Clinical AI Comes of Age | Suchi Saria on the Future of Healthcare

**Suchi Saria** (0:00)
Sepsis is leading cause of death in hospitals. You can't just like throw in an algorithm and hope you're going to see outcomes, right? That's just like adding chaos to chaos. Clinicians are already keeping track of 40 plus patients in their head.
No other industry, we expect this kind of heroism, so I don't feel like our current strategy is sustainable at all. We got clearance as the first AI sepsis monitor. This was a huge regulatory milestone. We are seeing 85, 89, 90, 95, and we've seen 3 to 5 percent absolute reduction in mortality. This means 20 to 30 percent relative reduction in mortality.

**Julie Yoo** (0:44)
At some point, it will be considered malpractice to not use clinical AI products like Bayesian. Is that a realistic vision?

**Suchi Saria** (0:52)
You know, there's three parts to this.

**SPEAKER_3** (0:54)
AI has already transformed administrative work across health care. The harder challenge is transforming clinical care itself.
What happens when AI doesn't just summarize notes or automate documentation but helps clinicians identify high-risk patients earlier, prevent medical emergencies, and make better decisions in real time? In this episode, Julie Yoo speaks with Dr. Suchi Saria, founder and CEO of Bayesian Health, and a professor at Johns Hopkins University, about the evolution of clinical AI, what it takes to earn clinician trust, and why deploying AI in health care requires far more than building a model. They discuss sepsis detection, hospital workflows, FDA approval, AI governance, and the future of proactive medicine.

**Julie Yoo** (1:44)
We are here with Dr. Suchi Saria, who is a globally renowned health AI researcher. She is an endowed professor at Johns Hopkins, runs a machine learning AI health care lab there, but more importantly is the co-founder and CEO of Bayesian Health, which is at the leading edge of clinical AI.
You were on our podcast three years ago, and the world has changed in so many ways since then, writ large, but also obviously specific to the health care AI space. So Suchi, why don't we start broad and then kind of go deep over time. What is the state of clinical AI from your vantage point? What is kind of the full spectrum of clinical AI look like these days? And where does Bayesian fit in that landscape?

**Suchi Saria** (2:21)
Absolutely. First of all, thanks for having me, Julie. I love this podcast.
Let's start by just telling you a little bit about what Bayesian is, especially to the people on this podcast who don't know. So what Bayesian does is it's a real-time clinical intelligence layer that is making care from what is today a very reactive system to making it more proactive.
And the way it does that is it continuously reads the full clinical records. So not just text data, but text, labs, vitals, clinical history, medications, treatments. And it's really making sense of that massively multimodal data to do clinical reasoning really well. And we'll talk a little bit about what we do and how we make that better. And then really tying that with AI-powered workflows to make all the follow-through steps really easy for the clinicians. In terms of the big headline, so one big headline since we last talked was that we got clearance as the first AI sepsis monitor. This was a huge regulatory milestone. Today, all tests that are cleared, so sepsis is leading cause of death in hospitals. Huge toll in terms of lives, but also in terms of hospital clinical variation, how it impacts day-to-day utilization within hospitals. So it's a problem where I'd say like over the last 15 years, many have banged their head against the wall.
It's an example area where I've done over a decade of research, and over three and a half years in partnership with the FDA, we worked really hard to get through all of the pieces needed to really show with a great degree of rigor what was needed to get this in terms of the quality of the solution, how it works across diverse sites, and again, can go more into that. So that really was a very big milestone for us. Another really exciting milestone is that we've partnered with CMS, because of our outcome data, we got FDA breakthrough designation, and we were able to then partner with CMS in a parallel review process, where they've made preliminary approval for reimbursement of this work. This is a huge milestones for the field, not just us.
Then just stepping back a little bit, you asked me, where do we fit? What's happened in the field of clinical AI? I'd say what's been so exciting for me to see is how much it felt for my early days inevitable. I felt it was imminent. It's taken a bit to get there. But in the last three years, what we've seen is really rapid integration of what I would call administrative AI. So a lot of work when you're looking at the patient journey, in terms of transcription, billing, coding. And really, if you just go to a patient journey, they're preparing to see the patient and opportunities and use cases there based on LLMs and text-based AI, that people are showing a lot of summarization, transcription opportunities, as well as post-discharge coding. And really thinking about billing and coding and cleaning that up. I'd say in the middle, which is when you think caring for the patient, where you really have to be trusted enough to get clinicians to change their decision or use the AI's input to inform their decisions. To me, that's kind of where the holy grail is from a care standpoint, a gap, and that's where we've been pushing the world and where we're seeing a lot of progress and I think that's the layer we own. So yeah, so the biggest story I'd say, top line from a Bayesian perspective, is really showing maturity in very hard use cases where we've gone from early results to showing it works across many sides, to really showing beautiful outcome data, to showing FDA approval, to partnership with CMS around reimbursement. And then second, taking the underlying platform concept here and really now starting to show these results across multiple sites in many use cases.