Search

BACKGROUND: Remote patient monitoring (RPM), or telemonitoring, offers ways for health care practitioners to gather real-time information on the physiological conditions of patients. As telemedicine, and thus telemonitoring, is becoming increasingly relevant in today's society, understanding the practitioners' opinions is crucial. This systematic review evaluates the perspectives and experiences of health care practitioners with telemonitoring technologies. METHODS: A database search was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for the selection of articles measuring health care practitioners' perspectives and experiences with RPM technologies published between 2017 and 2021. Only articles written in English were included. No statistical analysis was performed and thus this is a qualitative review. RESULTS: A total of 1605 studies were identified after the initial search. After applying the inclusion and exclusion criteria of this review's authors, 13 articles were included in this review. In all, 2351 practitioners' perspectives and experience utilizing RPM technology in a variety of medical specialties were evaluated through close- and open-ended surveys. Recurring themes emerged for both the benefits and challenges. Common benefits included continuous monitoring of patients to provide prompt care, improvement of patient self-care, efficient communication, increased patient confidence, visualization of health trends, and greater patient education. Challenges comprised increased workload, higher patient anxiety, data inaccuracy, disorienting technology, financial issues, and privacy concerns. CONCLUSION: Health care practitioners generally believe that RPM is feasible for application. Additionally, there is a consensus that telemonitoring strategies will become increasingly relevant. However, there are still drawbacks to the technology that need to be considered. [ABSTRACT FROM AUTHOR]

(1) Background: Telemetry units allow the continuous monitoring of vital signs and ECG of patients. Such physiological indicators work as the digital signatures and biomarkers of disease that can aid in detecting abnormalities that appear before cardiac arrests (CAs). This review aims to identify the vital sign abnormalities measured by telemetry systems that most accurately predict CAs. (2) Methods: We conducted a systematic review using PubMed, Embase, Web of Science, and MEDLINE to search studies evaluating telemetry-detected vital signs that preceded in-hospital CAs (IHCAs). (3) Results and Discussion: Out of 45 studies, 9 met the eligibility criteria. Seven studies were case series, and 2 were case controls. Four studies evaluated ECG parameters, and 5 evaluated other physiological indicators such as blood pressure, heart rate, respiratory rate, oxygen saturation, and temperature. Vital sign changes were highly frequent among participants and reached statistical significance compared to control subjects. There was no single vital sign change pattern found in all patients. ECG alarm thresholds may be adjustable to reduce alarm fatigue. Our review was limited by the significant dissimilarities of the studies on methodology and objectives. (4) Conclusions: Evidence confirms that changes in vital signs have the potential for predicting IHCAs. There is no consensus on how to best analyze these digital biomarkers. More rigorous and larger-scale prospective studies are needed to determine the predictive value of telemetry-detected vital signs for IHCAs. [ABSTRACT FROM AUTHOR]

Sleep patterns vary widely between individuals. We explore methods for identifying populations exhibiting similar sleep patterns in an automated fashion using polysomnography data. Our novel approach applies unsupervised machine learning algorithms to hypnodensities graphs generated by a pre-trained neural network. In a population of 100 subjects we identify two stable clusters whose characteristics we visualize graphically and through estimates of total sleep time. We also find that the hypnodensity representation of the sleep stages produces more robust clustering results than the same methods applied to traditional hypnograms.

Predicting the ability of an individual to compensate for blood loss during hemorrhage and detect the likely onset of hypovolemic shock is necessary to permit early clinical intervention. Towards this end, the compensatory reserve metric (CRM) has been demonstrated to directly correlate with an individual's ability to maintain compensatory mechanisms during loss of blood volume from onset (one-hundred percent health) to exsanguination (zero percent health). This effort describes a lightweight, three-class predictor (good, fair, poor) of an individual's compensatory reserve using a linear support-vector machine (SVM) classifier. A moving mean filter of the predictions demonstrates a feasible model for implementation of real-time hypovolemia monitoring on a wearable device, requiring only 408 bytes to store the models' coefficients and minimal processor cycles to complete the computations.

We propose a Deep Convolutional Neural Network (CNN) architecture for computing a Compensatory Reserve Metric (CRM) for trauma victims suffering from hypovolemia (decreased circulating blood volume). The CRM is a single health indicator value that ranges from 100% for healthy individuals, down to 0% at hemodynamic decompensation - when the body can no longer compensate for blood loss. The CNN is trained on 20 second blood pressure waveform segments obtained from a finger-cuff monitor of 194 subjects. The model accurately predicts CRM when tested on data from 22 additional human subjects obtained from Lower Body Negative Pressure (LBNP) emulation of hemorrhage, attaining a mean squared error (MSE) of 0.0238 over the full range of values, including those from subjects with both low and high tolerance to central hypovolemia.

Continuous remote physiologic and environmental monitoring, employing an ever-increasing array of sensors, is now commonplace. Given the significant amount of data being digitized, two common sources of energy consumption can be targeted to improve device runtime: data storage and data transmission. One embedded method to maximize device runtime is inline low energy data compression. Herein we present a low complexity data encoding scheme. We list and characterize the parameters necessary for encoding. The encoding method is then evaluated and tuned using contrived data with varying degrees of covariance, as well as open-source electrocardiography (ECG) data. Finally, the encoding method is evaluated with tri-axial accelerometry and ECG data previously collected on a Mount Everest Expedition using a remote physiologic monitor that was specifically designed for long autonomous runtimes. With the described low overhead delta transition lossless encoding method, the Mt. Everest device runtime would have doubled from two to four weeks of continuous recording. Finally, this approach would be beneficial given a requirement to transmit data wirelessly in real time, since the total transmission power and energy would be reduced by an amount related to the compression ratio.