Feasibility of Reidentifying Individuals in Large National Physical Activity Data Sets From Which Protected Health Information Has Been Removed With Use of Machine Learning.

Journal: JAMA network open
Published Date: Dec 7, 2018

Abstract

IMPORTANCE: Despite data aggregation and removal of protected health information, there is concern that deidentified physical activity (PA) data collected from wearable devices can be reidentified. Organizations collecting or distributing such data suggest that the aforementioned measures are sufficient to ensure privacy. However, no studies, to our knowledge, have been published that demonstrate the possibility or impossibility of reidentifying such activity data.

Authors

  • Liangyuan Na
    Operations Research Center, Massachusetts Institute of Technology, Cambridge.
  • Cong Yang
    Department of Industrial Engineering and Operations Research, University of California, Berkeley.
  • Chi-Cheng Lo
    Department of Industrial Engineering and Operations Research, University of California, Berkeley.
  • Fangyuan Zhao
    Tsinghua-Berkeley Shenzhen Institute, Tsinghua University, Shenzhen, China.
  • Yoshimi Fukuoka
    Department of Physiological Nursing/Institute for Health and Aging, School of Nursing, University of fornia, San Francisco, CA 94143.
  • Anil Aswani
    Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA 94720.

Keywords

External Resources

Popular Topics
Recent Journals