's going on.

I mean, we've seen it, of course, in anecdotes, but they're striking, like the boy who went three years where his mother took them to see. 17 different doctors, and he had progressive worsening of his gait and horrible pain and growth arrest. And then his mother, when she entered the symptoms, got the diagnosis of occult spina bifida, a tethered spinal cord, which was released by a neurosurgeon in Michigan, and he did much better. So, you know, Jeff, if you put all your symptoms and any tests that you have into chat GPT, you might get something that's useful, it'll just keep getting better over time. In fact, you mentioned in a recent TED talk, you told the story of a patient who had trouble

getting the proper diagnosis until their parent turned to chat GPT and imported their symptoms, and it worked, right? Yeah, there's so many cases that are emerging like that, Ira. I mean, a patient of mine whose sister had the diagnosis of long COVID, saw many neurologists over many months and was told there's no treatment. And then when she, the person I know, put in the symptoms in the lab tests that came out with a diagnosis of limbic encephalitis, which is treatable. And the patient was treated and is doing, you know, exceptionally well. So, you know, this is kind of a second opinion. You made the point that, of course, it can

generate mistakes. But also, you know, we have the doctors that can overlook this human the loop thing. So it's something that's useful to bounce an idea off, and it's just going to be more accurate as we go forward. Well, I have a story that's sort of the opposite thing. A friend of mine likes to use chat GPT, and his daughter was ill, and he entered some of her symptoms, and it diagnosed her with appendicitis. So he rushed her to the doctor, and it turns out she was completely fine. So for parents or for people who are entering their own systems, how reliable should they consider CHAPT as a diagnostic tool? Yeah, I'm really glad you made that point. Errors can be made. But you know, what's really important to put in context is that we make a lot of

errors without AI. You know, in fact, a recent Johns Hopkins study showed that there are 800,000 people with getting medical diagnostic errors who are severely disabled or die. Wow. And that's without AI per year. So yes, it's true. AI, but you know, when we get studies that are going to look at this scale, it'll be interesting to see how many mistakes are made. The good part is we got the wisdom and experience of clinicians to oversee the results of the AI. But don't underestimate how many errors are being made today without AI. So that's something to keep in mind. Interesting. Let's go to the phone to Connecticut. Genea and Connecticut. Hi, welcome to Science Friday.

Hi, thank you. Hi, go ahead. Dr. Topol, thank you for joining today. My question for you is about whether or not AI could be used in the creation of monoclonal antibodies, like, to prevent COVID. Because like Eveseld fell, you know, out of effectiveness because the variance changed. Could AI be used to, you know, create? monoclonal antibodies to prevent COVID on a much more rapid scale. And if it would be effective than that, could they also be used for asthma allergies? Like, does AI have a role

in the creation of those? Good question. Thanks for calling. We'll let you drive safely. Right. So it's a really important area, which is drug discovery, which is a very hot topic because recently, a group in Boston, for the first time in 38 years, used AI to discover a new structural class of antibiotics with antibiotics that were effective against staff aureus that are resistant to current antibiotics. So the point that's being made about COVID, there's already been AI work to show that you could come up with pan-coronavirus antibodies that bind to. to key sites that are in the virus. And so right now, of course, we don't have an antibody that's effective against the current variance. And this is going to be a segue to having those sort of antibodies.

So across the board, whether it's antibodies, small molecules, you know, we're going to see a lot of acceleration and drug discovery. It's not going to happen so much overnight, but over the next few years, you'll see the difference. Francois in Texas, hi, welcome. Are you there, Francis? Francois? Oh, oh, Francis was, yes. So I wonder if there's any particular field of medicine

like cardiology or gastroenterology that is currently better served by AI than others. You're talking to a cardiologist, so let's see what he said. Well, you know, it's interesting. Some specialties that have really been leading the charge, I mentioned the ophthalmologists with the retina. The gastroenterologist, There have been 33 randomized trials to have machine vision during the colonoscopy. And the pickup rate of polyps, adenomenous polyps, is substantially higher. So that one is on the brink of becoming, hopefully, the way we move forward. So we don't miss the small and important polyps at colonoscopy.

