AI System to Predict Patients at Higher Risk of Diabetes Complications – Houston Public Media

More than 37 million people in the United States have diabetes, but many do not receive timely care, which can lead to costly and even deadly complications. While effective treatments are available in primary care settings, clinicians lack the necessary tools to identify those most at risk. To prevent poor health outcomes before they occur, University of Houston researchers are developing Primary Care Forecast, a clinical decision support system that uses deep learning to predict which patients are most likely to experience complications.

The first tool to be developed within the innovative AI system is the Diabetes Complication Severity Index (DCSI) Progression Tool, which, in addition to a patient’s health history, considers how their social and environmental circumstances: state employment, living arrangement, educational level, food security – could increase the risk of complications. Research shows that these social factors can affect the progression of the disease.

Funded by the American Board of Family Medicine, the tool will provide clinicians with useful and timely information so they can intervene early, reduce the percentage of people with diabetes who have 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 sooner. make them sicker,” said Dr. Winston Liaw, 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.

For years, insurance companies and researchers have used the DCSI to quantify complications for patients at a single point in time. Still, there are no tools to predict which people are at the most significant risk of increasing DCSI scores.

The tool will be developed in collaboration with the Humana Integrated Health System Science Institute at the University of Houston and will leverage Humana Inc.’s unique data sets: individual and community claims, health records, and social risk factors. The tool will be tested within the PRIME Registry, a national platform that includes millions of primary care patients across the country.

“The challenge with existing prediction tools is that they provide little explanation and no guidance for further action, limiting confidence and implementation. The tool we are developing will inform clinicians why patients are at risk and suggest actions to reduce that risk,” said Ioannis Kakadiaris, the Hugh Roy and Lillie Cranz Cullen University Professor of Informatics and Health Systems and Population Health Sciences.

“Humana is pleased to collaborate with our partners at the University of Houston leveraging their artificial intelligence and predictive analytics expertise with our extensive diabetes expertise using DCSI and impactful social determinants of health solutions. This tool represents a great opportunity to put insights actionable in the hands of primary care physicians at the point of service where real health change happens,” said Dr. Todd Prewitt, Humana’s corporate medical director, clinical strategy and analytics.

Beyond diabetes, the researchers believe the tool could help predict complications associated with other conditions, such as uncontrolled high blood pressure or worsening depression. The tool will be especially relevant as the health care industry shifts to a value-based model of care in which doctors are rewarded for improving the health of patients rather than paying them for every visit, procedure, or test, regardless of the result.

Founded in 2019 with the social mission of improving health and healthcare in underserved urban and rural Texas communities, the Fertitta Family College of Medicine emphasizes primary care education and research.

“As primary care physicians, we need an efficient way to leverage the vast amount of information we receive to improve the quality of life for our patients. The number of complications a patient experiences is strongly associated with death or hospitalization, so that developing this AI tool is critical,” Liaw said.

Leave a Reply

Your email address will not be published. Required fields are marked *