Dr. Winston Liaw is the project’s principal investigator and chair of the Department of Health Systems and Population Health Sciences at the Tilman J. Fertitta Family College of Medicine.
More than 37 million people in the United States have diabetes, but many don’t receive timely care, which can lead to costly and even life-threatening complications. Although effective treatments are available in primary care settings, clinicians do not have the tools to identify those most at risk. To prevent bad health outcomes before they happen, researchers from the University of Houston are developing Primary Care Forecast, a clinical decision support system that uses deep learning to predict patients are more likely to have complications.
The first tool developed within the innovative AI system is the Diabetes Complication Severity Index (DCSI) progression tool, which, in addition to a patient’s medical history, takes into account how their social and environmental circumstances – employment status, lifestyle, level of education, food security – could increase their risk of complications. Research shows that these societal factors can affect disease progression.
Funded by the American Board of Family Medicine, the tool will provide clinicians with timely and actionable information so they can intervene early, reduce the percentage of people with diabetes who develop complications, and reduce the number of complications affecting each patient. .
“Our long-term goal is to help clinicians become more proactive and less reactive when treating diabetes. By leveraging the capabilities of artificial intelligence and machine learning, we can more effectively connect people at risk with interventions before they get sicker,” said project principal investigator Dr Winston Liaw. and chair of the Department of Health Systems and Population Health Sciences at the Tilman J. Fertitta Family College of Medicine.
For years, insurance companies and researchers have used DCSI to quantify patient complications at any given time. Yet, no tool exists to predict which people are most at risk of increasing DCSI scores.
The tool will be developed in collaboration with the Humana Integrated Health System Sciences Institute at the University of Houston and will leverage unique datasets from Humana Inc. – claims, health records and individual and community social risk factors. The tool will be tested within the PRIME registry, a national platform that includes millions of primary care patients nationwide.
“The challenge with existing prediction tools is that they provide little explanation and no guidance for subsequent actions, which limits confidence and implementation. The tool we are developing will inform clinicians of why patients are at risk and will suggest actions to reduce that risk,” said Ioannis Kakadiaris, Hugh Roy and Lillie Cranz Cullen University Professor of Informatics and Health Systems and Population Health Sciences.
“Humana is excited to collaborate with our partners at the University of Houston leveraging their expertise in AI and predictive analytics with our extensive diabetes experience using DCSI and social determinants solutions impacting health. This tool represents a great opportunity to put actionable insights into the hands of primary care physicians at the point of care where real change in health is happening,” said Dr. Todd Prewitt, corporate medical director, clinical strategy and analytics at Humana.
Beyond diabetes, the researchers believe the tool could help predict complications associated with other conditions, such as uncontrolled hypertension or worsening depression. The tool will be particularly relevant as the healthcare industry shifts to a value-based model of care where physicians are rewarded for improving patient health instead of being paid for each visit, procedure or test, regardless of the result.
The Fertitta Family College of Medicine, founded in 2019 as part of a social mission to improve health and health care in underserved urban and rural communities in Texas, emphasizes education and research in primary care.
“As primary care physicians, we need an effective way to harness the massive amounts of information we receive to improve our patients’ quality of life. The number of complications a patient experiences is strongly associated with death or hospitalization, so developing this AI tool is critical,” Liaw said.