Chronic Disease Management: New Analytics Framework
- A new study reveals that using data analytics to account for patient socioeconomic and demographic factors can lead to more equitable health care and better outcomes in chronic...
- According to Mukherjee, a data-informed approach to scheduling patient visits can decrease diabetes management risks by up to 19.4%, particularly for underserved populations. His co-authors include Dilip Chhajed...
- The study focused on enhancing diabetes care by creating a framework for more effective allocation of health care resources, especially for diverse populations.
Discover how a data-driven approach is revolutionizing chronic disease management and improving healthcare access. This study unveils a new analytics framework leveraging patient data and socioeconomic factors to promote equitable care and better outcomes.Researchers found that implementing data-informed scheduling can considerably reduce diabetes management risks-especially beneficial for underserved communities. The findings highlight how tailored strategies optimize healthcare resource allocation,potentially averting unnecessary hospitalizations. Using machine learning, the research team analyzed patient data alongside census facts, revealing disparities in care access. News Directory 3 reports on this innovative framework. Learn how this groundbreaking work supports fairer access to care and reduces health disparities.Discover what’s next in the future.
Data-Driven Approach Improves Health Care Access, Chronic Disease Outcomes
updated June 23, 2025
A new study reveals that using data analytics to account for patient socioeconomic and demographic factors can lead to more equitable health care and better outcomes in chronic disease management. The research, co-authored by Ujjal Kumar Mukherjee, a business administration professor at the University of Illinois Urbana-Champaign, highlights the potential of technology adoption in health care.
According to Mukherjee, a data-informed approach to scheduling patient visits can decrease diabetes management risks by up to 19.4%, particularly for underserved populations. His co-authors include Dilip Chhajed of Purdue University and Han Ye of Lehigh university.
The study focused on enhancing diabetes care by creating a framework for more effective allocation of health care resources, especially for diverse populations. Mukherjee noted that many high-risk patients don’t receive enough care, emphasizing the need to tailor treatment to improve outcomes.
Researchers analyzed data from over 10,000 diabetes patients from a U.S. clinic, combined with socioeconomic and demographic data from the U.S. Census. Machine learning was used to predict future diabetes risk based on clinical measures and socioeconomic variables like income and education.
The findings revealed significant disparities: patients from low-income, less-educated, or minority communities were less likely to have regular health care visits, despite having higher average glucose levels. This underscores the importance of risk-sensitive decision frameworks to support clinical decisions, Mukherjee said.
Mukherjee emphasized that optimizing health care allocation strategies benefits disadvantaged backgrounds the most, possibly avoiding unnecessary emergency hospitalizations through regular contact with clinicians.
“Managing chronic medical conditions such as diabetes is a major challenge for health care organizations because it requires both committing resources over a long timeline and high levels of patient engagement in the care process,” Mukherjee said.
The research suggests that health care providers can use analytics to distribute limited clinical resources more fairly and efficiently. This approach, according to Mukherjee, supports fairer access to chronic care and can reduce health disparities on a broad scale.
What’s next
Future research will explore how these findings can be implemented in various health care settings to improve chronic disease management and reduce health inequities across different populations.