With the booming development of medical informatization and the ubiquitous connections in the fifth generation mobile communication technology (5G) era, the heterogeneity and explosive growth of medical data have brought huge challenges to data access, security and privacy, as well as information processing in Internet of Medical Things (IoMT). This article provides a comprehensive review of how to realize the timely processing and analysis of medical big data and the sinking of high-quality medical resources under the constraints of the existing medical environment and medical-related equipment. We mainly focus on the advantages brought by the cloud computing, edge computing and artificial intelligence technologies to the IoMT. We also explore how to rationalize the use of medical resources and the security and privacy of medical data, so that high-quality medical services can be provided to patients. Finally, we discuss the current challenges and possible future research directions in the edge-cloud computing and artificial intelligence related IoMT.

During the outbreak of the Coronavirus disease 2019 (COVID-19), while bringing various serious threats to the world, it reminds us that we need to take precautions to control the transmission of the virus. The rise of the Internet of Medical Things (IoMT) has made related data collection and processing, including healthcare monitoring systems, more convenient on the one hand, and requirements of public health prevention are also changing and more challengeable on the other hand. One of the most effective nonpharmaceutical medical intervention measures is mask wearing. Therefore, there is an urgent need for an automatic real-time mask detection method to help prevent the public epidemic. In this article, we put forward an edge computing-based mask (ECMask) identification framework to help public health precautions, which can ensure real-time performance on the low-power camera devices of buses. Our ECMask consists of three main stages: 1) video restoration; 2) face detection; and 3) mask identification. The related models are trained and evaluated on our bus drive monitoring data set and public data set. We construct extensive experiments to validate the good performance based on real video data, in consideration of detection accuracy and execution time efficiency of the whole video analysis, which have valuable application in COVID-19 prevention.

Recently, wearable devices have got increasing popularity in wide applications in medical and disaster rescue efforts to ensure the health and safety of users, which facilitates the development of the Internet of Medical Things (IoMT). Due to the posture alteration and mobility of users, the topology of the IoMT changes frequently, which increases the difficulty for resource allocation and routing strategy. In this paper, we respectively probe into the health monitoring architectures of the IoMT for both individual and group, allowing the monitored users to move at will. Furtherly, combined with the diversity of disaster rescuers, we build an IoMT-based disaster rescuer health monitoring system with searchers, doctors and porters. For each application, we point out the enabling technologies and demonstrate the existing researches. It is worth noting that the complexity of environment and high mobility of rescuers increase the probability of route breakage. Thus, this paper creatively addresses effective routing repair solutions for route breakage in IoMT-based disaster rescuer health monitoring system by exploiting the mobility of rescuers. Finally, we forecast three most likely directions in the field of IoMTs.

Background: Parkinson disease (PD) is a common movement disorder. Patients with PD have multiple gait impairments that result in an increased risk of falls and diminished quality of life. Therefore, gait measurement is important for the management of PD. Objective: We previously developed a smartphone-based dual-task gait assessment that was validated in healthy adults. The aim of this study was to test the validity of this gait assessment in people with PD, and to examine the association between app-derived gait metrics and the clinical and functional characteristics of PD. Methods: Fifty-two participants with clinically diagnosed PD completed assessments of walking, Movement Disorder Society Unified Parkinson Disease Rating Scale III (UPDRS III), Montreal Cognitive Assessment (MoCA), Hamilton Anxiety (HAM-A), and Hamilton Depression (HAM-D) rating scale tests. Participants followed multimedia instructions provided by the app to complete two 20-meter trials each of walking normally (single task) and walking while performing a serial subtraction dual task (dual task). Gait data were simultaneously collected with the app and gold-standard wearable motion sensors. Stride times and stride time variability were derived from the acceleration and angular velocity signal acquired from the internal motion sensor of the phone and from the wearable sensor system. Results: High correlations were observed between the stride time and stride time variability derived from the app and from the gold-standard system (r=0.98-0.99, P<.001), revealing excellent validity of the app-based gait assessment in PD. Compared with those from the single-task condition, the stride time (F1,103=14.1, P<.001) and stride time variability (F1,103=6.8, P=.008) in the dual-task condition were significantly greater. Participants who walked with greater stride time variability exhibited a greater UPDRS III total score (single task: β=.39, P<.001; dual task: β=.37, P=.01), HAM-A (single-task: β=.49, P=.007; dual-task: β=.48, P=.009), and HAM-D (single task: β=.44, P=.01; dual task: β=.49, P=.009). Moreover, those with greater dual-task stride time variability (β=.48, P=.001) or dual-task cost of stride time variability (β=.44, P=.004) exhibited lower MoCA scores. Conclusions: A smartphone-based gait assessment can be used to provide meaningful metrics of single- and dual-task gait that are associated with disease severity and functional outcomes in individuals with PD.

Classification of Alzheimer's Disease (AD) has been becoming a hot issue along with the rapidly increasing number of patients. This task remains tremendously challenging due to the limited data and the difficulties in detecting mild cognitive impairment (MCI). Existing methods use gait [or EEG (electroencephalogram)] data only to tackle this task. Although the gait data acquisition procedure is cheap and simple, the methods relying on gait data often fail to detect the slight difference between MCI and AD. The methods that use EEG data can detect the difference more precisely, but collecting EEG data from both HC (health controls) and patients is very time-consuming. More critically, these methods often convert EEG records into the frequency domain and thus inevitably lose the spatial and temporal information, which is essential to capture the connectivity and synchronization among different brain regions. This paper proposes a cascade neural network with two steps to achieve a faster and more accurate AD classification by exploiting gait and EEG data simultaneously. In the first step, we propose attention-based spatial temporal graph convolutional networks to extract the features from the skeleton sequences (i.e., gait) captured by Kinect (a commonly used sensor) to distinguish between HC and patients. In the second step, we propose spatial temporal convolutional networks to fully exploit the spatial and temporal information of EEG data and classify the patients into MCI or AD eventually. We collect gait and EEG data from 35 cognitively health controls, 35 MCI, and 17 AD patients to evaluate our proposed method. Experimental results show that our method significantly outperforms other AD diagnosis methods (91.07 vs. 68.18%) in the three-way AD classification task (HC, MCI, and AD). Moreover, we empirically found that the lower body and right upper limb are more important for the early diagnosis of AD than other body parts. We believe this interesting finding can be helpful for clinical researches.