Recent progress in large-scale electrocardiogram (ECG) analysis has yielded cardiologist-level performance, albeit on uni-labeled datasets. However, in the real-world, ECG recordings often have markers of multiple labels like those in the PhysioNet Challenge 2020 dataset (PNC20DB). In the proposed classification strategy, we employ a novel class-distribution rebalancing approach, followed by a hybrid deep learning architecture to manage such multi-class multi-label (MCML) and class-imbalanced datasets. In the hybrid architecture, we pass 12-lead ECG data through a convolution neural network (CNN) and only Lead II ECG data through a residual network (ResNet). We also include domain features as a third processing unit. Finally, we employ k-means on the window-level predictions generated by the concatenation layer to obtain the final class-prediction. The proposed classification model is evaluated on the PNC20DB consisting of 27-class, 12-lead, MCML ECG recordings. The proposed architecture beats the leading entries of PhysioNet Challenge 2020 (PNC2020) and recent state-of-the-art techniques in a five-fold cross-validation method. It generates median AUROC and AUPRC of 94.1% and 56.2%, respectively. It also yields a median PNC2020 challenge metric of 60.4.

Stress management is paramount to maintaining optimal health and well-being; stress builds up in spikes, causing problems like hypertension and anxiety, necessitating personalized interventions delivered in real-time through wearable technology. This work underscores the pivotal role of unobtrusive stress detection and presents the development of auto-generated compact models tailored for on-device inference through Neural Architecture Search (NAS). These models aim to facilitate efficient stress monitoring directly on low-power devices, representing a promising avenue for advancing personalized healthcare with continuous monitoring and effective digital interventions.

Atrial Fibrillation (AF) is a common cardiac arrhythmia with significant health implications. To evaluate the severity of AF and monitor the effectiveness of treatments, continuous measurement of AF Burden (AFB) is crucial. This demo showcases a cost-effective, portable, and user-friendly solution for AFB monitoring. Our system integrates the Arduino Nano 33 BLE sense board with the AD8232 sensor to reliably capture single-lead ECG data. Additionally, a custom algorithm computes real-time AFB, providing insights into the frequency and duration of AF episodes. This system has the potential to enhance AF management and patient care, making cardiac health monitoring more accessible.

Abstract Recognizing patient activity in real‐time from video or images collected by a CCTV camera available in the hospital during a Covid‐19 situation has proven challenging. The dilemma of patient activity recognition is identifying and recognizing a patient's various actions in a series of videos. The process presented in our paper needs to achieve unrestricted, generic behavior in videos. Detecting events in any video is often difficult because we use Bidirectional ConvLSTM to create a robust patient in the sense behaviors (PSB) framework capable of eliminating certain barriers. To begin this paper by proposing a new Bidirectional ConvLSTM for establishing a stable PSB scheme. Our proposed model is capable of accurately predicting patient's behaviors like seated, standing, and so on. Using Bidirectional ConvLSTM, learning information from a pre‐trained model is an excellent place to start for rapidly developing a new PSB system using a current PSB database, as both the source and target datasets are critical. All parameters are frozen in a pre‐trained PSB device. Then, using the UCI and HMDB51 dataset to train the model, variables and local relations are progressively fixed. A novel PSB framework is developed using the target dataset. Relevant tests are conducted using commonly used research indices to assess prediction precision accuracy. They acknowledge six patient's behavior with a weighted accuracy rate of 92%. For recognizing novel activity, laying, the precision of a corresponding prediction is the best, 91%, of all six test results. The proposed work uses bidirectional ConvLSTM with modified activation layers to sense the patients' behavior. This article may be a patient activity recognition system to identify an individual. It takes a clip of COVID‐19 patients as input and looks for matches inside the hold‐on images.

Freezing of Gait (FoG) is a paroxysmal and devitalizing symptom associated with Parkinson’s disease (PD). Episodes of FoG impedes gait and augments fall propensity, often leading to serious fall-injury. In this paper, we present a method for online detection of FoG using a wearable motion sensor. The novelty lies in utilizing the Empirical Wavelet Transform for signal denoising and incorporating the two new features to ameliorate the accuracy of the algorithm. Fundamentally, we have focused on a patient-independent model and leveraged a single ankle sensor which makes it a more feasible approach in terms of usability. Our model is evaluated on Daphnet dataset and achieved the average Sensitivity of.95 and Specificity of.70 with only a single sensor, demonstrating its immense potential.