Shaped in 2012, the Parkland Middle for Scientific Innovation (PCCI) is a know-how analysis and growth group affiliated with Parkland Well being & Hospital System in Dallas. Healthcare Innovation just lately interviewed PCCI President and CEO Steve Miff, Ph.D., about among the highlights of PCCI’s 2026 annual report, which has a give attention to predictive analytics and AI.
Healthcare Innovation: Steve, your annual report notes that PCCI has pioneered a novel framework to make sure reliable and sustainable AI growth, and it now has 14 fashions in manufacturing, seven in testing, one in early exploration, and others below growth. Might you begin by speaking concerning the growth of that reliable AI framework?
Miff: It has developed over time, however significantly as we began to deploy fashions, we seen that it’s one thing that is required not solely on the entrance finish as you construct fashions, but additionally after deployment as you proceed to keep up and help them.
We have recognized 4 key pillars that we consider are essential to offering the required transparency to create belief. One is prediction transparency. The second is efficiency transparency. Third is safety transparency, and forth is compliance.
With prediction transparency, what we have seen is that it is nice to have the ability to predict rising threat and the extent of threat for people, however until you’ll be able to give the small print behind what’s driving the danger, the knowledge is helpful, however not as helpful because it might be, when it comes to giving customers the consolation that what they’re seeing is sensible. We develop this know-how known as “Islet” that permits real-time visualization of the knowledge behind a mannequin. With a click on of a button from the digital medical report, you possibly can pop up a window that provides you not solely the present predictive rating, however the historic values. After which dynamically it brings forth the highest 5 elements which are influencing the prediction essentially the most at that cut-off date. After which it provides you all of the precise knowledge that is feeding into that.
HCI: That is attention-grabbing as a result of we frequently hear from well being system leaders that providing that form of transparency is essential to getting clinician buy-in.
Miff: One other pillar is round compliance. It’s so vital to guarantee that any fashions which are being deployed meet the rigor of the newest compliance necessities. We have been a part of the Well being AI Partnership, one of many founding members with Duke and Mayo and Berkeley. They’ve printed some actually good standards and rubrics about components that ought to then go into each the compliance on the entrance finish after which a lifecycle administration of AI. We’ve recognized a rubric of 20 to 30 completely different components that we put each single mannequin by way of earlier than is being deployed and evaluated as an internally generated service.
The third pillar is round safety. No matter occurs with the info must be within the safe setting, since you’re managing PHI and managing a number of knowledge sources that want to return collectively. It is very important spotlight that and continuously take note of it, and have all of the the rigor, the accreditations and all these elements in place.
The final one is round efficiency transparency. The extra fashions we deployed, the extra time we’re spending really monitoring them to guarantee that they carry out based on nevertheless they have been designed, how they’re educated, and that they are not beginning to deviate. That turns into overwhelmingly time-consuming, and we’re spending extra time on monitoring issues than really being able to develop new issues. So we constructed and are within the course of deploying an AI monitoring dashboard that automates quite a lot of these statistical features of the fashions which are being deployed. We’re additionally doing that now for LLMs and ambient listening fashions. It is very important be capable to create these guardrails of what is anticipated, from a statistical perspective after which be alerted when the mannequin begins to deviate from the parameters that you’ve got recognized.
HCI: Can we stroll by way of among the AI improvements described within the annual report? However first I wished to ask whether or not a few of these improvements might be commercialized or exported past Parkland’s use?
Miff: Sure, we design them that means. We’re not ourselves a industrial entity, however we’re all the time trying to have the ability to replicate these in different environments. For instance, our trauma mortality mannequin, which is exclusive, is a little bit bit extra area of interest as a result of it applies to Stage 1 trauma facilities and predicts real-time mortality — we’re within the strategy of deploying that at Grady Well being in Atlanta.
