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.

Objective: Compare maternal and perinatal outcomes between emergency and elective caesarean-hysterectomy for placenta accreta spectrum (PAS) disorders managed by a multidisciplinary team. Design and setting: Single-centre retrospective cohort study Population: 125 cases of antenatally suspected and pathologically confirmed PAS disorder. Methods: Maternal and perinatal outcomes were analyzed. Multivariate logistic regression was used to test associations, adjusting for potential confounders. Survival curves exploring risk factors for emergency delivery were sought. Main Outcome Measures: Maternal outcomes including hemorrhagic morbidity, operative complications. Perinatal outcomes included gestational age at delivery, birthweight, Apgar scores and perinatal death. Results: 25 (20%) and 100 (80%) patients had emergency and elective delivery, respectively. Emergency delivery had a higher estimated blood loss (median IQR 2772 [2256.75] vs. 1561.19 [1152.95], p<0.001), with a higher rate of coagulopathy (40 vs. 6%; p<0.001) and bladder injury (44 vs. 13%; p<0.001). Emergency delivery was associated with increased rates of blood transfusion (aOR 4.9, CI95% 1.3-17.5, p=0.01), coagulopathy (aOR 16.4, CI95% 2.6-101.4, p=0.002) and urinary tract injury (aOR 6.96, CI95% 1.5-30.7, p=0.01). Gestational age at delivery was lower in the emergency group (mean SD 35.19 [2.77] vs. 31.55 [4.75], p=0.001), no difference in perinatal mortality was found (aOR 0.01, CI95% <0.001-17.5, p=0.53). A sonographically short cervix and/or history of APH had an increased cumulative risk of emergency delivery with advancing gestational age. Conclusions: Patients with PAS disorders managed in a tertiary centre by a multidisciplinary team requiring emergency delivery have increased maternal morbidity and poorer perinatal outcomes than those with elective delivery.