Predicting Risk of Post-Operative Morbidity and Mortality following Gynaecological Oncology Surgery (PROMEGO): A Global Gynaecological Oncology Surgical Outcomes Collaborative Led Study.

The medical complexity of surgical patients is increasing, and surgical risk calculators are crucial in providing high-value, patient-centered surgical care. However, pre-existing models are not validated to accurately predict risk for major gynecological oncology surgeries, and many are not generalizable to low- and middle-income country settings (LMICs). The international GO SOAR database dataset was used to develop a novel predictive surgical risk calculator for post-operative morbidity and mortality following gynecological surgery. Fifteen candidate features readily available pre-operatively across both high-income countries (HICs) and LMICs were selected. Predictive modeling analyses using machine learning methods and linear regression were performed. The area-under-the-receiver-operating characteristic curve (AUROC) was calculated to assess overall discriminatory performance. Neural networks (AUROC 0.94) significantly outperformed other models (p < 0.001) for evaluating the accuracy of prediction across three groups, i.e., minor morbidity (Clavien-Dindo I-II), major morbidity (Clavien-Dindo III-V), and no morbidity. Logistic-regression modeling outperformed the clinically established SORT model in predicting mortality (AUROC 0.66 versus 0.61, p < 0.001). The GO SOAR surgical risk prediction model is the first that is validated for use in patients undergoing gynecological surgery. Accurate surgical risk predictions are vital within the context of major cytoreduction surgery, where surgery and its associated complications can diminish quality-of-life and affect long-term cancer survival. A model that requires readily available pre-operative data, irrespective of resource setting, is crucial to reducing global surgical disparities.

Transfer Learning for Clinical Sleep Pose Detection Using a Single 2D IR Camera.

Sleep quality is an important determinant of human health and wellbeing. Novel technologies that can quantify sleep quality at scale are required to enable the diagnosis and epidemiology of poor sleep. One important indicator of sleep quality is body posture. In this paper, we present the design and implementation of a non-contact sleep monitoring system that analyses body posture and movement. Supervised machine learning strategies applied to noncontact vision-based infrared camera data using a transfer learning approach, successfully quantified sleep poses of participants covered by a blanket. This represents the first occasion that such a machine learning approach has been used to successfully detect four predefined poses and the empty bed state during 8-10 hour overnight sleep episodes representing a realistic domestic sleep situation. The methodology was evaluated against manually scored sleep poses and poses estimated using clinical polysomnography measurement technology. In a cohort of 12 healthy participants, we find that a ResNet-152 pre-trained network achieved the best performance compared with the standard de novo CNN network and other pre-trained networks. The performance of our approach was better than other video-based methods for sleep pose estimation and produced higher performance compared to the clinical standard for pose estimation using a polysomnography position sensor. It can be concluded that infrared video capture coupled with deep learning AI can be successfully used to quantify sleep poses as well as the transitions between poses in realistic nocturnal conditions, and that this non-contact approach provides superior pose estimation compared to currently accepted clinical methods.

Two-Step Deep Learning for Estimating Human Sleep Pose Occluded by Bed Covers.

In this study, a novel sleep pose identification method has been proposed for classifying 12 different sleep postures using a two-step deep learning process. For this purpose, transfer learning as an initial stage retrains a well-known CNN network (VGG-19) to categorise the data into four main pose classes, namely: supine, left, right, and prone. According to the decision made by VGG-19, subsets of the image data are next passed to one of four dedicated sub-class CNNs. As a result, the pose estimation label is further refined from one of four sleep pose labels to one of 12 sleep pose labels. 10 participants contributed for recording infrared (IR) images of 12 pre-defined sleep positions. Participants were covered by a blanket to occlude the original pose and present a more realistic sleep situation. Finally, we have compared our results with (1) the traditional CNN learning from scratch and (2) retrained VGG-19 network in one stage. The average accuracy increased from 74.5% & 78.1% to 85.6% compared with (1) & (2) respectively.

Sleep Posture Classification using a Convolutional Neural Network.

Sleep is a process of rest and renewal that is vital for humans. However, there are several sleep disorders such as rapid eye movement (REM) sleep behaviour disorder (RBD), sleep apnea, and restless leg syndrome (RLS) that can have an impact on a significant portion of the population. These disorders are known to be associated with particular behaviours such as specific body positions and movements. Clinical diagnosis requires patients to undergo polysomnography (PSG) in a sleep unit as a gold standard assessment. This involves attaching multiple electrodes to the head and body. In this experiment, we seek to develop non-contact approach to measure sleep disorders related to body postures and movement. An Infrared (IR) camera is used to monitor body position unaided by other sensors. Twelve participants were asked to adopt and then move through a set of 12 pre-defined sleep positions. We then adopted convolutional neural networks (CNNs) for automatic feature generation from IR data for classifying different sleep postures. The results show that the proposed method has an accuracy of between 0.76 & 0.91 across the participants and 12 sleepposes with, and without a blanket cover, respectively. The results suggest that this approach is a promising method to detect common sleep postures and potentially characterise sleep disorder behaviours.

Classification of awake, REM, and NREM from EEG via singular spectrum analysis.

In this study, a single-channel electroencephalography (EEG) analysis method has been proposed for automated 3-state-sleep classification to discriminate Awake, NREM (non-rapid eye movement) and REM (rapid eye movement). For this purpose, singular spectrum analysis (SSA) is applied to automatically extract four brain rhythms: delta, theta, alpha, and beta. These subbands are then used to generate the appropriate features for sleep classification using a multi class support vector machine (M-SVM). The proposed method provided 0.79 agreement between the manual and automatic scores.