Challenges and Next Steps for Using AI in Cancer Care

Anil Parwani, MD, PhD, professor of pathology at The Ohio State University Wexner Medical Center, discusses the challenges and opportunities he has encountered in either implementing or utilizing artificial intelligence (AI) technology in the clinical setting.

Transcription:

0:09 | Some of the challenges have been the ID component of it. Many of these are apps that are designed by different phone companies. So think about apps, like you have an iPhone or a smartphone, [where you] generally can go to the app store and buy any app and put it on your phone and you start using it. It is not the case with AI. They are all working on different image formats and different proprietary technology.

0:37 | One of the challenges has been to harmonize those, and bring them into 1 place. Let's say I have an AI app for prostate cancer and there are 3 companies selling it. All 3 of them will not work with my system, they are not compatible. So 1 challenge is compatibility. The second piece is the integration. These are standalone apps, so you have to launch them on a separate website, review the cases, log into the other system, it is not very well integrated in 2024. But I expect that as more pathologists, as more institutes launch these apps, they will become more universal, they will become more easy to use. I think the third thing is the cost. Currently, AI algorithms are not reimbursable, some of them are not reimbursable. Some of them are starting to get reimbursed, but the cost part is prohibitive because when the executive says, we want to launch a prostate cancer algorithm and they want to ask you, how much does it cost? How is it? Why are you not doing what you currently do? How will this help you? We have to go through this specification. On the flip side, because we do not get revenue, it becomes a challenge.

2:13 | The hospital has to focus on launching these AI algorithms based on the quality and the efficiency gains, but in the near future, in fact, January [of 2024] was the first time where they introduced a CPT code for a prostate AI algorithm. If this continues, then we will get reimbursed for it. It will be easier to buy this and make it available for patient care. Right now, only a handful of hospitals are doing it, and they are doing it in the context of patient safety, quality gains, efficiency gains, but soon, there will be revenue coming from it. Those are the biggest challenges.

2:55 | The advantages are more collaboration and more ability to share cases with oncologists, making it more objective, making it more reproducible. My results in my hospital running that algorithm will be the same as Cleveland Clinic or Case Western. [We have] taking away the subjectivity that sometimes comes with pathology diagnosis, and making it more objective, making it more accurate, maybe making it faster. At the end, freeing up some of the time the pathologist might have spent quantitating things.