Continuous non-contact monitoring of neonatal activity.

Journal: BMC pediatrics
PMID:

Abstract

PURPOSE: Neonatal activity is an important physiological parameter in the neonatal intensive care unit (NICU). The degree of neonatal activity is associated with under and over-sedation and may also indicate the onset of disease. Activity may also cause motion noise on physiological signals leading to false readings of important parameters such as heart rate, respiratory rate or oxygen saturation or, in extreme cases, a failure to calculate the parameter at all. Here we report on a novel neonatal activity monitoring technology we have developed using a Random Forest machine learning algorithm trained on features extracted from a depth video stream from a commercially available depth sensing camera.

Authors

  • Paul S Addison
    Research and Development, Acute Care and Monitoring, Medtronic, The Technopole Centre, Edinburgh, UK. paul.addison@medtronic.com.
  • Dale Gerstmann
    Timpanogos Regional Hospital, Orem, UT, USA.
  • Jeffrey Clemmer
    Timpanogos Regional Hospital, Orem, UT, USA.
  • Rena Nelson
    Timpanogos Regional Hospital, Orem, UT, USA.
  • Mridula Gunturi
    Research and Development, Acute Care and Monitoring, Medtronic, The Technopole Centre, Edinburgh, UK.
  • Dean Montgomery
    Research and Development, Acute Care and Monitoring, Medtronic, The Technopole Centre, Edinburgh, UK.
  • Sam Ajizian
    Clinical Research and Medical Science, Acute Care and Monitoring, Medtronic, Boulder, CO, USA.