Atrial fibrillation (AF) is a type of cardiac arrhythmia affecting millions of people every year. This disease increases the likelihood of strokes, heart failure, and even death. While dedicated medical-grade electrocardiogram (ECG) devices can enable gold-standard analysis, these devices are expensive and require clinical settings. Recent advances in the capabilities of general-purpose smartphones and wearable technology equipped with photoplethysmography (PPG) sensors increase diagnostic accessibility for most populations. This work aims to develop a single model that can generalize AF classification across the modalities of ECG and PPG with a unified knowledge representation. This is enabled by approximating the transformation of signals obtained from low-cost wearable PPG sensors in terms of Pulse Rate Variability (PRV) to temporal Heart Rate Variability (HRV) features extracted from medical-grade ECG. This paper proposes a one-dimensional deep convolutional neural network that uses HRV-derived features for classifying 30-s heart rhythms as normal sinus rhythm or atrial fibrillation from both ECG and PPG-based sensors. The model is trained with three MIT-BIH ECG databases and is assessed on a dataset of unseen PPG signals acquired from wrist-worn wearable devices through transfer learning. The model achieved the aggregate binary classification performance measures of accuracy: 95.50%, sensitivity: 94.50%, and specificity: 96.00% across a five-fold cross-validation strategy on the ECG datasets. It also achieved 95.10% accuracy, 94.60% sensitivity, 95.20% specificity on an unseen PPG dataset. The results show considerable promise towards seamless adaptation of gold-standard ECG trained models for non-ambulatory AF detection with consumer wearable devices through HRV-based knowledge transfer.

Training machine learning and deep learning models for medical image classification is a challenging task due to a lack of large, high-quality labeled datasets. As the labeling of medical images requires considerable time and effort from medical experts, models need to be specifically designed to train on low amounts of labeled data. Therefore, an application of semi-supervised learning (SSL) methods provides one potential solution. SSL methods use a combination of a small number of labeled datasets with a much larger number of unlabeled datasets to achieve successful predictions by leveraging the information gained through unsupervised learning to improve the supervised model. This paper provides a comprehensive survey of the latest SSL methods proposed for medical image classification tasks.

Atrial fibrillation (AF) is a type of cardiac arrhythmia with a worldwide prevalence of more than 37 million among the adult population. This elusive disease is a major risk factor for ischemic stroke, along with increased rates of significant morbidity and eventual mortality. It is clinically diagnosed using medical-grade electrocardiogram (ECG) sensors in ambulatory settings. The recent emergence of consumer-grade wearables equipped with photoplethysmography (PPG) sensors has exhibited considerable promise for non-intrusive continuous monitoring in free-living conditions. However, the scarcity of large-scale public PPG datasets acquired from wearable devices hinders the development of intelligent automatic AF detection algorithms unaffected by motion artifacts, saturated ambient noise, inter- and intra-subject differences, or limited training data. In this work, we present a deep learning framework that leverages convolutional layers with a bidirectional long short-term memory (CNN-BiLSTM) network and an attention mechanism for effectively classifying raw AF rhythms from normal sinus rhythms (NSR). We derive and feed heart rate variability (HRV) and pulse rate variability (PRV) features as auxiliary inputs to the framework for robustness. A larger teacher model is trained using the MIT-BIH Arrhythmia ECG dataset. Through transfer learning (TL), its learned representation is adapted to a compressed student model (32x smaller) variant by using knowledge distillation (KD) for classifying AF with the UMass and MIMIC-III datasets of PPG signals. This results in the student model yielding average improvements in accuracy, sensitivity, F1 score, and Matthews correlation coefficient of 2.0%, 15.05%, 11.7%, and 9.85%, respectively, across both PPG datasets. Additionally, we employ Gradient-weighted Class Activation Mapping (Grad-CAM) to confer a notion of interpretability to the model decisions. We conclude that through a combination of techniques such as TL and KD, i.e., pre-trained initialization, we can utilize learned ECG concepts for scarcer PPG scenarios. This can reduce resource usage and enable deployment on edge devices.

Obstructive Sleep Apnea (OSA) is a prevalent chronic sleep-related breathing disorder characterized by partial or complete airway obstruction. The expensive, time-consuming, and labor-intensive nature of the gold-standard approach, polysomnography (PSG), and the lack of regular monitoring of patients’ daily lives with existing solutions motivates the development of clinical support for enhanced prognosis. In this study, we utilize image representations of sleep stages and contextual patient-specific data, including medical history and stage durations, to investigate the use of wearable devices for OSA screening and comorbid conditions. For this purpose, we leverage the publicly available Wisconsin Sleep Cohort (WSC) dataset. Given that wearable devices are adept at detecting sleep stages (often using proprietary algorithms), and medical history data can be efficiently captured through simple binary (yes/no) responses, we seek to explore neural network models with this. Without needing access to the raw physiological signals and using epoch-wise sleep scores and demographic data, we attempt to validate the effectiveness of screening capabilities and assess the interplay between sleep stages, OSA, insomnia, and depression. Our findings reveal that sleep stage representations combined with demographic data enhance the precision of OSA screening, achieving F1 scores of up to 69.40. This approach holds potential for broader applications in population health management as a plausible alternative to traditional diagnostic approaches. However, we find that purely modality-agnostic sleep stages for a single night and routine lifestyle information by themselves may be insufficient for clinical utility, and further work accommodating individual variability and longitudinal data is needed for real-world applicability.

Cloud computing has grown significantly in recent years and is now widely used by both individuals and businesses. Cloud service providers need to be prepared for failures to ensure that they can respond to them appropriately by minimizing downtime and achieving business continuity. This can be accomplished through fault tolerance mechanisms which aim to predict, prevent, and recover from failures. One of the common causes of task failures in the cloud is the deterioration of physical machines. If deterioration is detected in the physical machine, the virtual machines (VMs) being hosted must be moved to healthy physical machines. This paper proposes an approach to VM allocation in the event of host deterioration or failure. Namely, an integer linear programming optimization model is proposed for the allocation of the failing VMs while minimizing VM migration time. In addition, hybrid genetic and simulated annealing (HGA and HSA) algorithms are proposed for providing efficient solutions for the optimization model. The HGA is hybridized by a procedure that penalizes infeasible solutions to reduce their chances of being selected in the offspring populations and a hill-climbing procedure that modifies feasible solutions to produce better (or more fit) ones. The HSA starts from a feasible solution and also uses elitism as the HGA in its search to ensure that good candidate solutions are preserved. To validate the quality of the obtained solutions, we compare our approach to the commercial optimization solver CPLEX. In comparison to the CPLEX solver, the results show that for small size data center problems, the proposed HGA and HSA achieve near-optimal solutions with 70.80% and 81.43% increase in speed with an average solution quality trade-off by 20.57% and 78.52%, respectively. Notably, for medium, large and very large size problems the HGA and HSA obtained solutions where the CPLEX solver could not provide solutions within acceptable time. For medium size problems HGA attains solutions with better quality (75.82%) yet with higher execution time (57.27%). For large and very large problems HGA significantly outperforms HSA in terms of solution quality (better by 84.88% and 86.46%) yet with significantly higher execution time (74.22% and 76.55 %), respectively. Thus, the designer may choose which algorithm to use based on whether the focus is on quality or execution time.