Researchers at the University of Utah have developed an innovative software tool called RiskPath that uses artificial intelligence to predict whether individuals will develop progressive and chronic diseases. The tool analyzes patterns in health data gathered over multiple years to identify at-risk individuals with an accuracy rate of 85% to 99%. Nina de Lacy, a professor of psychiatry and member of the One-U Responsible AI Initiative’s executive committee, stated that chronic and progressive diseases are responsible for about 90% of the health care costs in the United States and the vast majority of morbidity and mortality.
RiskPath aims to understand the trajectories of these diseases to enable better prevention and early intervention. The tool uses advanced time-series AI algorithms to deliver insights into how risk factors interact and change in importance throughout the disease process. The main advantage of utilizing longitudinal data is understanding how individuals develop and change over time.
Predicting disease progression with RiskPath
Research indicates that current medical prediction systems for longitudinal data often fail to accurately identify at-risk patients, achieving correct identification only 50% to 75% of the time. RiskPath provides enhanced insights and identifies high-risk individuals much earlier, allowing for more targeted preventive strategies.
De Lacy and her research team validated RiskPath across three primary long-term patient cohorts, involving thousands of participants, to successfully predict eight different conditions, including depression, anxiety, ADHD, hypertension, and metabolic syndrome. Key advantages offered by RiskPath include enhanced understanding of disease progression, streamlined risk assessment, and practical risk visualization. The system provides intuitive visualizations showing which periods in a person’s life contribute most to disease risk, aiding researchers in identifying optimal times for preventive interventions.
While RiskPath is primarily a research tool designed to enhance risk stratification models, de Lacy hopes it will eventually find utility within clinical settings to improve disease management. The ultimate aim of RiskPath and similar tools is to help people build better risk stratification and decision support tools that assist clinicians and potentially patients understand their risk for chronic or progressive diseases better and earlier.
Kirstie a technology news reporter at DevX. She reports on emerging technologies and startups waiting to skyrocket.
