Results

From July 2022 through April 2023, 51 people expressed interest in participating in the real-world study. Of these, 34 (67%) were not assessed for eligibility (four decided against participating after learning more about the study, 25 did not respond after their initial expression of interest, and five gave birth prior to screening) – we did not collect any data from these. Of the seventeen (33%) participants that were screened, all met the eligibility criteria and gave written informed consent. All seventeen had bed partners, but only fifteen bed partners gave informed consent and participated. Two participants (and their bed partners) installed the camera incorrectly, so their data was excluded from the model building. As such, fifteen participants (and thirteen bed partners) successfully completed the study.

Demographic Characteristics

Demographic characteristics of the pregnant participants and their bed partners (if applicable) are shown in Table 1 . Ethnic backgrounds from the real-world dataset included representation from Northern European, Latino, Greek, South Asian, East Asian, Armenian/Turkish, Italian, and Hungarian ancestries. We did not collect ethnicity, gravida, or parity data from the participants in the controlled-setting dataset.

Dataset

In the real-world study, we collected 29,253 minutes (487.6 hours) of infrared video from which we extracted and annotated 6,960 unique frames. Of these, 6,514 were multi-participant frames, and 446 were single-participant frames. See Appendix B for a qualitative description of the real-world dataset. These data from our real-world dataset were combined with our controlled-setting dataset (5,970 frames) for a total of 12,930 annotated frames, which contained 47,001 annotations, and comprised our dataset for building SLeeP AIDePt-2. SeeTable 2 for class-wise information about the datasets.
A bar chart of the frequency of occurrences of each position class in the real-world dataset and controlled-setting dataset are shown inFigure 1 . The sleeping positions have been rearranged on the x-axis of the bar chart to demonstrate the progression of the positions starting from left recovery and proceeding leftward, rolling across the back (supine), until right recovery and, finally, prone and sitting.

Models

In Figure 2 , class-wise results (averaged across all five loops) are shown using a bar chart and heat map. The bar chart inFigure 2A shows the four performance metrics from the testing phase averaged across the five models’ (one model per loop of the cross-validation) testing sets and across all classes. The error bars on the bar chart represent one standard deviation of the respective value across all measures, reflecting the variability across models (n=5) and classes (n=14). The heatmap in Figure 2B shows the four performance parameters (columns) from the testing phase averaged across the five models’ test sets for each of the predicted classes (rows).
On a per-class basis and averaged across the five models, the sitting class had the highest AP@0.50 (0.92). The left lateral, right lateral, and supine classes also had high values of AP@0.50 (0.82 to 0.89), whereas recovery, prone, and twisted/hybrid positions generally had intermediate values of AP@0.50 (0.62 to 0.72). The non-hybrid tilted positions (left tilt and right tilt) had the lowest values of AP@0.50 (<0.50). As for the pillow class, the AP@0.50 was intermediate-to-high (0.80).
See Table B.1 and Table B.2 in Appendix B for a loop-wise summary of the training, validation, and performance testing of the cross-validation of SLeeP AIDePt-2.
A running example using one of our trained SLeeP AIDePt-2 models to localise and classify the sleeping position of a study participant and their bed partner in eight different extracted frames is displayed inFigure 3 .

Harms

There were no known or identified harms related to this study.