Residents from around the world discuss their learning and experiences with artificial intelligence in the radiology profession
Artificial intelligence (AI). It has become so much more than a theory in a laboratory, a theoretical idea of what technology and algorithms can do to support medical practitioners as they juggle complex workloads and busy lives. Over the past three years alone, AI has become a recognized tool in the radiology profession, certified by organizations such as the US Food and Drug Administration (FDA), the Therapeutic Goods of Australia (TGA), and the European Union CE. It has moved from a considered idea to an embedded practice in many medical institutions and has grown in its application variety and potential.
To find out more about how residents feel about the arrival of AI and how it has influenced their careers and roles, Aidoc has spoken with several leading residents from across the globe. From how they were introduced to Aidoc and AI to how it has shifted the parameters of their jobs and research, they have provided highly relevant and interesting insights into AI and its influence on the profession.
These residents are the people who will be working with AI in the future. They are the ones that will be on the proverbial front lines as AI evolves and algorithms adapt to provide them with even richer and more relevant support. They are also likely to leverage AI in new and innovative ways, allowing them to undertake their roles and patient care with greater efficiency and improved results.
Dr. Eric Gray, a resident at UCSD San Diego; Dr. Komal Chughtai, a third-year resident at the University of Rochester Medical Center; Dr. Atin Saha, Junior Chief Resident at Yale; and Dr. Yosef Chodakiewitz, Resident at Cedars-Sinai in Los Angeles, offered varied and interesting insights into AI and their profession.
A resident’s view
Some of the key takeaways from the interviews were around how Aidoc enhanced interpretive efficiency and accuracy, how it has added an extra layer of support and diagnostic confidence, and its ability to help with complex workloads.
Dr. Atin Saha believes that AI has become, “a reliable tool that supports not just clinical diagnosis in busy periods, but serves as a teaching aid that gives radiology residents insights into their performance and success rates.”
At Yale, Dr. Saha and the ER research group initiated research focused on assessing whether or not Aidoc could assist residents in quantifying sensitivity and accuracy in terms of their ability. You can read more about how the research was developed and its measurement parameters here, as well as more about how he has found working with the AI platform as a whole.
For Dr. Eric Gray, Aidoc came as a surprise: “It is a very intuitive program that you can pretty much learn how to use right away. Most radiologists will find it easy to use within a day, and the fact that it runs in the background is great. It doesn’t cause unnecessary distractions. It’s like any simple app – like a sport’s score widget that you’re occasionally checking!”
Dr. Gray goes on to discuss a patient situation that highlighted the value of the Aidoc solution as the platform identified a hyperdense focus that wasn’t a solid fit for the clinical scenario. Read more about the AI-aided identification and what happened next here.
“The Aidoc triage system is impacting my day-to-day work, particularly when I’m working as the on-call overnight radiology resident.” Dr. Yosef Chodakiewitz goes on to discuss how the introduction of AI to his department was something that he’d been looking forward to and how his understanding of AI has shifted through the implementation of the solution since then.
Of course, no discussion around AI would be complete without mentioning science fiction. Dr. Chodakiewitz noted, “I had always thought of AI in the same way as science fiction, honestly. This idea that one day all images would be read by a computer and that AI would do all the work. So, when I heard about AI, it was a very distant concept.”
Dr. Komal Chugtai takes you through an AI journey that starts with Star Trek and ends with a highly beneficial solution that has supported workflows, helped with patient treatment, and changed the dynamic of triage.
The residents of the future series from Aidoc underscores how the platform has evolved from a theoretical idea to a solid and reliable extra pair of eyes that supports the radiologist in the workflow, patient care and role. Aidoc has already achieved significant progress in the field, receiving the CE mark for four algorithms and has FDA clearance in triage for cervical spine fractures, pulmonary embolism, large vessel occlusion and intracranial-hemorrhage. The company currently covers around 80% of most commonly found acute pathologies in CT scans and has moved into non-acute pathologies for CT such as the detection, measurement and comparison of lesions.