So this has really been one of the biggest reasons that we’re going through this process to advance responsible AI use in healthcare as it relates to clinical research, primarily due to the massive burden that this puts on research coordinators as well as our providers. So number one, our physicians that are seeing several patients throughout the day have limited time and capacity to remember every single clinical trial and the eligibility criteria for that trial...
So this has really been one of the biggest reasons that we’re going through this process to advance responsible AI use in healthcare as it relates to clinical research, primarily due to the massive burden that this puts on research coordinators as well as our providers. So number one, our physicians that are seeing several patients throughout the day have limited time and capacity to remember every single clinical trial and the eligibility criteria for that trial. So this really prompts them in real time to identify patients who are matching to those trials during that visit. They can then send that information over to a research coordinator who can review the evidence from the AI platform that points them directly to the areas within the chart that the eligibility criteria came from. So with that, we’ve now seen with our preliminary data, this can save the research coordinator’s time by at least doubling the amount of patients they can prescreen. And that’s really a conservative estimate. Atrium Health, Advocate Health, we tend to put about 14,000 cancer patients on trials every year. As of last year, those are our data. And so we expect we can probably double or triple that volume by leveraging kind of human-in-the-loop AI processes to match patients to trials.
This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.
