Can "Reality Mining" Improve Public Health and Medicine?

White paper on reality mining - analyzing data gathered from the use of modern technological devices - to improve public health and medicine

    • November 10, 2009

Can the emerging technology of reality mining—which involves inferring human relationships and behavior by measuring physical and social activity—be used to improve public health and medicine? With a grant from the Robert Wood Johnson Foundation (RWJF), Cogito Inc. composed a white paper that looked at this possibility.

The Issue: Project director Professor Alex Pentland, PhD, of the Massachusetts Institute of Technology (MIT) is a pioneer of reality mining technology. He believes reality mining represents a new era of health-oriented research. He further states that it may be especially promising when information reported by individuals is combined with data gathered by cell phones and other technologies.

One of the key reasons for using reality mining for health-oriented research is that, as the world becomes increasingly interconnected through the movement of people and goods, the potential for global pandemics of infectious disease rises.

Computational models based on reality mining data could transform the assessment of individual and community health and health risks, and bring a new level of understanding to the problems of patient compliance, health services use, and disease causation and propagation.

The Project: Project staff drafted the white paper and then convened a meeting of 20 participants to discuss how to advance public health and medicine through reality mining and to review the paper. They then presented the final white paper, "Using Reality Mining to Improve Public Health and Medicine," to program officers at RWJF and posted it online at the MIT website.

Key Findings

  • Reality mining may be used to conduct individual health assessments—as well as assessments of groups of people (sub-populations)—and potentially provide improvements in health education efforts and behavioral interventions.

  • Certain chronic health-related conditions and behaviors—such as smoking and obesity—tend to be more prevalent among social networks. In the future, perhaps health education efforts can be targeted toward key members of a social network, resulting in improved health behaviors throughout that network.

  • Tracking the movement of individuals may help limit the spread of infectious diseases. If an infected individual's movements are able to be traced, health officials may be able to quickly locate people who may have become infected.

  • Individual privacy can become a controversial issue in reality mining, so safeguards will have to be put in place to protect individual identities. There is still value in massive amounts of anonymous data.

  • Because data collection capabilities are increasing rapidly—more rapidly than legislation regarding individual privacy—it's particularly important to begin discussing how this technology will and should be used.