Health care is more than doctor visits; it's a team effort. But most artificial intelligence-driven technologies built on patient data use only the information provided by physicians, omitting crucial input from nurses and rehabilitation therapists.
An innovative, interdisciplinary project co-led by the University of Illinois Chicago will use artificial intelligence to unify data from a broader range of health professions and create novel, holistic datasets that could transform health care, driving discoveries that positively impact patient outcomes and care.
The collaboration with University of Iowa, University of Missouri and Loyola University and technical partners Microsoft and Tackle AI received up to $10 million from the federal Advanced Research Projects Agency for Health, or ARPA-H. The award is the first ARPA-H funding received by UIC, which will serve as the contracting institution.
Researchers will create new ways to combine structured data and free-text notes from nurses, physical and occupational therapists, speech and language pathologists and physicians for more effective use in electronic health records. These notes often provide additional, valuable information about a patient's progress, particularly as their care moves outside a hospital or clinic.
The project will focus on two complex patient populations: patients who have experienced injuries related to a fall and infants transitioning from the neonatal intensive care unit to home. Both populations rely on the care provided by a variety of health professionals.
Health care is an interdisciplinary process, but existing data tools and infrastructure ignore most of the team. 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."
Andrew Boyd, one of the project's principal investigators and professor of biomedical and health information sciences at UIC
Researchers will use advanced computational methods on the novel data sets to create all-team care summaries and powerful new AI applications. They will also use the data to make new scientific discoveries that will improve care and treatment for patients.
"Falls and NICU patients require all-team care while in the hospital and via outpatient clinics. But fragmented, siloed documentation impedes communication," said Catherine K. Craven, a principal investigator and biomedical informatician at the University of Missouri School of Medicine. "By unifying this data, we can improve communication between health care providers, the patient and their care partners and generate novel scientific insights that improve patient outcomes."
These advances could also be applied to other care domains in addition to falls and NICU transitions, said Karen Dunn Lopez, a principal investigator and professor of nursing at the University of Iowa.
"When you address complex difficult problems, the insights you gain and solutions you develop will likely be applicable to less complex problems," Lopez said. "Our team's work will help us understand how to guide patient-centered decision making about the synergy of care provided by a multidisciplinary team."
Deeper data for complex cases
Much of AI's promise for health care is its potential to automatically extract insights from electronic health record data. An algorithm may suggest a diagnosis based on symptoms or lab results, or match patients with the specific treatment that will be most effective for their case.
More data can lead to better AI guidance. Research has shown that including observations from nurses in patient data can lead to more accurate predictions on measures such as the risk of dying in a hospital than physician notes and lab results alone.
The value of multidisciplinary data is particularly clear for managing adult fall injuries, a surprisingly complex area of health care. Falls are difficult to prevent and can lead to multiple negative health outcomes in older adults.
The top predictor of fall risk is the number of previous falls, but patients may not tell their physicians about all their falls. Reports on falls from emergency-room visits or outpatient therapy sessions may be overlooked in the flood of information in a patient's health record.
Physical and occupational therapists also collect detailed information relevant to fall risk, such as strength and balance assessments. Because these reports are often subjective and text-based, they are hard to combine with physician notes or numerical data such as test results.
"Data is gold, but until it can be used, it is meaningless," said Tanvi Bhatt, professor of physical therapy and rehabilitation sciences at UIC and co-investigator on the project. "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."
Unifying this data with other sources could help clinicians identify the cause of a patient's falls and link them with the most appropriate interventions to prevent future injuries. It could also help researchers design and test new prediction models of fall risk and share those insights with patients in clear language, Bhatt said.
Incorporating this data will also help involve the patient in health care decisions, said Mary Khetani, professor of occupational therapy and rehabilitation sciences at UIC and a co-investigator on the grant. The narrative notes taken by physical and occupational therapists often come directly from interviews with a patient and their family. Organizing the data to share with patients and their caregivers can help them feel more informed and engaged as they navigate multiple health care services outside of the hospital.
"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," Khetani said. "But we can't do that if we overload them with information."
AI as a health care interpreter
Computer scientists on the project will use and develop advanced text-mining and language-processing tools to overcome the linguistic and technical hurdles that prevent the integration of data from other disciplines. The research will test whether large language models can be trained to help understand and connect text data across professions.
"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," said Natalie Parde, associate professor of computer science at UIC and a project co-investigator. "Language processing tools tend not to work as well when applied to health care data. A central technical challenge in this grant is getting these tools and technologies to the point where we can use them reliably in a health care setting."
Once integrated, the data from nurses, rehabilitation therapists and other health professionals can help train more detailed models to predict health risks or treatment effectiveness. AI tools can also generate concise summaries of large amounts of text and data.
For example, a primary care provider may get a synopsis based on their patient's weekly physical and speech therapy visits. Or the parents of a premature infant could receive a summary of the nursing and rehabilitative therapies delivered in the NICU, to help them transition to follow-up care in a clinic or a natural environment like their home.
"It's not just a question of translating into lay language, it's really a question of understanding what's important to present to the patient or their provider," said Barbara Di Eugenio, the Warren S. McCulloch Collegiate Professor of Computer Science at UIC and a project co-investigator.
Through hackathons and other activities using deidentified data, the team will also invite data scientists and software developers to create additional clinical and research applications. All tools developed by the project will be open source and built with input and feedback from health-domain experts.
The partnership highlights the strengths of UIC: seven health sciences colleges representing a broad range of health care disciplines and a computer science department with deep research expertise in machine learning, natural language processing and data science.
Other UIC team members on the project include Samantha Bond of the College of Applied Health Sciences, Miiri Kotche from the College of Engineering and David Chestek of the College of Medicine.
"UIC is a great place where we have this diversity of skills and everyone knows each other and works together," Boyd said. "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 health care data."
Multiomic signatures identified for rapid detection and treatment of high-risk T-ALL