But, you know, it's affecting every type of clinical practice over time. I mean, this is not something that's only. only radiologists, pathologists, and certain clinicians, but it's starting to have an effect across the board. Programs like ChatGPT, they are trained on publicly available information and on past data. And sometimes that data has a lot of bias within it. Could we be replicating that same bias by relying on these AI programs for diagnoses?

Yeah, this is another key point, which is since the inputs are all human content and we have all sorts of embedded biases in that content. That will be reflected in the output too. So that's why we have to be on guard and interrogate the input data and the model for propagating or amplifying bias. And this is something that can't get enough emphasis. We have to do much better. We've seen so many examples of biased AI models. And now that we're into this multimodal model phase where these transformer models that are that are really enabling chat GPT and these advanced large language model chatbots, that potential can even be worse. And it's a very serious limitation I have to deal with.

Do you have any suggestions and how to make it better and taking the bias out? Well, I wish we didn't have such deep biases in our human content. But since that's the basis, that's what has to be, you know, of course, course, it'll be helped, Ira, if the input is based on multi-ancestry data, not just, you know, a emphasis on, you know, European ancestry, for example. That's going to help. But it has to be, you know, see, now the data is not supervised anymore. It's unsupervised, self-supervised. So with that, there has to be an increased attention, tight surveillance of what's going in. And that shows. And that help weed out or reduce the magnitude of the bias.

Is there enough data to do that? Very, very data. Yes, the problem we have right now is the major models that are used today, like the ones we've been talking about, were not ever medically trained. They're just trained on, you know, everything that's out there in the Internet and books and Wikipedia. And so we need fine-tuning. And of course, there hasn't been much of that.

But there was a fascinating pre-print published just a few days ago from Google using one of their models, which compared 20 primary care doctors versus patients and had amazingly improved outcomes on the AI. So we'll see that when it's trained medically. Let's go to Maria in Sunset Park, Brooklyn. Hi there. Welcome to Science Friday. Well, thank you. Welcome to you, too.

Go ahead. Okay. So I accompanied a good friend for sort of an emergency mammograph after a doctor's visit, given some symptoms on what the physician had noticed. So I accompanied her because clearly that was. the stress level, her stress level was very high. I said, I'll come along with you, we'll have lunch, blah, blah. So we get there.

And at the desk, paperwork gets the usual paperwork. And then she was offered an option to have an additional read beyond the human eyes of their physician by AI. And indeed, the cost was $40. dollars and i didn't say anything because she had enough stress and she didn't need me questioning her her uh decision um but it made me very concerned first of all if someone is doing research and is um for a product and see and a patient is being asked to participate they should be paying you you shouldn't be paying them i'm with you on that yeah i didn't say anything but then it made me It kept me thinking, where is that information going?

Because the release that she paid, that she wrote, it's the sign, didn't say anything about the security of that information. Is this going to be somewhere that an insurance company somewhere down the line? Regardless of, you know, depending regardless of what the outcome of the read was, is going to have access to that. And what are the implications of that? Good question. Good question. Yeah, I'm glad you went along with her. You could ask this question, Dr. Topal?

Yes. Well, Maria is spot on about that concern. You know, the way we have treated health data until now, there's all sorts of data brokers and data and breaches of data. So this is something that has to be protected. So it adds on to the insult of charging a patient to use AI that isn't proven to be of value and then to be concerned that what's going to happen to that. data. So I share Maria's point. It's something has to be addressed. That's where there's lots of loose

ends here. Maria, I hope that answers your question. Right. I just have one more question. Is this group your guest, where would one start the query or the questions from the legal, political, legislative aspect of this. Who should be concerned about this is that are senators and representatives? Does it start at the state level or just everywhere and, you know, send that email to everybody. Like, what are you guys doing about? Good question, Marie. Good question.

