Search

Background Liver-type fatty acid–binding protein (L-FABP) is a promising biomarker for the early prediction of acute kidney injury (AKI). However, the clinical utility of L-FABP in different populations or settings remains unclear. We present a meta-analysis of studies evaluating the performance of L-FABP in AKI prediction. Methods We performed a literature search in MEDLINE, EMBASE, and Cochrane library, using search terms “acute kidney injury” and “L-FABP.” Studies investigating the performance characteristics of L-FABP for the early diagnosis of AKI were included. Data about patient characteristics, diagnostic criteria of AKI, quantitative data required for construction of a 2 × 2 table (number of participants, sensitivity, specificity, and case number), study settings, and outcomes were extracted. The bivariable model was applied to calculate the estimated sensitivity and specificity of L-FABP. A summary ROC curve was created by plotting the true-positive rate against the false-positive rate at various cutoff values from different studies. Results We found 27 studies reporting measurement of urine (n = 25 studies) or plasma (n = 2 studies) L-FABP. Overall, the estimated sensitivity was 0.74 (95% CI: 0.69–0.80) and specificity was 0.78 (95% CI: 0.71–0.83). L-FABP demonstrated a stable area under the ROC of 0.82 (95% CI: 0.79–0.85) in variable clinical settings including intensive care unit, surgery, and contrast-induced AKI. In subgroup analysis excluding pediatric and post radiocontrast exposure cohorts, L-FABP had comparative diagnostic performance with neutrophil gelatinase associated lipocalin (NGAL). Conclusions Despite broad prevalence, L-FABP is a clinically useful marker with moderate accuracy in variable clinical settings as demonstrated in our subgroup analysis. Except for pediatric patients and those post-radiocontrast exposure, L-FABP has comparable discriminative capability as NGAL.

Localization is the foundation of location-based services and has received considerable attention recently. Pedestrian dead-reckoning (PDR) systems are widely used to infer user positions. However, a main problem is that the errors may easily accumulate during multiple integrations. In this research, we exploit the frequency shift of a wave caused by relative movement, i.e., the Doppler effect, of feet to infer user movement for locating user’s location. Specifically, when the two feet of a person move, the relative movements exhibit self-Doppler effect. This observation allows us to implement a PDR system by mounting two speakers and one microphone on shoes. The advantage is that the displacement can be inferred by integration once, as opposed to twice for accelerometers. To investigate the performance of our system, we evaluate its capability in measuring step event, step length, and step direction. Field trial results are presented, which show that our approach performs very well in step detection with 99.6% accuracy and step length estimation with error $\approx 0.0073$ m. However, its direction estimation is still not accurate enough and, thus, needs the help of other sensors.

This paper proposes to train a group of badminton serving machines by a simple deep neural network (DNN) consisting of 8 dense layers. Our ultimate goal is to have the proposed system reproduce a badminton rally captured from social media such as YouTube. All the parameters of these serving machines need to be predicted from a trajectory image in a race video through a deep learning regression model. We can successfully estimate 10 trajectory parameters with an average RMSE loss of 0.087.

Rehabilitation and physical therapies can recover people suffering from neurological disorder. Due to limited medical personnels, there are not enough medical personnels help patients with their posture diagnosis. In this paper, we propose a 3D gait tracking method to help medical personnels monitor patients. Based on acoustic signals, our approach derives displacement by only one integration of velocity. When one walks, his feet move back and forth, causing relative movements to our acoustic sensors, which we call self-Doppler effect. We utilize three buzzers and one microphone mounted on feet to collect the frequency shifts caused by relative movements and measure 3D trajectories. We validate through simulations that this approach would perform very well. In real experiments, due to the existence of noise and the limitation of hardware, we observe an average error of 0.1669 m in step length estimation and 0.0867 m in step height estimation.

