The RSNA Conference, the annual conference of the Radiological Society of North America, held each year at the McCormick Place Convention Center in Chicago, and still the largest annual medical conference in the world, continues to evolve with the times. As I have noted in previous reports, today’s RSNA Conference is very different than it was in 1990, when I started attending.
Back then, it was all about showroom modalities, with radiology chiefs and other radiologists being courted by vendor representatives eager to sell them the latest CT, MR and PET machines; and the educational sessions were purely clinical, that is, on how best to consider and diagnose clinical problems. Fast forward to the present and both the exhibition halls and educational sessions have been transformed; On the show floor, the people wandering from booth to booth are much more likely to be hospital and health system administrators than they were 35 years ago, and purchasing new, non-replacement equipment is becoming relatively rare due to the decreasing size of teams. Hospital and health system budgets. Meanwhile, the educational sessions not only focus on topics never dreamed of 35 years ago, such as health equity and the interoperability of information technologies; The emergence of artificial intelligence is becoming a turning point for practicing radiologists and, as a result, ample space is being created for AI-related debate.
It was a little disconcerting to see the number of AI-related sessions decrease a bit this year from last year’s volume, but I’m going to chalk that up to random variation and anticipate the number of such sessions to increase again next year. . In any case, the level of depth and breadth of AI-related sessions was certainly impressive this year, and it’s clear that radiologists are helping to lead the way in US healthcare by discovering ways to leverage the AI strategically and thoughtfully.
In fact, what seemed clear this year is the almost unlimited range of possibilities, clinical, clinical-operative and operative, across the specialty. Broadly speaking, radiology leaders are focusing on a few broad areas: AI to support initial diagnosis; AI to support clinical decision-making about the type of diagnostic test to order; AI to support intelligent programming and protocols; the use of large language models to support patient registration and history summary; and the use of LLM to facilitate the translation of radiology reports and information into a patient-friendly language and framework.
As Arun Krishnaraj, MD, MPH, professor of radiology and medical imaging at the University of Virginia, told attendees Tuesday in a session titled “Improving Patient-Centered Care in Radiology through LLM: Opportunities and Challenges,” “ Unfortunately, radiology reports, even in the 21st century, still look like they could be produced on a 20th century typewriter. It’s full of jargon and long lists.” The good news is He’s here to rescue the situation. and other presenters In that session they described how they and their colleagues are now actively leveraging large language models to provide patient-friendly reporting, something Dr. Krishnaraj and others believe will no longer be a “nice to have” but rather a necessity. as patients become empowered and take a more active part in their care in the years to come.
And there are so many different possibilities in so many dimensions that Eric Topol, MD, bestselling author and practicing cardiologist at the Scripps Clinic in San Diego and editor-in-chief of medical landscape, He was confident when he told the audience present at Monday’s plenary session that he believes that artificial intelligence will transform the practice of medicine in the coming years.
Speaking to a standing-room-only audience at the Arie Crown Theatre, Dr. Topol, author of the 2019 bestseller deep medicine, He took his audience of radiologists and others involved in radiology through the evolution to date of artificial intelligence, and then predicted, based on the progress so far, what would happen next.
Top said a new era in which artificial intelligence tools will help doctors better diagnose and treat diseases, and even predict the onset of them, is just on the horizon for U.S. healthcare. He said the fundamental work done over the past few years in developing algorithms and working with large language models has laid the foundation for massive change. For example, data collected from huge amounts of data and images is already leading to better diagnoses, such as in gastroenterology, where gastroenterologists are already using AI-enabled endoscopy to detect more polyps than they expected. they could detect previously. And data is being collected even from diagnostic images such as X-rays, creating huge data lakes that are used to support medical diagnostic processes. He called this phenomenon “Machine Eyes,” the collection of data that, when analyzed and used to support clinical decisions, can improve diagnosis. Surprisingly now, studies are finding that analysis based on chest x-rays can lead to the diagnosis of a surprising variety of diseases, including diabetes. He cited a September 2023 study based on the analysis of 1.6 million retinal images collected in the United Kingdom that produced groundbreaking predictive diagnoses.
Meanwhile, Topol told his audience, what is becoming clear is that “AI does a really good job with your text in terms of completeness, correctness and conciseness. “AI reports are more accurate, easier to understand and more complete than reports produced by doctors.” It also noted a couple of studies that have concluded not only that AI does a better job of diagnosing than human doctors, but two studies have found that AI itself actually does a better job of diagnosing than AI. + humans. That result, however, he quickly added, is probably related to the fact that the studies were artificial “artificial” tests, not based on real patient care situations. It is interesting to note, however, that AI appears to promote the expression of empathy among doctors.
For all that, Dania Daye, MD, Ph.D., associate professor of radiology at Harvard Medical School and director of the Precision Medical and Interventional Imaging laboratory in the Division of Vascular and Interventional Radiology at Mass General Brigham, in session started by Dr. Krishnaraj referenced an article in Radiology titled “A Context-Based Chatbot Outperforms Radiologists and Generic ChatGPT by Following ACR Appropriateness Guidelines,” in the That one study found that the Chatbot provided substantial time and cost savings. He cited several other studies in recent literature, including one that appeared in the October 5, 2023, issue of Open JAMA Network, titled “Generative Artificial Intelligence for Interpretation of Chest X-rays in the Emergency Department,” which found that reports generated by GPT were equivalent to those of radiologists in the ED and better than teleradiologists.
Dr. Daye warned that doctors and data scientists must act quickly to eliminate “hallucinations, reproduction of bias, spread of misinformation and lack of accountability.” But given the great efforts in those areas, he said, the way is open to effectively harness AI for patient care, education and research.
The potential is enormous, said RSNA President Curtis P. Langlotz, M.D., Ph.D., in his presidential address Sunday. In fact, he noted, it had taken four years in the 1980s to build a system that could analyze just a few images. “Today,” in contrast, “with the right training data, we can build in a matter of days a system that has greater accuracy than anything we built back then.” And so Dr. Langlotz said, “Anyone who works with AI knows that machine intelligence is different, not better, than human intelligence.”
And what seems clear is that the humans driving AI in radiology are being extremely thoughtful and avoiding the temptation to try to “boil the ocean,” a temptation that is often present in healthcare. Instead, they are getting down to business and rolling up their sleeves to address a number of practical problems; In the process, they will not only make radiologists more efficient and effective (an important goal as the healthcare system faces a growing shortage of radiology staff as demand for diagnostic imaging increases in our aging society), but they will also mark the beginning of a new era. era of patient engagement, another extremely important area for healthcare system progress.
And it is obvious that we are now on the path with all of this, and that the next few years in radiology will see enormous progress in leveraging AI to improve the practice of radiology and the delivery of healthcare. And that’s an exciting prospect and one of the encouraging aspects of attending RSNA this year. Who knows what RSNA24 will be like? I can’t wait to find out.
