In February, UCI launched the Institute for Precision Health, a campus-wide interdisciplinary enterprise that merges UCI’s capabilities in health sciences, engineering, machine learning, artificial intelligence, clinical genomics and data science. The goal is to identify, create and implement the most effective health and wellness strategy for each individual and, in doing so, address the related challenges of health equity and high cost care.
IPH will bring a multifaceted, integrated approach to what many are calling the next big thing in healthcare. The institute is an ecosystem of interdisciplinary collaboration.
Dr. Daniel Chow is Assistant Professor of Radiological Sciences and Co-Director of the Center for Artificial Intelligence in Diagnostic Medicine at UCI. He was named Educator of the Year by the Department of Radiology and was recognized by UCI Chancellor Howard Gillman as the 2018 Big Idea Winner for his team’s proposal focused on precision health and l ‘artificial intelligence. Chow is the A3 Lead (Applied Analytics and Artificial Intelligence) at UCI’s Institute for Precision Health. Its team brings solutions to hospital, ambulatory and community settings and supports pilot applications. Here, Chow explains why he’s a fan of the Institute for Precision Health and how the data is great, but humans working together are always at the heart of advancements in healthcare.
What excites you most about launching the Institute for Precision Health?
I’m really excited, because I think we’re now in a position where, within this generation, we can bring big ideas to life to improve patient care. I’m still a clinician and want to understand how we can deploy AI tools to benefit patients. For me, that should always be the goal.
Explain a little more. I heard precision medicine was a giant leap forward for healthcare. Is that how you see it?
I think we are on the edge of the abyss. And I feel a lot of pieces are there. You look at, say, clinical omics, you look at AI, big data… all of these terms have been around for a while. I don’t think any of these things move healthcare forward, but when you integrate all of these technologies — and when you integrate consistent goals — then I think things can progress. This is exactly what we do with IPH.
What do you think will be your main contribution to the HPI?
All groups within IPH have specific goals. The group I lead focuses on deploying tools and strategies and quantifying benefits.
Do you mean that you will bring tools into clinical environments and figure out how to make them work in the hospital or clinic?
It is exactly what it is. And some of the solutions that we use will be developed within IPH and others may already be developed within the industry. So we’ll work with a bit of both.
You are wearing many hats right now. How quickly do you think IPH will be the thing that will really take over your life?
I feel like for myself right now, that’s kind of the goal. I want to be able to go in this direction where I devote a large part of my time to IPH.
Is it because you think it’s the most important place to put your energy?
Yes. I think growing up is what I always wanted to do. That’s what I dreamed of doing.
What fueled this dream?
What I’m interested in is looking at the operational benefits, sort of the downstream effects of tools and strategies. When you start making an impact on these, it’s not just about touching the life of one person or even a group of people. It’s about advancing an entire field and touching the lives of countless people. So that’s what excites me.
Do you know what will be your first project within IPH?
We have a few things we’ve already worked on. One is an AI tool that will automatically detect hits. From the initial analysis we performed, we showed that it can significantly improve turnaround time – that is, the time from admission to when radiology flags the discovery of stroke to neurology. However, one thing we are still measuring is whether this actually translates into better patient outcomes. The answer at the moment is that it’s a bit mixed.
Do you know why?
The analogy I use is that AI is a kind of cog, and a cog is supposed to turn other cogs. In this first generation, people still treat AIs like wheels. And we try to integrate them into our regular and customary workflows. So we will have to adapt. One of the goals should be to not only develop cool technology, but also to develop ways to exploit it. We need to understand how to actually integrate these tools into our workflow. So with the stroke work, we have the new tool for faster stroke detection, but we need to figure out how much of the bottleneck with patient care is detection or maybe something else.
And you were also part of the team that developed the COVID Vulnerability Index, a tool doctors use to quickly determine how best to treat each patient?
