geneXwell: Multidimensional Omic Risk Models and Dynamic Visualizations to Drive Positive Change in Employee Behavioral Economics

Employee productivity is directly related to employee health, providing employers strong financial incentives to deploy preventative health programs. One of the most challenging andamp; costly chronic conditions is coronary artery disease (CAD). Most employers spend a significant portion of overall benefits (40-45%) managing andamp; treating symptoms and risk factors associated with CAD. Each CAD event (heart attack, angina) and related procedures (stents, CABG) costs the employer $125k in direct medial and productivity costs. These CAD events are also the number 1 cause of death in the United States. Self-insured employers, which provide health coverage to 100M individuals in the US, bear the costs of CAD directly. Therefore, any cost-effective approach able to reduce CAD incidence in employee populations, particularly through early interventions would have significant societal and economic benefits.geneXwell provides this opportunity by targeting the delivery of our world-class digital preventative cardiology program to those employees most at risk for CAD and most likely to benefit from lipid lowering therapy. As part of ordinary employee health risk assessment, employees provide screening samples for clinical and genomic analysis. Standard demographic and biometric risk factors are combined with a genetic risk estimate, resulting in a personalized CAD risk score per employee. The addition of genetic risk both improves risk stratification as compared to standard clinical guidelines and, more importantly, identifies the nature of risk and the most effective interventions. This strategy is validated and supported by the research of our co-founders at The Scripps Research Translational Institute. In the employee setting, this comprehensive risk modeling is used to stratify the employee pool into risk tiers, and analytics run to determine the cost vs benefit of lifestyle vs therapeutic intervention strategies for each risk tier. This information is then summarized and displayed via intuitive visualization tools that allow employees to evaluate the benefits of prevention behaviors and health interventions. Dynamic visualizations tools will allow collaboration, shared decision making and visibility across all stakeholders. Revenue will be generated through Software as a Service and risk share models to employers.Phase I will target the extension of our established baseline risk model to the data available in an employer health setting, we will develop a prototype employee visualization interface, and conduct a usability study. First, we will build on our existing, validated polygenic CAD scoring model. We will develop and deploy a CAD risk score personalized with genetic, demographic, and clinical factors to produce individualized CAD risk scores for employees. A risk reducer interface will be developed to integrate prevention strategies and anticipated health benefits to drive employee behavioral change. Next, a prototype employee mobile platform will be developed with focus on data synchronization across multiple domains and sources, as well as dynamic, intuitive visualization tools, developed and informed by behavioral science expertise, to guide complex behavioral health decision making by employees. Once the prototype platform has been integrated at the system level and passes verification and validation testing, it will be deployed in a usability study with employees to validate interpretability.The objective is to demonstrate the feasibility of geneXwell-CAD, a predictive health and behavioral change platform to maximize employee health through multidimensional omic risk modeling and dynamic visualizations. Current US healthcare cost structures provide self-insured employers strong financial incentives to ensure employees remain healthy and productive. One of the most challenging andamp; costly chronic conditions is coronary artery disease (CAD). GeneXwell aims to leverage modern predictive analytics and personalized healthcare algorithms, while protecting the privacy of employees, to identify the subpopulation of employees most at risk for adverse CAD outcomes, and to improve employee health and reduce long-term costs.