At the University of California Irvine Sue & Bill Gross School of Nursing, faculty members are developing ways for artificial intelligence to help deliver better patient care and improved outcomes.

Amir Rahmani is a professor at the nursing school – and also a computer science professor at the Donald Bren School of Information and Computer Sciences, a professor of electrical engineering at the Henry Samueli School of Engineering and an associate director of the Institute for Future Health.

His latest project is openCHA, a conversational health agent with a personalized large language model-powered framework. He's developing it in collaboration with Mahyar Abbasian, Iman Azimi and Ramesh Jain, all from UCI's School of Information and Computer Sciences.

We interviewed Rahmani to learn more about openCHA – discussing LLMs' need for more comprehensive capabilities; how developers will be able to integrate external data sources, knowledge bases and analysis models into their systems using openCHA; and next steps getting openCHA out onto the healthcare market.

Q. In general terms, please describe openCHA and your goals for the technology.

A. In the realm of healthcare, the abundance of misinformation can leave individuals feeling lost and uncertain. Sorting through the sea of conflicting information online is no easy feat, and without proper guidance, it's easy to fall prey to inaccurate advice.

Language barriers further compound this issue, making it difficult for individuals to access the help they need. But amidst this confusion lies a potential solution: personalized health data. By leveraging biomarkers, genomics, images and other personal information, individuals can gain clearer insights into their health and make more informed decisions. This is where recent advancements in AI come into play.

With the ability to analyze vast amounts of data and provide personalized recommendations, AI is becoming an invaluable tool in navigating the complex landscape of healthcare. However, accessibility to these AI-driven solutions remains a challenge, akin to searching for a needle in a haystack.

Enter the large language model era, which is poised to revolutionize how we access and interact with healthcare information, offering a beacon of hope in an otherwise murky sea of misinformation.

In recent years, LLM-based conversational systems have been shaking things up big time. These systems are like the cool kids on the block, giving us access to loads of text info and serving up conversations that actually make sense.

But here's the thing: When it comes to managing health, we need more than just your run-of-the-mill LLM. We're talking about conversational health agents (CHAs) – the superheroes of the health world. These guys need to be able to talk the talk, adapting to your ever-changing health needs and analyzing your personal data like a pro.

And guess what? They're powered by those trusty LLMs, making sure they understand you and can give you the personalized support you need, whether it's answering your burning health questions or just lending an empathetic ear.

Now, let's talk about openCHA. Right now, we're at the brink of creating frameworks that can dish out info in the friendliest, most culturally sensitive way possible. That's where openCHA comes in – it's like the toolkit for developers looking to build CHAs.

Our goal? To make sure CHAs can really connect with users, giving them personalized, caring responses to their health questions. With openCHA, we're talking about enabling the integration of all sorts of data sources, knowledge bases and analytical models to totally revamp how CHAs interact with people.

This framework is a game-changer, arming CHAs with the brains and resources they need to give spot-on health advice that's tailored just for you. Say hello to a whole new level of health companionship – openCHA is here to make sure you get the info you need, when you need it.

Q. You say LLMs need more comprehensive capabilities, including critical thinking, knowledge acquisition and problem-solving abilities. How are you accounting for this in openCHA's LLM-powered framework?

A. Let me introduce you to the orchestrator, the cornerstone of our framework, designed to emulate human behavior within the healthcare process. At its core, this orchestrator comprises two LLMs and one executor.

One LLM serves as the planner, coordinating with the executor to gather essential information and conduct necessary analyses. Leveraging well-established prompting techniques, this primary LLM navigates the planning and problem-solving process, providing transparent reasoning behind its responses and decisions.

Within the openCHA framework, this capability allows for the decomposition of user queries into manageable subproblems, facilitating the execution of tasks required to gather pertinent information. Once all relevant data is collected, the second LLM takes charge, utilizing the amassed information to furnish users with reliable answers.

This structured approach has proved a comprehensive and dependable response to user inquiries, fostering confidence and trust in the openCHA system.

Q. How will developers be able to integrate external data sources, knowledge bases and analysis models into their systems using openCHA?

A. We've rolled out an open-source codebase, offering developers all the tools they need to seamlessly integrate existing datasets, knowledge bases and analysis models to CHAs.

We've kept the code flexible and modular, making it a breeze to add new external sources with just a few lines of codes. The orchestrator handles the heavy lifting, managing the logic effortlessly, so developers can focus on what they do best.

Q. What are the next steps for you in getting openCHA out into the healthcare market?

A. Currently, openCHA is an open-source solution to build community. But with the vision of enabler tech for making applications happen. Prototyping. It can be vague.

Our mission is to foster a thriving community centered around openCHA, sparking innovation within the realm of CHAs. Our focus is on establishing an open architecture for openCHA, forging connections with other open health technologies, accessing open-content resources, and shaping future standards for CHAs.

We're passionate about raising awareness of the future of healthcare, highlighting the pivotal role of LLMs. By integrating execution and planning methodologies, our goal is to deliver top-notch health solutions that meet the ever-changing needs of users.

Our ultimate vision is to cultivate a collaborative environment where stakeholders can freely exchange ideas, share expertise and collectively drive the conversational health technology field forward.

Through collaborative efforts and shared insights, we're dedicated to guiding the development of CHAs toward increased effectiveness and relevance in addressing healthcare challenges.

Follow Bill's HIT coverage on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.