One other factor we have finished with a number of entities and well being methods, and even with payers, is the work that we’re doing with our Neighborhood Vulnerability Compass, which is de facto granular SDOH knowledge, however it’s finished on the block group degree. We reverse geocode, and attribute to a affected person report their block traits, so now we now have it on 100% of the sufferers with out the necessity to interview them. We simply printed a paper on this in JAMIA and it actually confirmed that it has unbelievable recall charges, not solely on the total index degree, however once you take a look at particular indicators, equivalent to whether or not any individual has meals insecurities or housing instability. It’s superb to have the ability to take a block group data attribute to a report after which for that to be so extremely indicative of what that particular person says. We’ve 50-plus organizations that now use it.
HCI: I learn that’s being utilized by the United Approach of their knowledge capacity-building initiative within the Dallas space.
Miff: Sure, it’s been a six-year journey with them. What I simply completely love about that’s that it is foundational in a number of layers. United Approach has been utilizing it for years to trace the affect that their investments within the communities are having, and monitor that yr over yr.
United Approach additionally wished to deliver the neighborhood organizations in and improve their knowledge capability. As a substitute of simply saying we’ll pay so that you can have licenses to entry this, they discovered 200 organizations and put them into cohorts that undergo a six-month curriculum to discover ways to apply it to their particular scenario. It’s been superb to see. That is thrilling, as a result of it’s educating folks learn how to use knowledge.
HCI: Let me ask about a few different predictive instruments which are used within the hospital setting. One is a office security prediction software. Does it display screen sufferers for the potential of violent interactions?
Miff: That is what it does. As you realize, violence in opposition to frontline workers is actually a pandemic. It is gotten considerably worse after the COVID pandemic, and it continues to be an enormous problem. Many organizations are specializing in attempting to alleviate the issue. This pulls it from a number of sources. This additionally makes use of the Neighborhood Vulnerability Compass knowledge. It even makes use of issues equivalent to smoking standing, earlier involvement with prison justice, or earlier violent occasions. It pulls all this advanced data collectively and principally predicts the chance that that encounter will end in a violent occasion. You need to be very cautious that you just’re not profiling people. You are actually figuring out triggers. This is without doubt one of the most susceptible time in our lives, once we’re within the hospital for our personal well being or a cherished one, and also you add all these different issues that compile that nervousness. For instance, smoking all the time reveals up within the prime 10 predicting elements. All hospital campuses are smoke-free. In case you are a heavy smoker and never capable of smoke, that provides to your stress, and begins to create a better threat.
HCI: You even have a pre-term start prevention program.
Miff: The pre-term start concerned constructing a predictive mannequin taking a look at underlying elements to determine ladies who’re more likely to have a pre-term supply. Initially that program initiated each schooling to ladies by way of texting and alerts to their suppliers. Then a broader coalition got here collectively to do extra work on this area, and we’re the analytical engine behind it. We’re utilizing CVC that we mannequin throughout these sufferers to know the non-medical boundaries and drivers of well being. We’re modeling with knowledge from an area supply that is known as the DFW Hospital Basis, the place we now have near 100% of all pregnancies that happen throughout the 2 counties and the related sequence of examine issues. So we’re capable of geocode and mannequin these to know the place the best density of those severe septic issues happen, and what’s the make-up of these neighborhoods. One of many intervention is iron distribution to have the ability to give pregnant ladies iron very early within the being pregnant. We’re utilizing this to determine areas the place the iron distributions happen.
We additionally construct a maternal well being forecasting mannequin. Beforehand we had constructed a diabetes surveillance system, and we’re modeling it after that. The diabetes mannequin predicts deterioration that can require ED visits and hospitalization 12 months out. It is the neighborhood degree, and it provides you each the medical points which are driving that prediction and the non-medical drivers, and it ranks them, and it’s totally dynamic.
HCI: One other one featured within the annual report is a digital imaging surveillance system that leverages generative AI to determine missed analysis for follow-up care. We’ve written about well being methods which are attempting to do a greater job of following up on incidental imaging findings. Is that this just like these efforts?
Miff: There are hidden issues within the notes from the radiology report equivalent to incidental findings and Parkland’s been doing this manually for quite a few years. We now use LLMs to scan by way of all these notes and determine these incidental findings. I believe it is superb how sturdy the accuracy is — the place it is really extra correct than people doing this.