In industrialized countries, Mycobacterium avium complex and other nontuberculous mycobacteria (NTM) are major causes of opportunistic infection–related deaths in HIV patients. However, in resource-limited regions, data on NTM are scarce, and tuberculosis (TB) was often assumed to be the cause of death in HIV patients with a positive acid-fast smear. We searched MEDLINE and Embase databases for studies on autopsied HIV patients in sub-Saharan Africa published between January 1997 and April 2020. We included studies that reported histopathological or microbiological evidences for diagnosis of TB and NTM infection. We excluded articles without mycobacterial evidence from culture or molecular testing, such as those that used verbal autopsy, death certificates, or national registry data (systematic review registration number: CRD42019129836 at PROSPERO). We included six eligible studies that reported 391 autopsies in sub-Saharan African HIV patients. The prevalence of NTM and TB at autopsy ranged from 1.3% to 27.3% and 11.8% to 48.7%, respectively. The weighted prevalence ratio of NTM versus TB was 0.16 indicating that for every seven HIV patients died with mycobacterial infections, there was one died with NTM infection. Of the 13 NTM infections, six were caused by M. avium complex. Mycobacterium avium complex and other NTM infections are important differential diagnoses of TB at the time of death among HIV patients in sub-Saharan Africa. Our findings highlight the need to systematically survey the prevalence of NTM infections among HIV patients seeking medical care in resource-limited regions.

With the growth of aging population, elder care service has become an important part of the service industry of Internet of Things. Activity monitoring is one of the most important services in the field of the elderly care service. In this paper, we proposed a wearable solution to provide an activity monitoring service on elders for caregivers. The system uses wireless signals to estimate calorie burned by the walking and localization. In addition, it also uses wireless motion sensors to recognize physical activity, such as drinking and restroom activity. Overall, the system can be divided into four parts: wearable device, gateway, cloud server, and caregiver's android application. The algorithms we proposed for drinking activity are Decision Tree (J48) and Random Forest (RF). While for restroom activity, we proposed supervised Reduced Error Pruning (REP) Tree and Variable Order Hidden Markov Model (VOHMM). We developed a prototype service Android app to provide a life log for the recording of the activity sequence which would be useful for the caregiver to monitor elder activity and its calorie consumption.

Recent advances in technology have led to the rapid development of the Internet of Things (IoT) and the use of smartphones. The phenomenon has been widely influenced by the use of smart sensors, the accuracy of which is critical to the quality of service provided. Hence, it is vital that sensors are calibrated at both the device and software levels. Some applications even rely on environment-dependent sensing results. Floor detection by barometers is one example, where the pressure of a floor actually depends on the base reference pressure. This observation motivates us to study the floor detection problem by using barometers with device-to-device (D2D) communications. In this paper, we propose the Floor Calibration Protocol (FCP), which enables a mobile device to be calibrated with other mobile devices and anchor devices by considering both temporal and spatial factors. We conducted trace- based simulations to evaluate the proposed scheme and compared its performance with that of state- of-the-art approaches to validate the efficacy of our protocol.

Recently, elder care services, especially for those with chronic diseases, have become an important application in the field of IoT. Several studies have reported that the progress of chronic diseases can be slowed down effectively by moderate physical activities. In this paper, we propose an activity intensity monitoring system to support continuous monitoring of indoor calorie consumption. The system uses wireless signals to infer calorie burned in walking. In the proposed system, Bluetooth smart beacons are deployed in various spaces of a house. The elders who wear smart wristbands are continuously monitored for their locations by received wireless signals. The system has the following features. First, it utilizes wireless signals as location and activity intensity indicators; inertial sensors are only used in the training stage. Second, it is semi-training free and only needs relatively short training time to start using the monitoring services. Finally, the system is map-free, in the sense that it can be easily deployed without constructing the interior map of the house. A prototype system is implemented on a smartphone to evaluate the feasibility of the proposed system.

This paper proposes a continuous location and skeletal tracking system using multiple RGB-Depth sensors (such as Kinects) deployed along a corridor with overlapping coverages. First, we transform the coordinates of all sensor into a unified coordinate. Second, the system recognizes users (such as patients under rehabilitation) from different views of these sensors and classifies them by their patient IDs. Third, the patient information can be continuously handed over among sensors when they move around the area. Experiment results show that the skeletal association during handover achieves approximately 90.61% in accuracy and 96.89% in precision in 44,817 experiment trials. By our observation, injured people possess asymmetric gait parameters especially on the ratio of the duration of the swing/stance phase. For example, the injured foot generally has a longer swinging duration than the healthy side. The proposed system has potential in patient rehabilitation monitoring applications.