Ten years of laser-induced graphene: impact and future prospect on biomedical, healthcare, and wearable technology.

Since its introduction in 2014, laser-induced graphene (LIG) from commercial polymers has been gaining interests in both academic and industrial sectors. This can be clearly seen from its mass adoption in various fields ranging from energy storage and sensing platforms to biomedical applications. LIG is a 3-dimensional, nanoporous graphene structure with highly tuneable electrical, physical, and chemical properties. LIG can be easily produced by single-step laser scribing at normal room temperature and pressure using easily accessible commercial level laser machines and materials. With the increasing demand for novel wearable devices for biomedical applications, LIG on flexible substrates can readily serve as a technological platform to be further developed for biomedical applications such as point-of-care (POC) testing and wearable devices for healthcare monitoring system. This review will provide a comprehensive grounding on LIG from its inception and fabrication mechanism to the characterization of its key functional properties. The exploration of biomedicals applications in the form of wearable and point-of-care devices will then be presented. Issue of health risk from accidental exposure to LIG will be covered. Then LIG-based wearable devices will be compared to devices of different materials. Finally, we discuss the implementation of Internet of Medical Things (IoMT) to wearable devices and explore and speculate on its potentials and challenges.

Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection.

Smartwatch health sensor data are increasingly utilized in smart health applications and patient monitoring, including stress detection. However, such medical data often comprise sensitive personal information and are resource-intensive to acquire for research purposes. In response to this challenge, we introduce the privacy-aware synthetization of multi-sensor smartwatch health readings related to moments of stress, employing Generative Adversarial Networks (GANs) and Differential Privacy (DP) safeguards. Our method not only protects patient information but also enhances data availability for research. To ensure its usefulness, we test synthetic data from multiple GANs and employ different data enhancement strategies on an actual stress detection task. Our GAN-based augmentation methods demonstrate significant improvements in model performance, with private DP training scenarios observing an 11.90-15.48% increase in F1-score, while non-private training scenarios still see a 0.45% boost. These results underline the potential of differentially private synthetic data in optimizing utility-privacy trade-offs, especially with the limited availability of real training samples. Through rigorous quality assessments, we confirm the integrity and plausibility of our synthetic data, which, however, are significantly impacted when increasing privacy requirements.

An Explainable Deep Learning Approach for Stress Detection in Wearable Sensor Measurements.

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose a Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE), to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress-detection methodologies in terms of precision, recall, and interpretability. The results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on.

A Conditional GAN for Generating Time Series Data for Stress Detection in Wearable Physiological Sensor Data.

Human-centered applications using wearable sensors in combination with machine learning have received a great deal of attention in the last couple of years. At the same time, wearable sensors have also evolved and are now able to accurately measure physiological signals and are, therefore, suitable for detecting body reactions to stress. The field of machine learning, or more precisely, deep learning, has been able to produce outstanding results. However, in order to produce these good results, large amounts of labeled data are needed, which, in the context of physiological data related to stress detection, are a great challenge to collect, as they usually require costly experiments or expert knowledge. This usually results in an imbalanced and small dataset, which makes it difficult to train a deep learning algorithm. In recent studies, this problem is tackled with data augmentation via a Generative Adversarial Network (GAN). Conditional GANs (cGAN) are particularly suitable for this as they provide the opportunity to feed auxiliary information such as a class label into the training process to generate labeled data. However, it has been found that during the training process of GANs, different problems usually occur, such as mode collapse or vanishing gradients. To tackle the problems mentioned above, we propose a Long Short-Term Memory (LSTM) network, combined with a Fully Convolutional Network (FCN) cGAN architecture, with an additional diversity term to generate synthetic physiological data, which are used to augment the training dataset to improve the performance of a binary classifier for stress detection. We evaluated the methodology on our collected physiological measurement dataset, and we were able to show that using the method, the performance of an LSTM and an FCN classifier could be improved. Further, we showed that the generated data could not be distinguished from the real data any longer.

A Physiological Sensor-Based Android Application Synchronized with a Driving Simulator for Driver Monitoring.

In this paper, we present an Android application to control and monitor the physiological sensors from the Shimmer platform and its synchronized working with a driving simulator. The Android app can monitor drivers and their parameters can be used to analyze the relation between their physiological states and driving performance. The app can configure, select, receive, process, represent graphically, and store the signals from electrocardiogram (ECG), electromyogram (EMG) and galvanic skin response (GSR) modules and accelerometers, a magnetometer and a gyroscope. The Android app is synchronized in two steps with a driving simulator that we previously developed using the Unity game engine to analyze driving security and efficiency. The Android app was tested with different sensors working simultaneously at various sampling rates and in different Android devices. We also tested the synchronized working of the driving simulator and the Android app with 25 people and analyzed the relation between data from the ECG, EMG, GSR, and gyroscope sensors and from the simulator. Among others, some significant correlations between a gyroscope-based feature calculated by the Android app and vehicle data and particular traffic offences were found. The Android app can be applied with minor adaptations to other different users such as patients with chronic diseases or athletes.

