In recent years, wearable devices have attracted attention because of their ability to enhance the quality of life. This disruptive technology has helped healthcare professionals with intervening early in chronic diseases, especially amongst independently living patients, and has facilitated real-time monitoring of patients’ vital signs remotely. One of the major bottlenecks that hampers the adoption of wearable device is continuous power supply. Most wearable devices solely depend on battery supply. When the energy stored in the battery is depleted, the operation of wearable devices is affected. To overcome this limitation, efficient energy harvesters for wearable devices are crucial. The paper primarily aims to present a comprehensive classification of different energy sources that can be capitalised to power wearable devices. In addition, this research paper deals with the key challenges that must be considered in the development of autonomous wearable devices for telemedicine applications with a proposed system design for wearable device that uses energy harvesting technology.

Individualized health-care is gaining traction recently due to the advances in sensor technology, edge computing and the improvement in communication technologies. In this work, we show the application of wearable device for mobile health-care along with supporting algorithms using photoplethysmogram (PPG) as our signal source. We introduce the design of our wearable device equipped PPG sensors for extracting valuable bio-information from the human body. Using our device, we introduce Centralized State Sensing (CSS), an algorithm that improves the estimation of different health parameters. By using heart rate estimation as an example, the proposed algorithm is 26.8% better in terms of mean absolute error when compared with the average reading taken across sensors. We also propose a deep neural network model applied to a PPG-glucose dataset containing 349 samples provided by our industry partner for non-invasive blood glucose estimation achieving an accuracy of 84.29% based on ISO:15197:2013 standard.

Digital microfluidic biochips (DMFBs) are being increasingly used for DNA sequencing, point-of-care clinical diagnostics, and immunoassays. DMFBs based on a micro-electrode-dot-array (MEDA) architecture have recently been proposed, and fundamental droplet manipulations, e.g., droplet mixing and splitting, have also been experimentally demonstrated on MEDA biochips. There can be thousands of microelectrodes on a single MEDA biochip, and the fine-grained control of nanoliter volumes of biochemical samples and reagents is also enabled by this technology. MEDA biochips offer the benefits of real-time sensitivity, lower cost, easy system integration with CMOS modules, and full automation. This review paper first describes recent design tools for high-level synthesis and optimization of map bioassay protocols on a MEDA biochip. It then presents recent advances in scheduling of fluidic operations, placement of fluidic modules, droplet-size-aware routing, adaptive error recovery, sample preparation, and various testing techniques. With the help of these tools, biochip users can concentrate on the development of nanoscale bioassays, leaving details of chip optimization and implementation to software tools.

Emotion is a crucial aspect of human health, and emotion recognition systems serve important roles in the development of neurofeedback applications. Most of the emotion recognition methods proposed in previous research take predefined EEG features as input to the classification algorithms. This paper investigates the less studied method of using plain EEG signals as the classifier input, with the residual networks (ResNet) as the classifier of interest. ResNet having excelled in the automated hierarchical feature extraction in raw data domains with vast number of samples (e.g., image processing) is potentially promising in the future as the amount of publicly available EEG databases has been increasing. Architecture of the original ResNet designed for image processing is restructured for optimal performance on EEG signals. The arrangement of convolutional kernel dimension is demonstrated to largely affect the models performance on EEG signal processing. The study is conducted on the Shanghai Jiao Tong University Emotion EEG Dataset (SEED), with our proposed ResNet18 architecture achieving 93.42 accuracy on the 3-class emotion classification, compared to the original ResNet18 at 87.06 accuracy. Our proposed ResNet18 architecture has also achieved a model parameter reduction of 52.22 from the original ResNet18. We have also compared the importance of different subsets of EEG channels from a total of 62 channels for emotion recognition. The channels placed near the anterior pole of the temporal lobes appeared to be most emotionally relevant. This agrees with the location of emotion-processing brain structures like the insular cortex and amygdala.

Owing to the rapid progress in artificial intelligence (AI) and the widespread use of generative learning, the problem of sparse data has been solved effectively in various research fields. The application of AI technologies has resulted in important transformations in healthcare, particularly in radiology. To ensure the high quality, safety, and effectiveness of AI and machine learning (ML) medical devices, the US Food and Drug Administration (FDA) has established regulatory guidelines to support the performance evaluation of medical devices. Furthermore, the FDA has proposed continuous surveillance requirements for AI/ML medical devices. This paper presents a summary of SaMD products that have passed the FDA 510 (k) AI/ML pathway, the challenges associated with the current AI/ML software-as-a-medical-device, and solutions for promoting the development of AI technologies in medicine. We hope to provide valuable information pertaining to medical-device design, development, and monitoring to ultimately achieve safer and more effective personalized medical services.

To evaluate ways to improve the generalizability of a deep learning algorithm for identifying glaucomatous optic neuropathy (GON) using a limited number of fundus photographs, as well as the key features being used for classification. A total of 944 fundus images from Taipei Veterans General Hospital (TVGH) were retrospectively collected. Clinical and demographic characteristics, including structural and functional measurements of the images with GON, were recorded. Transfer learning based on VGGNet was used to construct a convolutional neural network (CNN) to identify GON. To avoid missing cases with advanced GON, an ensemble model was adopted in which a support vector machine classifier would make final classification based on cup-to-disc ratio if the CNN classifier had low-confidence score. The CNN classifier was first established using TVGH dataset, and then fine-tuned by combining the training images of TVGH and Drishti-GS datasets. Class activation map (CAM) was used to identify key features used for CNN classification. Performance of each classifier was determined through area under receiver operating characteristic curve (AUC) and compared with the ensemble model by diagnostic accuracy. In 187 TVGH test images, the accuracy, sensitivity, and specificity of the CNN classifier were 95.0%, 95.7%, and 94.2%, respectively, and the AUC was 0.992 compared to the 92.8% accuracy rate of the ensemble model. For the Drishti-GS test images, the accuracy of the CNN, the fine-tuned CNN and ensemble model was 33.3%, 80.3%, and 80.3%, respectively. The CNN classifier did not misclassify images with moderate to severe diseases. Class-discriminative regions revealed by CAM co-localized with known characteristics of GON. The ensemble model or a fine-tuned CNN classifier may be potential designs to build a generalizable deep learning model for glaucoma detection when large image databases are not available.