Wearable Medical Sensors Research Articles

DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensors

Modern advances in machine learning (ML) and wearable medical sensors (WMSs) in edge devices have enabled ML-driven disease detection for smart healthcare. Conventional ML-driven methods for disease detection rely on customizing individual models for each disease and its corresponding WMS data. However, such methods lack adaptability to distribution shifts and new task classification classes. In addition, they need to be rearchitected and retrained from scratch for each new disease. Moreover, installing multiple ML models in an edge device consumes excessive memory, drains the battery faster, and complicates the detection process. To address these challenges, we propose DOCTOR, a multi-disease detection continual learning (CL) framework based on WMSs. It employs a multi-headed deep neural network (DNN) and a replay-style CL algorithm. The CL algorithm enables the framework to continually learn new missions in which different data distributions, classification classes, and disease detection tasks are introduced sequentially. It counteracts catastrophic forgetting with either a data preservation (DP) method or a synthetic data generation (SDG) module. The DP method preserves the most informative subset of real training data from previous missions for exemplar replay. The SDG module models the probability distribution of the real training data and generates synthetic data for generative replay while retaining data privacy. The multi-headed DNN enables DOCTOR to detect multiple diseases simultaneously based on user WMS data. We demonstrate DOCTOR’s efficacy in maintaining high disease classification accuracy with a single DNN model in various CL experiments. In complex scenarios, DOCTOR achieves 1.43× better average test accuracy, 1.25× better F1-score, and 0.41 higher backward transfer than the naïve fine-tuning framework, with a small model size of less than 350 KB.

Physics-Informed Transfer Learning to Enhance Sleep Staging.

At-home sleep staging using wearable medical sensors poses a viable alternative to in-hospital polysomnography due to its lower cost and lower disruption to the daily lives of patients, especially in the case of long-term monitoring. Machine learning with wearables however is difficult due to the paucity of data from wearable sensors, making automation a challenge. Transfer learning from hospital polysomnograms can boost performance, but is still hindered by differences between wearable and in-hospital EEG resulting in part from differing electrode placement. We improve transfer learning performance by using electrophysiological models of a human head to generate synthetic EEG resembling EEG from a wearable sensor. The data generation method utilizes Low-Resolution Electromagnetic Tomography Analysis (LORETA). Real EEG from standard in- hospital recordings is first mapped to point currents within the brain using LORETA, after which the point currents are used to estimate EEG that would have been recorded using a wearable sensor at any given point on the head. Augmenting source datasets with synthetic data statistically significantly boosted accuracy on a wearable sleep staging task from 80.8% to 81.3% on average, depending on the transfer learning parameters and data sources. Machine learning performance can be improved using data synthesized using physical models. Our approach represents a new form of transfer learning and demonstrates that incorporating domain knowledge of electrophysiological modeling can improve machine learning results for sleep staging tasks. We expect this approach to be particularly useful for EEG data which is hard to collect, or which is obtained using unusual electrode configurations.

Evaluation of Fatigue in Older Drivers Using a Multimodal Medical Sensor and Driving Simulator

In recent years, the spread of wearable medical sensors has made it possible to easily measure biological signals such as pulse rate and body acceleration (BA), and from these biological signals, it is possible to evaluate the degree of biological stress and autonomic nervous activity in daily life. Accumulated fatigue due to all-day work and lack of sleep is thought to be a contributing factor to distracted driving, and technology to estimate fatigue from biological signals during driving is desired. In this study, we investigated fatigue evaluation during a driving simulator (DS) using biological information on seven older subjects. A DS experiment was performed in the morning and afternoon, and no significant differences were observed in the change over time of heart rate variability and skin temperature. On the other hand, in the afternoon DS, changes in arousal and body movements were observed based on BA calculated from the three-axis acceleration sensor and fingertip reaction time in a psychomotor vigilance test. It is suggested that by combining biological information, it may be possible to evaluate the degree of fatigue from the presence or absence of arousal and changes in body movements while driving.

