Bias in machine learning applications to address non-communicable diseases at a population-level: a scoping review.

Journal: BMC public health
PMID:

Abstract

BACKGROUND: Machine learning (ML) is increasingly used in population and public health to support epidemiological studies, surveillance, and evaluation. Our objective was to conduct a scoping review to identify studies that use ML in population health, with a focus on its use in non-communicable diseases (NCDs). We also examine potential algorithmic biases in model design, training, and implementation, as well as efforts to mitigate these biases.

Authors

  • Sharon Birdi
    Upstream Lab, MAP Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, Unity Health Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada.
  • Roxana Rabet
    Upstream Lab, MAP Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, Unity Health Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada.
  • Steve Durant
    Research coordinator (at the time of writing) of the Upstream Lab.
  • Atushi Patel
    Upstream Lab, MAP Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, Unity Health Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada.
  • Tina Vosoughi
    Upstream Lab, MAP Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, Unity Health Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada.
  • Mahek Shergill
    Upstream Lab, MAP Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, Unity Health Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada.
  • Christy Costanian
    Upstream Lab, MAP Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, Unity Health Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada.
  • Carolyn P Ziegler
    Library Services, Unity Health Toronto, St. Michael's Hospital, Toronto, ON, Canada.
  • Shehzad Ali
    Department of Epidemiology and Biostatistics, Western Centre for Public Health & Family Medicine, Western University, London, ON, Canada.
  • David Buckeridge
    Department of Epidemiology, Biostatistics and Occupational Health, School of Population and Global Health, McGill University, Montreal, QC, Canada.
  • Marzyeh Ghassemi
    Electrical Engineering and Computer Science, Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, United States.
  • Jennifer Gibson
    Joint Centre for Bioethics, Dalla Lana School of Public Health, University of Toronto, 155 College Street, Suite 754, Toronto, ON, M5T 1P8, Canada. jennifer.gibson@utoronto.ca.
  • Ava John-Baptiste
    Departments of Epidemiology & Biostatistics, Anesthesia & Perioperative Medicine, Schulich Interfaculty Program in Public Health, Western University, London, ON, Canada.
  • Jillian Macklin
    Upstream Lab, MAP Centre for Urban Health Solutions, Unity Health Toronto, Toronto, Ontario, Canada.
  • Melissa McCradden
    Department of Bioethics, The Hospital for Sick Kids, Toronto, Ontario, Canada.
  • Kwame McKenzie
    Wellesley Institute, Toronto, ON, Canada.
  • Sharmistha Mishra
    MAP Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.
  • Parisa Naraei
    Department of Computer Science, Toronto Metropolitan University, Toronto, ON, Canada.
  • Akwasi Owusu-Bempah
    Department of Sociology, Faculty of Arts & Sciences, University of Toronto, Toronto, ON, Canada.
  • Laura Rosella
    Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada.
  • James Shaw
    Department of Internal Medicine, University of Manitoba, Winnipeg, MB, Canada.
  • Ross Upshur
  • Andrew D Pinto
    Upstream Lab, MAP/Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, Unity Health Toronto, Toronto, Canada.