Predict Metabolic Syndrome

Metabolic syndrome (MetS) is a clustering of risk factors, including central obesity, insulin resistance, dyslipidemia, and hypertension that increases the risk of cardiovascular disease threefold and the risk of type 2 diabetes fivefold (1). People with MetS also often have other conditions, including excessive blood clotting and constant, low-grade inflammation throughout the body. MetS has also been associated with a plethora of cancers including breast, pancreatic, colon and liver cancer (2,3).

Size of the Problem

• 80 million adults in the U.S. meet the criteria for MetS (1).
• 60% higher annual utilization and costs on average are associated with MetS (2).
• 5x individuals with MetS are five times more likely to develop diabetes mellitus (1).

Nearly one-third of U.S. adults—approximately 80 million people—meet the criteria for MetS (1). Such a high prevalence and potential for adverse outcomes imposes an enormous clinical and economic burden. Healthcare costs for individuals with MetS are 60% higher, and increase by another 24% for each additional risk factor (4). In total, the annual healthcare costs for people with MetS is estimated to exceed $220 billion (5). And yet, public awareness of MetS is alarmingly low. In a study of people with diabetes or at elevated risk for developing it, less than 15% indicated they had heard of the condition (6). Increased awareness and identification is paramount; an additional 104 million people are at risk for developing MetS (1).

1. Continuous Risk Factor Monitoring with AI: Develop and deploy continuous monitoring devices integrated with artificial intelligence algorithms to track critical patient parameters in real-time, such as blood pressure, glucose levels, and body mass index (BMI). These devices can alert both patients and healthcare professionals to any significant deviations that may indicate an increased risk of metabolic syndrome. Early intervention based on this real-time data can prevent the progression of risk factors.
2. Comprehensive Health Data Analysis: Utilize advanced AI systems to comprehensively analyze available health data, such as electronic medical records, laboratory test results, and data collected from interviews about social determinants of health. These systems can identify patterns and correlations between various risk factors and the development of metabolic syndrome. For example, an increase in the frequency of elevated triglyceride levels or an upward trend in fasting glucose in a patient may trigger recommendations for further evaluations or adjustments in treatment.
3. Predictive Model for Identifying Metabolic Syndrome: We have developed an artificial intelligence model that uses a balanced dataset to predict the presence of metabolic syndrome in individuals. This model considers variables such as age, body mass index (BMI), blood pressure, fasting glucose, HDL cholesterol, and triglycerides. The target variable, 'Metabolic Syndrome', classifies patients as 'Yes' for those who present with metabolic syndrome and 'No' for those who do not, allowing healthcare organizations to prioritize interventions and resources for those at greater risk.

• Vital Signs: Data indicating the status of the body’s vital and life-sustaining functions, with core vital signs including blood pressure, pulse, respiration rate, and body temperature.
• EHR Problem Lists: Data capturing the most important problems facing a patient, when it occurred and when it was resolved, and lists other illnesses, injuries and factors that affect their health.
• Lab Test Results: Data about important risk markers from tests used for diagnosis, monitoring therapy, or screening, with details about specific results and abnormal indicators.