Reactive Aerosol Jet Printing of 2D and 3D Ag Patterns

Printed electronics is a rapidly growing field that involves the use of printing technologies to create electronic devices such as sensors, displays, and solar cells 1. Unlike traditional electronics, which rely on rigid and bulky components, printed electronics can be obtained on flexible and lightweight substrates such as plastic and paper, allowing the development of novel applications such as wearable electronics, smart packaging, and medical sensors. Printing technologies uniquely feature miniaturization and patterning capability at low-cost and high-throughput production. Among them, screen-printing, inkjet printing (IJP) and aerosol jet printing (AJP) are the most employed to fabricate conductive metallic patterns of Ag, Au, Cu and other metal nanoparticles (NPs). These printing techniques typically requires concentrated ink of metal NPs. However, specially in the case of IJP and AJP the synthesis of very small NPs (d < 100 nm) as well as proper ink formulation and long-time stability are major limitations to printing conductive metallic patterns 2.In this work, we propose an innovative method to produce 2D and 3D patterns and structures of Ag NPs by reactive Aerosol Jet Printing (r-AJP) on different substrates, using a custom-built aerosol jet printer. Ag NPs were in-situ reduced coupling two aerosol streams carrying the Ag precursor and a reducing agent, respectively. The process is fast, scalable and cheap. The electrical properties, in terms of both linear and areal electrical conductivity, of the r-AJP silver structures metallization patterns were investigated. Furthermore, the effect of both process parameters and precursor solution physical properties on printed Ag structure and morphology was assessed by x-ray diffraction (XRD) and scanning electron microscopy (SEM) in order to define the optimized condition for high definition 2d and 3D patterns by r-AJP. Bibliography P. Martins et al., Advanced Functional Materials, 33, 2213744 (2023).Y. Sui and C. A. Zorman, J. Electrochem. Soc., 167, 037571 (2020).

A full privacy-preserving distributed batch-based certificate-less aggregate signature authentication scheme for healthcare wearable wireless medical sensor networks (HWMSNs)

AbstractThe dynamic connectivity and functionality of sensors has revolutionized remote monitoring applications thanks to the combination of IoT and wireless sensor networks (WSNs). Wearable wireless medical sensor nodes allow continuous monitoring by amassing physiological data, which is very useful in healthcare applications. These text data are then sent to doctors via IoT devices so they can make an accurate diagnosis as soon as possible. However, the transmission of medical text data is extremely vulnerable to security and privacy assaults due to the open nature of the underlying communication medium. Therefore, a certificate-less aggregation-based signature system has been proposed as a solution to the issue by using elliptic curve public key cryptography (ECC) which allows for a highly effective technique. The cost of computing has been reduced by 93% due to the incorporation of aggregation technology. The communication cost is 400 bits which is a significant reduction when compared with its counterparts. The results of the security analysis show that the scheme is robust against forging, tampering, and man-in-the-middle attacks. The primary innovation is that the time required for signature verification can be reduced by using point addition and aggregation. In addition, it does away with the reliance on a centralized medical server in order to do verification. By taking a distributed approach, it is able to fully preserve user privacy, proving its superiority.

Adaptive Maximization of the Harvested Power for Wearable or Implantable Sensors With Coulomb Force Parametric Generators

Miniaturized wearable or implantable medical sensors (or actuators) are important components of the Internet of Things (IoT) in healthcare applications. However, their limited source of power is becoming a bottleneck for pervasive use of these devices, specially, as their functionality increases. Kinetic-based micro-energy harvesters can generate power through the natural human body motion. Therefore, they can be an attractive solution to supplement the source of power in medical wearables or implants. The architecture based on the Coulomb force parametric generator (CFPG) is the most viable micro-harvester solution for generating power from the human motion. This paper proposes three methods, namely, linear estimation approach, multi-armed bandit, a min-max-based approach to adaptively estimate the desirable electrostatic force in a CFPG using the input acceleration waveform. Through extensive simulations, the performance of the proposed methods in maximizing the output power of the micro-harvester is evaluated.

A wearable medical sensors system for in-situ monitoring vital signs of patients with hemorrhagic shock in big disaster scenes

In big disaster sites, such as earthquakes, wars, and traffic accidents, monitoring the vital signs of people with hemorrhagic shock is crucial for accurate injury classification and timely rescue. Clinical medical equipment is unsuitable for in-situ detection since large size and complex operations. In this paper, we propose a set of wearable medical sensors system that integrates bio-radar, wristwatch, nose clip, and biochemical sensor to monitor the vital signs of patients in big disaster scenes. This system offers portable advantages over bulky medical equipment and flexible measurement of blood pressure, heart rate, blood oxygen saturation, respiratory rate, body temperature, and levels of glucose, lactate, and hemoglobin (Hb). By addressing individual differences and improving the signal-to-noise ratio, the sensors system can achieve highly sensitive measurements online. Experimental studies on 15 patients in ICU wards reveal high uniformity of measurement results between our wearable sensors system and clinical equipment. Based on the data collected by the wearable sensor system and processed through a pre-established assessment model, color labels indicating severity levels will be presented to classify the injury degree for efficient rescue. Our proposed wearable medical sensor system contributes to saving more lives in big disaster scenes through accurate and timely measurement of vital signs.

