Transitioning sleeping position detection in late pregnancy using
computer vision from controlled to real-world settings: an observational
Objective: To build a computer vision model that can
automatically detect sleeping position in the third trimester under
real-world conditions. Design: This study used data from an
ongoing observational study and a previous cross-sectional study.
Setting: Participants’ homes. Sample: Pregnant
participants in the third trimester and their bed partners.
Methods: Real-world overnight video recordings were collected
from an ongoing, Canada-wide, prospective, four-night, home sleep apnea
study and controlled-setting video recordings were used from a previous
study. Images were extracted from the videos and body positions were
annotated. Five-fold cross validation was used to train, validate, and
test a model using state-of-the-art deep convolutional neural networks.
Main Outcome Measures: Precision and recall of the model for
detecting thirteen pre-defined body positions. Results: The
dataset contained 39 pregnant participants, 13 bed partners, 12,930
images, and 47,001 annotations. The model was trained to detect pillows,
twelve sleeping positions, and a sitting position in both the pregnant
person and their bed partner simultaneously. The model significantly
outperformed a previous similar model for the three most commonly
occurring natural sleeping positions in pregnant and non-pregnant
adults, with an 82-to-89% average probability of correctly detecting
them and a 15-to-19% chance of failing to detect them when any one of
them is present. Conclusions: The model holds potential to
solve yet unanswered research and clinical questions regarding the
relationship between sleeping position and pregnancy outcomes.