Arrow
use cases

Metabolic Syndrome Screening

AI can help healthcare organizations (HCOs) identify individuals at-risk for developing Metabolic syndrome (MetS).

Problem

Metabolic syndrome (MetS) is a cluster of risk factors—central obesity, insulin resistance, dyslipidemia, and hypertension—that significantly increases the risk of cardiovascular disease and type 2 diabetes. It also often includes conditions such as excessive blood clotting and chronic low-grade inflammation, and has been linked to various cancers including breast, pancreatic, colon, and liver cancer (1)(2). Approximately 80 million adults in the U.S. meet the criteria for MetS, leading to an average of 60% higher annual healthcare utilization and costs compared to those without MetS (3). Individuals with MetS are five times more likely to develop diabetes, and the condition contributes to a total annual healthcare cost exceeding $220 billion (4)(5). Despite its prevalence and serious implications, public awareness of MetS is low, with less than 15% of those at risk or with diabetes aware of the condition. Increasing awareness and early identification are crucial, as an additional 104 million people are at risk of developing MetS (6).

Why it matters

  • Approximately 80 million adults in the U.S. meet the criteria for MetS, representing a significant public health concern.
  • Healthcare costs for individuals with MetS are 60% higher than those without, with annual costs exceeding $220 billion.
  • Individuals with MetS are five times more likely to develop diabetes and have a threefold increased risk of cardiovascular disease.

Solution

To assist in this effort, an AI model has been developed to predict the occurrence of MetS in individuals. It leverages physiological and lifestyle variables, offering healthcare providers a means to identify and support patients in high-risk categories for MetS with appropriate preventive measures.

Discover more and interact with our AI!

Datasources

The synthetic dataset was constructed by referencing extensive research and data from peer-reviewed studies and healthcare databases to closely replicate authentic clinical cases. Sources such as Steinberg et al. (1), NHLBI (2), O'Neill and O'Driscoll (3), Boudreau et al. (4), Yu et al. (5), and Lewis et al. (6), provided the necessary frameworks for model attributes, ensuring accurate MetS prediction.

Citations

  1. Steinberg, Gregory B., et al. “Novel Predictive Models for Metabolic Syndrome Risk: A 'Big Data' Analytic Approach.” The American Journal of Managed Care, vol. 20, no. 6, Jun. 24. pp:221-228. Accessed 20 Mar. 2021.
  2. NHLBI. Metabolic Syndrome | NHLBI, NIH. Nih.gov. Published December 28, 2020. Accessed March 24, 2021.
  3. O'Neill S, O'Driscoll L. Metabolic syndrome: a closer look at the growing epidemic and its associated pathologies. Obesity Reviews. 2014,16(1):1-12. doi:10.1111/0br.12229.
  4. Boudreau, D.M., et al. “Health Care Utilization and Costs by Metabolic Syndrome Risk Factors.” Metabolic Syndrome and Related Disorders, vol. 7, no. 4, Aug. 2009, pp. 305-314, doi:10.1089/met.2008.0070. Accessed 21 Mar. 2021.
  5. Yu, Yu, et al. “Air Pollution, Noise Exposure, and Metabolic Syndrome - a Cohort Study in Elderly Mexican-Americans in Sacramento Area.” Environment International, vol. 134, Jan. 2020, p. doi:10.1016/j.envint.2019.105269. Accessed 21 Mar. 2021.
  6. Lewis, S. J., et al. “Self-Reported Prevalence and Awareness of Metabolic Syndrome: Findings from SHIELD.” International Journal of Clinical Practice, vol. 62, no. 8, 29 Apr. 2008, pp. 1168-1176, doi:10.1111/j.1742-1241.2008.01770.x. Accessed 21 Mar. 2021.

Book a Free Consultation

Trusted by the world's top healthcare institutions