Self-Powered Textile Triboelectric Pulse Sensor for Cardiovascular Monitoring.

Cardiovascular diseases have become a severe threat to human health. Fortunately, most of them can be effectively assessed and prevented through long-term monitoring of cardiovascular signals. Wearable medical sensors play an essential role in monitoring human physiological health, which are heading towards ultra-low power consumption, high sensitivity and stability. Furthermore, a comfortable wearable sensor also needs to be flexible and breathable. Here, a self-powered textile pulse sensor (STPS) based on triboelectric nanogenerator (TENG) is demonstrated for real-time monitoring of the radial artery pulse waveform. STPS can directly convert tiny pressure signals into electrical signals with excellent linearity (R2 = 0.996), low detection limit, and long-term stable performance (5×104 cycles). The flexible textile-based STPS can be conformally attached to the human body for continuously and stably recording physiological mechanical signals, which is expected to be utilized in the personalized cardiovascular pulse monitoring wearable devices in the Internet of Things era.

Wearable-Based Intelligent Emotion Monitoring in Older Adults during Daily Life Activities

We present a system designed to monitor the well-being of older adults during their daily activities. To automatically detect and classify their emotional state, we collect physiological data through a wearable medical sensor. Ground truth data are obtained using a simple smartphone app that provides ecological momentary assessment (EMA), a method for repeatedly sampling people’s current experiences in real time in their natural environments. We are making the resulting dataset publicly available as a benchmark for future comparisons and methods. We are evaluating two feature selection methods to improve classification performance and proposing a feature set that augments and contrasts domain expert knowledge based on time-analysis features. The results demonstrate an improvement in classification accuracy when using the proposed feature selection methods. Furthermore, the feature set we present is better suited for predicting emotional states in a leave-one-day-out experimental setup, as it identifies more patterns.

Federated Learning for Medical Imaging Segmentation via Dynamic Aggregation on Non-IID Data Silos

A large number of mobile devices, smart wearable devices, and medical and health sensors continue to generate massive amounts of data, making edge devices’ data explode and making it possible to implement data-driven artificial intelligence. However, the “data silos” and other issues still exist and need to be solved. Fortunately, federated learning (FL) can deal with “data silos” in the medical field, facilitating collaborative learning across multiple institutions without sharing local data and avoiding user concerns about data privacy. However, it encounters two main challenges in the medical field. One is statistical heterogeneity, also known as non-IID (non-independent and identically distributed) data, i.e., data being non-IID between clients, which leads to model drift. The second is limited labeling because labels are hard to obtain due to the high cost and expertise requirement. Most existing federated learning algorithms only allow for supervised training settings. In this work, we proposed a novel federated learning framework, MixFedGAN, to tackle the above issues in federated networks with dynamic aggregation and knowledge distillation. A dynamic aggregation scheme was designed to reduce the impact of current low-performing clients and improve stability. Knowledge distillation was introduced into the local generator model with a new distillation regularization loss function to prevent essential parameters of the global generator model from significantly changing. In addition, we considered two scenarios under this framework: complete annotated data and limited labeled data. An experimental analysis on four heterogeneous COVID-19 infection segmentation datasets and three heterogeneous prostate MRI segmentation datasets verified the effectiveness of the proposed federated learning method.

PMHE: a wearable medical sensor assisted framework for health care based on blockchain and privacy computing

Nowadays, smart medical cloud platforms have become a new direction in the industry. However, because the medical system involves personal physiological data, user privacy in data transmission and processing is also easy to leak in the smart medical cloud platform. This paper proposed a medical data privacy preserving framework named PMHE based on blockchain and fully homomorphic encryption technology. The framework receives personal physiological data from wearable devices on the client side, and uses blockchain as data storage to ensure that the data cannot be tampered with or forged; Besides, it uses fully homomorphic encryption method to design disease prediction models implemented by smart contracts. In PMHE, data is encoded and encrypted on the client side, and encrypted data is uploaded to the cloud platform via the public Internet, preventing privacy leakage caused by channel eavesdropping; smart contracts run on the blockchain platform for disease prediction, and the operators participating in computing are encrypted user data too. So, privacy and security issues caused by platform data leakage are avoided. The client-to-cloud interaction protocol is also designed to overcome the defect that fully homomorphic encryption only supports addition and multiplication by submitting tuples on the client side, to ensure that the prediction model can perform complex computing. In addition, the design of the smart contract is introduced in detail, and the performance of the system is analyzed. Finally, experiments are conducted to verify the operating effect of the system, ensuring that user privacy is not leaked without affecting the accuracy of the model, and realizing a smart medical cloud platform in which data can be used but cannot be borrowed.

