Next generation wellness: A technology model for personalizing healthcare

Abstract

Personalization or individualization of care is essential to the behavioral modifications and lifestyle changes that result in patient wellness (for good health or chronic disease management). The implementation of effective personalized care is hampered by the lack of reliable means to collect and process real-time data on individual contexts (preferences, constraints) and on adherence to care protocols and mechanisms to provide timely, customized cognitive coaching that is structured, consistent and informative to users. The advent of personal embedded biosensors is creating an accumulation of patient-generated data from numerous "touch points" (data interfaces and exchanges between patient and healthcare services before, during and after traditional clinical encounters). A major technical challenge is the establishment of a patient-centered infrastructure that can: • Provide the customized, timely, evidence/knowledge-driven messaging based on data from multiple touch points for continuous feedback to individual patients • Support this functionality within an information infrastructure of multiple service providers to provide access to unified views of patients' data across touch points and time for multiple users (patients, providers, administrators, researchers) We propose the implementation of a cloud-based platform to support the analytics and other services to implement this infrastructure. From an IT perspective, we explore • Modeling of patient contexts (preferences, behaviors) within a risk-based framework • Calibration of individualized, evidence-based recommendations based on patient-generated data • Deployment of analytics functionalities within the platform model