What do you think, Dr. Topal? Who do we get involved in this, the best, the easiest, the fastest way? Well, we have not done a good job, Ira, as you know, for a particular. our health data and we have most Americans have had that breached and even perhaps more than once. So part of the problem is if we want to get this right, people should own their data. They're all their health data and it shouldn't be sitting on servers that can be hacked and have their health systems hijacked, ransomware, all sorts of things that have happened to breaches. So we have to do much better to protect. And this is not just an AI problem. This is a

general deep problem in this country. On the pro-AI side, there was a recent study from Google that suggested AI chatbots actually showed more compassion to patients than doctors did. I mean, doctors can't be pleased by this, can they? How hard is that to do? You know, this was a shocker to me, and I was a doubting Thomas on this when the first study came out last year. But the most recent study, have really reinforced it. And what's going on here is, as you know, machines don't know what empathy is,

but they can promote it greatly. And so what's amazing is now that the notes are getting automated through this process of AI, they can train, coach the doctors, say, why did you interrupt Mrs. Jones after eight seconds? Why didn't you ask her about this concern that. And so the human content that's being used to train the AI is in turn directly promoting empathy. And I wouldn't be surprised in the years ahead that all doctors will have to go through

coaching by an AI to be more compassionate, be more empathetic. Who would ever have guessed that? I had thought we would get more empathetic by having more time with patients, having direct face time. but I didn't anticipate this, and it's getting replicated several times now through multiple different groups. This is a movie coming out. Well, you actually, you mentioned something about having the AI take care of the notes so the doctor's not doing it. Can you tell us a little more about that? Yeah, this is starting to spread like wildfire in a good way, because, as you know, the worst thing for clinicians is spending hours as a data clerk. That's not why we went into this.

We went into it to care for patients, and this detracts from it, and it's just something that was never envisioned to be such a major dominant part of medical practice. But what we're seeing now is that that conversation between a patient and doctor can be automated, digitized in a note that's better than anything in our charts today. But more importantly, not just the note, which can be put in any level of education, any cultural, language, whatever for the patient with the audio file, if there's any confusion or forgetting what was discussed during the visit. But then that can drive all the data clerk work so that the keyboard liberation movement is on right now, taking care of pre-authorization, follow-up appointments, lab tests, procedures, prescriptions, nudging the patient subsequently for, did you check your blood pressure? Are you going on these walks or whatever that was

being discussed during the visit. So this is a very welcome change and will quickly in the next couple of years be, I think, widespread throughout the practice of medicine. Good to know. Who would have thunk? Let's go to Levittown PA. Caitlin, hi. Welcome to Science Friday. Hi, good afternoon. So my question was, I'm a mental health therapist in New Jersey. and I work with a lot of clients who have needs that might not be met, and their families or their friends that people around them might not necessarily understand all of those needs. So coming in to see me, I'm wondering if there's any way for the AI to essentially put out a disclaimer almost to these potential families, patients that they really need to talk with a mental health professional or a clinician to make

these diagnoses because otherwise we might end up with situations where people could just have, you know, a need that isn't being met. And instead, because they're raising some concern about it, misunderstandings could lead to misdiagnoses such as oppositional defiance disorder or something like that. So how do we prevent some of those biases? or how do we prevent some of these misunderstandings when inherently as human beings, it's hard to understand what our biases are sometimes and hard to recognize that and therefore hard to make that not a part of our software.

Yeah, we talked about that a bit, Dr. Topol, but what about, thanks for the call. What about that? Can AI recommend to the families to, you know, treat the patient better or how to treat the patient better or understand the patient. Yes, I mean, I think what's being touched on here is that we have such inadequate support from psychologists, psychiatrist, counselors for mental health issues. And so we need help, but trying to find the right balance, as the questioner put forth, is tricky. And yet, you know, we have these chatbots that are trying to help manage anxiety, depression, certain parts of mental health. But, you know, this still is in the early stages of validation.