MHDeep: Mental Health Disorder Detection System Based on Wearable Sensors and Artificial Neural Networks

Mental health problems impact the quality of life of millions of people around the world. However, diagnosis of mental health disorders is a challenging problem that often relies on self-reporting by patients about their behavioral patterns and social interactions. Therefore, there is a need for new strategies for diagnosis and daily monitoring of mental health conditions. The recent introduction of body-area networks consisting of a plethora of accurate sensors embedded in smartwatches and smartphones and edge-compatible deep neural networks (DNNs) points toward a possible solution. Such wearable medical sensors (WMSs) enable continuous monitoring of physiological signals in a passive and non-invasive manner. However, disease diagnosis based on WMSs and DNNs, and their deployment on edge devices, such as smartphones, remains a challenging problem. These challenges stem from the difficulty of feature engineering and knowledge distillation from the raw sensor data, as well as the computational and memory constraints of battery-operated edge devices. To this end, we propose a framework called MHDeep that utilizes commercially available WMSs and efficient DNN models to diagnose three important mental health disorders: schizoaffective, major depressive, and bipolar. MHDeep uses eight different categories of data obtained from sensors integrated in a smartwatch and smartphone. These categories include various physiological signals and additional information on motion patterns and environmental variables related to the wearer. MHDeep eliminates the need for manual feature engineering by directly operating on the data streams obtained from participants. Because the amount of data is limited, MHDeep uses a synthetic data generation module to augment real data with synthetic data drawn from the same probability distribution. We use the synthetic dataset to pre-train the weights of the DNN models, thus imposing a prior on the weights. We use a grow-and-prune DNN synthesis approach to learn both architecture and weights during the training process. We use three different data partitions to evaluate the MHDeep models trained with data collected from 74 individuals. We conduct two types of evaluations: at the data instance level and at the patient level. MHDeep achieves an average test accuracy, across the three data partitions, of 90.4%, 87.3%, and 82.4%, respectively, for classifications between healthy and schizoaffective disorder instances, healthy and major depressive disorder instances, and healthy and bipolar disorder instances. At the patient level, MHDeep DNN models achieve an accuracy of 100%, 100%, and 90.0% for the three mental health disorders, respectively, based on inference that uses 40, 16, and 22 minutes of sensor data collection from each patient.

Hospital selection framework for remote MCD patients based on fuzzy q-rung orthopair environment.

This research proposes a novel mobile health-based hospital selection framework for remote patients with multi-chronic diseases based on wearable body medical sensors that use the Internet of Things. The proposed framework uses two powerful multi-criteria decision-making (MCDM) methods, namely fuzzy-weighted zero-inconsistency and fuzzy decision by opinion score method for criteria weighting and hospital ranking. The development of both methods is based on a Q-rung orthopair fuzzy environment to address the uncertainty issues associated with the case study in this research. The other MCDM issues of multiple criteria, various levels of significance and data variation are also addressed. The proposed framework comprises two main phases, namely identification and development. The first phase discusses the telemedicine architecture selected, patient dataset used and decision matrix integrated. The development phase discusses criteria weighting by q-ROFWZIC and hospital ranking by q-ROFDOSM and their sub-associated processes. Weighting results by q-ROFWZIC indicate that the time of arrival criterion is the most significant across all experimental scenarios with (0.1837, 0.183, 0.230, 0.276, 0.335) for (q = 1, 3, 5, 7, 10), respectively. Ranking results indicate that Hospital (H-4) is the best-ranked hospital in all experimental scenarios. Both methods were evaluated based on systematic ranking and sensitivity analysis, thereby confirming the validity of the proposed framework.

