Arrow
use cases

Diabetes Prediction Models

Predict high-risk diabetes patients for early intervention, reducing complications and costs.

Problem

Diabetes causes high blood sugar levels and can cause significant damage to nerves and blood vessels if not controlled effectively. This chronic condition generates more than 4,000 new diagnoses each day in the US (1). Given that medical expenses for diabetic patients are 2.3 times higher than those without the disease (3), the economic burden is substantial. Approximately 10% of the US population, or 34 million adults, live with diabetes, contributing to its status as a leading cause of mortality and increased risk of serious health complications. Despite its prevalence, it is estimated that 20% of cases remain undiagnosed (2). As the number of adults with diabetes has doubled over the past two decades, the need for greater awareness and better management becomes increasingly clear.

Why it matters

  • Diabetes causes high blood sugar levels and can damage nerves and blood vessels if not controlled.
  • In the US, over 4,000 new diabetes diagnoses occur daily, with about 34 million adults living with the disease.
  • Medical expenses for diabetic patients are 2.3 times higher, and 20% of cases are estimated to be undiagnosed.

Solution

“DiabetesPredict” is a an algorithm trained to interpret aggregate health data, focusing on clinical factors such as blood pressure and glucose levels. Their assessments guide public health efforts to manage the prevalence of diabetes and mitigate its financial burden on health systems.

Discover more and interact with our AI!

Datasources

The synthetic data set used for the AI model incorporates variables similar to those reported by the CDC in its “National Diabetes Statistics Report, 2020” (1) and considerations for the economic impact of diabetes explored by the American Diabetes Association (2) . The structure and values of the data set are intended to resonate with information on diabetes management and prevention, as discussed by Shrivastava et al. (3) and the role of self-care in diabetes control. The design is also based on studies examining the cost-effectiveness of diabetes interventions (4)(5).

Citations

  1. CDC. “National Diabetes Statistics Report, 2020." U.S. Department of Health and Human Services, 18 Feb. 2020.
  2. American Diabetes Association. “Economic Costs of Diabetes in the U.S. in 2017” Diabetes Care, vol. 41, no. 5, 22 Mar. 2018, pp. 917-928. doi.org/10.2337/dci18-0007.
  3. CDC “Cost-Effectiveness of Diabetes Interventions.” Centers for Disease Control and Prevention, 29 Sep. 2020, https://www.edc.gov/chronicdisease/programs-impact/pop/diabetes.htm. Accessed 12 Feb. 2021.
  4. Zhao, Xilin, et al. * Cost-effectiveness of Diabetes Prevention Interventions Targeting High-risk Individuals and Whole Populations: A Systematic Review.” American Diabetes Association: Diabetes Care, vol. 43, no. 7, Jul. 2020, pp. 1593-1616. doi.org/10.2337/dci20-0018.
  5. Shrivastava, Saurabh, et al. “Role of Self-Care in Management of Diabetes Mellitus.” Journal of Diabetes 8 Metabolic Disorders, vol. 12, no. 1, 2013, p. 14, 10.1186/2251-6581-12-14.

Book a Free Consultation

Trusted by the world's top healthcare institutions