In the world of healthcare, “it’s a team effort,” yet many AI technologies focus solely on physician-provided data, leaving out vital contributions from nurses and rehabilitation therapists. An innovative project co-led by the University of Illinois Chicago (UIC) aims to change that by harnessing artificial intelligence to unify health data from a wider array of professionals, creating holistic datasets that could revolutionize patient care.
This groundbreaking collaboration involves institutions like the University of Iowa, University of Missouri, and Loyola University, alongside technical partners Microsoft and Tackle AI. With the support of up to $10 million from the federal Advanced Research Projects Agency for Health
(ARPA-H), this marks the first ARPA-H funding awarded to UIC, which will serve as the contracting institution.
The researchers will develop new methods for integrating structured data and free-text notes from various health professionals—including nurses, physical and occupational therapists, and speech and language pathologists—into electronic health records. These notes often hold valuable insights into a patient’s progress, especially as their care extends beyond hospital walls.
The project focuses on two complex patient populations—those recovering from fall-related injuries and infants transitioning from the neonatal intensive care unit (NICU) to home—and recognizes that both groups require a collaborative approach to care.
“Healthcare is an interdisciplinary process, but existing data tools and infrastructure ignore most of the team,” emphasizes Andrew Boyd, a principal investigator and professor at UIC. “Other professions see patients more frequently and provide very high-fidelity data that gets closer to the reality of the patient, instead of just the brief snapshots in time that you get from data documented by physicians.”
By utilizing advanced computational methods on these novel datasets, researchers aim to generate comprehensive care summaries and develop new AI applications to enhance patient treatment and outcomes.
“Falls and NICU patients require all-team care while in the hospital and via outpatient clinics. But fragmented, siloed documentation impedes communication,” states principal investigator Catherine K. Craven from the University of Missouri. “By unifying this data, we can improve communication between healthcare providers, the patient, and their care partners and generate novel scientific insights that improve patient outcomes.”
The potential impact of this initiative extends beyond falls and NICU transitions, as highlighted by Karen Dunn Lopez from the University of Iowa, who points out, “When you address complex, difficult problems, the insights you gain and solutions you develop will likely apply to less complex problems.
AI Integrates Data From Various Healthcare Professionals
AI’s promise in healthcare primarily resides in its ability to extract insights from electronic health records. Research indicates that incorporating nursing observations leads to more accurate predictions regarding patient risks, such as mortality rates. This is particularly crucial in managing adult fall injuries, which are fraught with complexities. The most significant predictor of fall risk is the number of previous falls, yet patients often don’t report all their incidents to physicians.
“Data is gold, but until it can be used, it is meaningless,” remarks Tanvi Bhatt, a professor at UIC. “The text-based notes that we have are more narrative and descriptive compared to lab measures. But if that text is lost, there is no continuum of care.”
Integrating data from various health professionals can give clinicians a clearer picture of patient fall risks and enable them to implement targeted interventions. Additionally, this approach encourages patient involvement in healthcare decisions.
“We know that best practice is centering the expertise of the patient and family in decision-making to drive the best outcomes and get their buy-in and adherence,” says Mary Khetani, a professor at UIC. “But we can’t do that if we overload them with information.”
AI As a Healthcare Interpreter
To facilitate this integration, computer scientists on the project will develop advanced text-mining and language-processing tools to overcome barriers in combining data from different disciplines.
“Medical data is unique in many ways, one being that it tends to include jargon and other terms that don’t appear commonly in more popular online sources,” explains Natalie Parde, an associate professor of computer science at UIC. “A central technical challenge in this grant is getting these tools and technologies to the point where we can use them reliably in a healthcare setting.”
The combined insights from nurses and therapists will enable the creation of more detailed predictive models for health risks and treatment effectiveness. AI tools can also generate concise summaries of extensive text data, enhancing communication between healthcare providers and patients.
The project showcases UIC’s diverse strengths in health sciences and computer science through collaborative efforts and open-source tools.
“UIC is a great place where we have this diversity of skills, and everyone knows each other and works together,” Boyd concludes. “So when these wonderful opportunities come up, we can pull everyone together, including our collaborating institutions, and try to transform the way we look at healthcare data.”
The post Revolutionizing Healthcare: Harnessing the Power of AI to Unify Diverse Health Data first appeared on Daily Nurse.