Secured Health Monitoring System Using AES

Wireless medical sensor network is used in healthcare applications that have the collections of biosensors connected to a human body or emergency care unit to monitor the patient's physiological vital status. The real-time medical data collected using wearable medical sensors are transmitted to a diagnostic centre. The data generated from the sensors are aggregated at this centre and transmitted further to the doctor's personal digital assistant for diagnosis. The unauthorised access of one's health data may lead to misuse and legal complications while unreliable data transmission or storage may lead to life threatening risk to patients. So, this system uses Advanced Encryption Standard (AES) algorithm to encrypt the data to make it secured transmission and access control system for medical sensor network. Further the data is sent to a centralised server through a wireless network. In this case this server can be a Personal Computer (PC) connected to the same network, for this transmission User Datagram Protocol (UDP) can be used. This data can be accessed at the receiver side only.

Emerging Artificial Intelligence–Empowered mHealth: Scoping Review

BackgroundArtificial intelligence (AI) has revolutionized health care delivery in recent years. There is an increase in research for advanced AI techniques, such as deep learning, to build predictive models for the early detection of diseases. Such predictive models leverage mobile health (mHealth) data from wearable sensors and smartphones to discover novel ways for detecting and managing chronic diseases and mental health conditions.ObjectiveCurrently, little is known about the use of AI-powered mHealth (AIM) settings. Therefore, this scoping review aims to map current research on the emerging use of AIM for managing diseases and promoting health. Our objective is to synthesize research in AIM models that have increasingly been used for health care delivery in the last 2 years.MethodsUsing Arksey and O’Malley’s 5-point framework for conducting scoping reviews, we reviewed AIM literature from the past 2 years in the fields of biomedical technology, AI, and information systems. We searched 3 databases, PubsOnline at INFORMS, e-journal archive at MIS Quarterly, and Association for Computing Machinery (ACM) Digital Library using keywords such as “mobile healthcare,” “wearable medical sensors,” “smartphones”, and “AI.” We included AIM articles and excluded technical articles focused only on AI models. We also used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) technique for identifying articles that represent a comprehensive view of current research in the AIM domain.ResultsWe screened 108 articles focusing on developing AIM models for ensuring better health care delivery, detecting diseases early, and diagnosing chronic health conditions, and 37 articles were eligible for inclusion, with 31 of the 37 articles being published last year (76%). Of the included articles, 9 studied AI models to detect serious mental health issues, such as depression and suicidal tendencies, and chronic health conditions, such as sleep apnea and diabetes. Several articles discussed the application of AIM models for remote patient monitoring and disease management. The considered primary health concerns belonged to 3 categories: mental health, physical health, and health promotion and wellness. Moreover, 14 of the 37 articles used AIM applications to research physical health, representing 38% of the total studies. Finally, 28 out of the 37 (76%) studies used proprietary data sets rather than public data sets. We found a lack of research in addressing chronic mental health issues and a lack of publicly available data sets for AIM research.ConclusionsThe application of AIM models for disease detection and management is a growing research domain. These models provide accurate predictions for enabling preventive care on a broader scale in the health care domain. Given the ever-increasing need for remote disease management during the pandemic, recent AI techniques, such as federated learning and explainable AI, can act as a catalyst for increasing the adoption of AIM and enabling secure data sharing across the health care industry.

Toward an ultrasonic Internet of medical things

Wireless networked systems of “smart” miniaturized and electronically controlled implantable or wearable medical sensors and actuators will be the basis of many innovative and potentially revolutionary therapies and applications. The main obstacle in realizing this vision of smart networked implants is posed by the dielectric nature of the human body, which strongly attenuates radio-frequency electromagnetic waves used in traditional wireless technologies such as Bluetooth or WiFi. This talk will give an overview of our work exploring a radically different approach, i.e., establishing wireless networked systems in human tissues that transfer data and energy through acoustic waves at ultrasonic frequencies. We will start off by discussing applications of networked implantable medical systems.We will then analyze fundamental aspects of ultrasonic propagation in human tissues and their impact on the design of wireless networking protocols at different layers of the networking protocol stack. We will then review our work on designing and prototyping ultrasonically rechargeable and connected Internet-of-Things platforms through a closed-loop combination of mathematical modeling, simulation, and experimental evaluation.