Infection prevention and early warning in neonatal intensive care unit based on physiological sensor monitoring.

The infection rate in the Neonatal Intensive Care Unit (NICU) is very high, which is also one of the important causes of morbidity and even death in critically ill neonates and premature infants. At present, the monitoring system of the Neonatal Intensive Care Unit is not very complete, and it is difficult to provide early warning of neonatal illness. Coupled with the untimely response measures, it has brought certain difficulties to the ward's infection prevention and control work. The rapid development of the Internet of Things (IoT) in recent years has made the application fields of various sensor devices more and more extensive. This paper studied infection prevention and early warning in the Neonatal Intensive Care Unit based on physiological sensors. Combined with a wireless network and physiological sensors, this paper built an intelligent monitoring system for the Neonatal Intensive Care Unit, which aimed to monitor various physiological data of newborns in real-time and dynamically, and gave early warning signals, so that medical staff could take preventive measures in time. The experiments showed that the monitoring system proposed in this paper could obtain the physiological information of neonates in time, which brought convenience to prevention and early warning work, and reduced the infection rate of neonatal wards by 7.39%.

Emerging Implantable Energy Harvesters and Self-Powered Implantable Medical Electronics.

Implantable energy harvesters (IEHs) are the crucial component for self-powered devices. By harvesting energy from organisms such as heartbeat, respiration, and chemical energy from the redox reaction of glucose, IEHs are utilized as the power source of implantable medical electronics. In this review, we summarize the IEHs and self-powered implantable medical electronics (SIMEs). The typical IEHs are nanogenerators, biofuel cells, electromagnetic generators, and transcutaneous energy harvesting devices that are based on ultrasonic or optical energy. A benefit from these technologies of energy harvesting in vivo, SIMEs emerged, including cardiac pacemakers, nerve/muscle stimulators, and physiological sensors. We provide perspectives on the challenges and potential solutions associated with IEHs and SIMEs. Beyond the energy issue, we highlight the implanted devices that show the therapeutic function in vivo.

A highly stretchable and conductive 3D porous graphene metal nanocomposite based electrochemical-physiological hybrid biosensor.

Recently, highly stretchable and flexible electrodes essential for wearable electronic devices has been reported. However, their electrical resistances are high, the fabrication processes are complicated and involve a high cost, and deformations such as stretching can lead to the degradation on electrical performance. To address these issues, a novel fabrication process (both inexpensive and simple) for the highly stretchable and conductive electrodes using well patterned 3D porous laser-induced graphene silver nanocomposite was developed. The fabricated electrode exhibited a high, uniform electrical conductivity even under mechanical deformations. Addition of platinum and gold nanoparticles (PtAuNP) on the 3D porous LIG greatly improved the electrochemical performance for wearable glucose sensor applications. The fabricated glucose sensor exhibited low detection limit (5 µM), and acceptable detection range from 0 to 1.1 mM (covers the glucose range in sweat), and high linearity (0.99). In addition, the fabricated pH sensor also exhibited a linear response (66 mV/pH) at the range from 4 to 7. This work successfully demonstrates the potential of this novel fabrication technique and stretchable LIG metal nanocomposite for wearable electrochemical-physiological hybrid biosensors.

Are We There Yet? Feasibility of Continuous Stress Assessment via Wireless Physiological Sensors.

Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol and drug use), and lead to cardiovascular diseases and cancer. Continuous assessment of stress from sensors can be used for timely delivery of a variety of interventions to reduce or avoid stress. We investigate the feasibility of continuous stress measurement via two field studies using wireless physiological sensors - a four-week study with illicit drug users (n = 40), and a one-week study with daily smokers and social drinkers (n = 30). We find that 11+ hours/day of usable data can be obtained in a 4-week study. Significant learning effect is observed after the first week and data yield is seen to be increasing over time even in the fourth week. We propose a framework to analyze sensor data yield and find that losses in wireless channel is negligible; the main hurdle in further improving data yield is the attachment constraint. We show the feasibility of measuring stress minutes preceding events of interest and observe the sensor-derived stress to be rising prior to self-reported stress and smoking events.