Making sense of mobile health data: an open architecture to improve individual- and population-level health

Abstract

Mobile phones and devices, with their constant presence, data connectivity, and multiple intrinsic sensors, can support around-the-clock chronic disease prevention and management that is integrated with daily life. These mobile health (mHealth) devices can produce tremendous amounts of location-rich, real-time, high-frequency data. Unfortunately, these data are often full of bias, noise, variability, and gaps. Robust tools and techniques have not yet been developed to make mHealth data more meaningful to patients and clinicians. To be most useful, health data should be sharable across multiple mHealth applications and connected to electronic health records. The lack of data sharing and dearth of tools and techniques for making sense of health data are critical bottlenecks limiting the impact of mHealth to improve health outcomes. We describe Open mHealth, a nonprofit organization that is building an open software architecture to address these data sharing and "sense-making" bottlenecks. Our architecture consists of open source software modules with well-defined interfaces using a minimal set of common metadata. An initial set of modules, called InfoVis, has been developed for data analysis and visualization. A second set of modules, our Personal Evidence Architecture, will support scientific inferences from mHealth data. These Personal Evidence Architecture modules will include standardized, validated clinical measures to support novel evaluation methods, such as n-of-1 studies. All of Open mHealth's modules are designed to be reusable across multiple applications, disease conditions, and user populations to maximize impact and flexibility. We are also building an open community of developers and health innovators, modeled after the open approach taken in the initial growth of the Internet, to foster meaningful cross-disciplinary collaboration around new tools and techniques. An open mHealth community and architecture will catalyze increased mHealth efficiency, effectiveness, and innovation.

Figure 1

Stovepipe versus open architectures: mHealth apps (left) are built independently with little sharing of data, methods, or learning. In contrast, the Internet has an hourglass architecture (right), in which a common protocol, transmission control protocol/Internet protocol (TCP/IP), acts as a simple point of commonality at the narrow waist that allows innovation to flourish through open application programming interfaces (APIs) both above and below the waist. Open mHealth aims to catalyze the mHealth ecosystem from a siloed architecture to an hourglass architecture to increase the scale and effectiveness of mHealth.

Figure 2

InfoVis: Third-party data applications and data stores save and manage data. Data processing units (DPUs) are the building blocks for extracting relevant features and patterns from data streams. Data visualization units enable visual presentations to be created from the extracted data features. Each DPU and DVU completes one task, and then can be composed for higher functions. HTTP = hypertext transfer protocol, JSON = JavaScript object notation.