Wearable Sensors for Vital Signs Measurement: A Survey

With the outbreak of coronavirus disease-2019 (COVID-19) worldwide, developments in the medical field have aroused concerns within society. As science and technology develop, wearable medical sensors have become the main means of medical data acquisition. To analyze the intelligent development status of wearable medical sensors, the current work classifies and prospects the application status and functions of wireless communication wearable medical sensors, based on human physiological data acquisition in the medical field. By understanding its working principles, data acquisition modes and action modes, the work chiefly analyzes the application of wearable medical sensors in vascular infarction, respiratory intensity, body temperature, blood oxygen concentration, and sleep detection, and reflects the key role of wearable medical sensors in human physiological data acquisition. Further exploration and prospecting are made by investigating the improvement of information security performance of wearable medical sensors, the improvement of biological adaptability and biodegradability of new materials, and the integration of wearable medical sensors and intelligence-assisted rehabilitation. The research expects to provide a reference for the intelligent development of wearable medical sensors and real-time monitoring of human health in the follow-up medical field.

Wearable Medical Sensor Devices, Machine and Deep Learning Algorithms, and Internet of Things-based Healthcare Systems in COVID-19 Patient Screening, Diagnosis, Monitoring, and Treatment

Wearable Medical Sensor Devices, Machine and Deep Learning Algorithms, and Internet of Things-based Healthcare Systems in COVID-19 Patient Screening, Diagnosis, Monitoring, and Treatment

Effective Resource Aware Health Care Monitoring in Body Sensor Network Platform Using Modified Particle Swarm Optimization

Real-time physiological data may be gathered using wearable medical sensors based on a network of body sensors. We do not however have an effective, trustworthy and secure body sensor network platform (BSN) that can satisfy growing e-health requirements. Many of these applications require BSN to provide the dependable and energy efficient data transfer of many data speeds. Cloud computing is giving assets to patient dependent on application request at SLA (service level agreement) rules. The service providers are focusing on giving the necessity based asset to satisfy the QoS (quality of service) prerequisites. Therefore, it has become an assessment to adapt service-oriented assets because of vulnerability and active interest for cloud services. The task scheduling is an option in contrast to appropriating asset by evaluating the inconsistent outstanding task at hand. the allocation of tasks given by the microprocessor Subsequently, a productive asset scheduling method needs to disseminate proper VMs (Virtual Machines). The swarm intelligence is appropriate to deal with such vulnerability issues carefully. In this paper, an effective resource scheduling strategy Utilizing Modified Particle Swarm Optimization approach (MPSO) is presented, with a target to limit execution cost that gives an approach for the microprocessor to deal with the multiple number of tasks gives to the controllers in order to perform the multiple tasks that gets logged in the cloud via Internet of things technology (Iot), energy consumed, bandwidth consumption, speed and execution cost. The near investigation of results has been exhibited that the presented scheduling scheme performed better when contrasted with existing evaluation. In this manner, the presented resource scheduling approach might be utilized to enhance the viability of cloud resources.

CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks

The novel coronavirus (SARS-CoV-2) has led to a pandemic. The current testing regime based on Reverse Transcription-Polymerase Chain Reaction for SARS-CoV-2 has been unable to keep up with testing demands, and also suffers from a relatively low positive detection rate in the early stages of the resultant COVID-19 disease. Hence, there is a need for an alternative approach for repeated large-scale testing of SARS-CoV-2/COVID-19. The emergence of wearable medical sensors (WMSs) and deep neural networks (DNNs) points to a promising approach to address this challenge. WMSs enable continuous and user-transparent monitoring of physiological signals. However, disease detection based on WMSs/DNNs and their deployment on resource-constrained edge devices remain challenging problems. To address these problems, we propose a framework called CovidDeep that combines efficient DNNs with commercially available WMSs for pervasive testing of the virus and the resultant disease. CovidDeep does not depend on manual feature extraction. It directly operates on WMS data and some easy-to-answer questions in a questionnaire whose answers can be obtained through a smartphone application. We collected data from 87 individuals, spanning three cohorts including healthy, asymptomatic (to detect the virus), and symptomatic (to detect the disease) patients. We trained DNNs on various subsets of the features automatically extracted from six WMS and questionnaire categories to perform ablation studies to determine which subsets are most efficacious in terms of test accuracy for a three-way classification. The highest test accuracy obtained was 98.1%. The models were also shown to perform well on other performance measures, such as false positive rate, false negative rate, and F1 score. We augmented the real training dataset with a synthetic training dataset drawn from the same probability distribution to impose a prior on DNN weights and leveraged a grow-and-prune synthesis paradigm to learn both DNN architecture and weights. This boosted the accuracy of the various DNNs further and simultaneously reduced their size and floating-point operations. This makes the CovidDeep DNNs both accurate and efficient, in terms of memory requirements and computations. The resultant DNNs are embedded in a smartphone application, which has the added benefit of preserving patient privacy.