There's small, randomized trials. But whether it will do what you're asking, Ira, it remains to be seen. Hopefully it will because we have such a terrible mismatch of professional help versus need. Let's go to the phones to Mike in northern Wisconsin. Hi, Mike. Hi, that's a real nice segue into the comment question that I have for the guests. You know, it's my argument that we are overselling the artificial intelligence terminology idea. You know, I argue that a lot of the things that we've talked about today and a lot of the advancements are being labeled as AI are actually incremental advancements in techniques and technologies that were thought up by humans, advanced by humans, but with the advancement of computing power and humans that are going in and better organizing

how the data is organized and what tools are being applied, that we're getting some increasement and it's valuable increasing knowledge. But as far as artificial intelligence, where a computer scheme is being put together to come up with a completely new, novel, unique idea, I would argue that there is very little of that we've seen yet. And, you know, I use an example of the, you know, design of experiments, which I'm sure your guest is very well aware of, is applying computing power in ever-increasing amounts, with ever-increasing amount of data to be able to do what,

essentially scientists were doing 100 years ago is not the same thing as artificial intelligence where the machines are thinking of new ways that were never thought of by humans to do something. Let me get back to Topol's reaction. Well, I mean, there's some elements of what you're bringing up that I agree, and that is we're seeing massive computing power. I mean, the base models like GPT4, the prototype, has over 24,000 graphic processing units that are being used. So in massive computing power, and it's a trillion connections, as opposed to our brain. It has 100 trillion connections.

But it isn't just that. I mean, the transformer model, which in recent times, like led to chat GPT, GPT4, Gemini, and so many other models, this is something that is AI. It's the real deal. It isn't just computing power and an ingestion of massive content. It isn't just a stochastic parrot. It is truly the most advanced form. And that's why there's so much fear about artificial general intelligence emerging and companies that are making at their target, which is having every task of a human being, being performed as well or better by an AI. So, no, I don't agree with the point that this is just human stuff and higher computing power.

There's another very vital component added to that. I mean, all these definitions are areas of contention with people disagreeing over what exactly they mean by artificial general intelligence and, yes, by AI as well. But I'd kind of like to change the topic a sec and go back to doctors and AI. I was wondering if there's a tension between the use of these programs and between doctors who might not want to cede authority to AI. I'm thinking about how the doctor might get upset with you if you tell them you've Googled your symptoms and they tell you not to use Dr. Google. Right. Well, Sophie, there's a history of that with Google and also with people bringing. in their data from whatever source, and the reluctance of many physicians to really take that

seriously. But that's going to get amped up now, because now that these chatbots are going to be widely available, we're going to see a different look where, you know, you have this extensive conversation and you get outputs and you say, I'm going to my doctor to ask about this. So it is a challenge to physicians. That is, seeding authority, not having, you know, total control, as has been the case for, you know, a couple of millennia. And so this is just another version of that, which is perhaps even more of a challenge. But that's, this is the future is what you're saying, get used to it. Yeah. I think what we have to, you know, everything has its benefits and risk. But if you just think about what we've been discussing with respect to alleviation of

being a data clerk and getting a second opinion. You know, eventually we're going to have models that have the entire corpus of the medical literature and knowledge up to the moment. And we can't know human, no doctor can have that kind of information at their fingertips. So this is where we're headed and it is a one way path, you know, and I think the net benefit, but we have been discussing many of the liabilities too. Yeah. Well, that's about all the time.

We have sort of run out this hour. Will you come back, Dr. Topol, and we can get into the other discussion? Absolutely. I love the conversation with you and Sophie. It's been fun. That's it. And that's about all the time we have this hour. I want to thank our guest, Dr. Eric Topal, founder and director of the Scripps Research

Translational Institute. He's professor of molecular medicine, executive vice president of Scripps research based in La Jolla, California. And that's it for today. Lots of people help make the show, including... Dee Petersmith. Sandy Roberts. Beth Rami.

John Dan Kosky. And many more. I'm sci-fi producer Shoshana Buxbaum. Tomorrow, the history of our relationship with the moon and the scientific quest to better understand it. Catch you next time.