Yes. With the COVID Vulnerability Index, we went from a simple idea to having the tool in place and rolling out within four months of the pandemic hitting the UCI. And part of the COVID tool is that we use the knowledge gained from each patient to better treat the next. This represents a very big change. In medicine, knowledge is traditionally generational. Now it becomes more real time.
An axiom taught to medical students is that half of what you learn in school is wrong, but you don’t know which half yet. Why? Because historically, if we had a new challenge, fellow physicians would share their experiences, perhaps writing them up for publication in a peer-reviewed journal and learning from each other that way. But this process really takes a long time. And, of course, that’s not what we did with COVID. We pulled all the data in real time and we learned from the patients in real time. So that was kind of our testing ground. He showed that translational medicine – the bench-to-bedside process – can scale much faster in a precision health paradigm.
And do you now think this tool has legs?
Exactly. There are other issues we could use the model on. Some ideas: hospital readmission, sepsis… there are so many other challenges where we could apply the same formula we used for the COVID tool. But it wasn’t just me or my band who developed it. We have collaborated with Laboratory Medicine, Radiology, Computer Science, Public Health, Nursing and many more. To come full circle, it’s as if no one technology is going to solve the huge modern health problems. Nor is it a field or a specialty that will. You really have to combine all the different expertise and knowledge to make it happen. And that’s something that IPH does.
Sometimes when people talk about precision health, they focus on the idea of just getting more data. Sounds like you recognize that the success of Precision Health and the UCI Institute for Precision Health will also be because it brings together so many specialties and so much human expertise?
Precision health is really about team effort; it’s bigger than anyone. But, yeah, I think historically there’s been a lot of focus on specific types of data. Sometimes the problem is that there is almost too much data. So I would just like to point out that we also need to know how we combine all the different types of tools that we develop. And we need to know how best to integrate knowledge into the health care setting.
How long before we can say with certainty that IPH has improved the health of patients?
Well, we can already tell from our work with COVID and stroke detection. Now the task is to find more applications and more uses. What interests me most are the frequent and progressive successes. I firmly believe that small successes add up to major progress.
If you would like to learn more about supporting this or other UCI activities, please visit the Brilliant Future website at https://brilliantfuture.uci.edu. Launched publicly on October 4, 2019, the Brilliant Future campaign aims to raise awareness and support for the UCI. By engaging 75,000 alumni and raising $2 billion in philanthropic investments, UCI seeks to reach new heights of excellence in student success, health and wellness, research and more . UCI Health Affairs plays an essential role in the success of the campaign. Learn more by visiting https://brilliantfuture.uci.edu/uci-health-affairs/.
About the UCI Institute for Precision Health: Founded in February 2022, the Institute for Precision Health (IPH) is a multi-faceted integrated collaborative ecosystem that maximizes the collective knowledge of patient datasets and the power of computational algorithms, predictive modeling and AI. IPH combines UCI’s powerful capabilities in health sciences, engineering, machine learning, artificial intelligence, clinical genomics and data science to deliver the most effective health and wellness strategy for every individual and, in doing so, confronts the related challenges of health equity and the high cost of care. IPH is part of UCI Health Affairs and is co-led by Tom Andriola, Vice-Chancellor for Information, Technology and Data, and Leslie Thompson, Donald Bren Professor of Psychiatry and Human Behavior and Neurobiology and Behavior. The IPH includes seven domains: SMART (statistics, machine learning and artificial intelligence), A2IR (applied research on artificial intelligence), A3 (applied analysis and artificial intelligence), Precision Omics (promotes the translation of the results of genomic research , proteomics and metabolomics in clinical applications), Collaboratory for Health & Wellness (provides the ecosystem that fosters collaboration across disciplines through the integration of health-related data sources), Deployable Equity (involves community stakeholders and health equity groups to create solutions that close the gap in disparities in the health and well-being of underserved and at-risk populations.) and Education and Training (brings data-centric education to students and to healthcare professionals so they can practice at the peak of their licenses).