User Orientation Detection in Relation to Antenna Geometry in Ultra-Wideband Wireless Body Area Networks Using Deep Learning

In this paper, the issue of detecting a user's position in relation to the antenna geometry in ultra-wideband (UWB) off-body wireless body area network (WBAN) communication using deep learning methods is presented. To measure the impulse response of the channel, a measurement stand consisting of EVB1000 devices and DW1000 radio modules was developed and indoor static measurement scenarios were performed. It was proven that for the binary classification of user orientation, neural networks achieved accuracy that was more than 9% higher than that for the well-known threshold method. In addition, the classification of user position angles relative to the reference node was analyzed. It was proven that, using the proposed deep learning approach and the channel impulse response, it was possible to estimate the angle of the user's position in relation to the antenna geometry. Absolute user orientation angle errors of about 4-7° for convolutional neural networks and of about 14-15° for multilayer perceptrons were achieved in approximately 85% of the cases in both tested scenarios.

Design and Analysis of High-Capacity MIMO System in Line-of-Sight Communication

The phase of the channel matrix elements has a significant impact on channel capacity in a mobile multiple-input multiple-output (MIMO) communication system, notably in line-of-sight (LoS) communication. In this paper, the general expression for the phase of the channel matrix at maximum channel capacity is determined. Moreover, the optimal antenna configuration of the 2 × 2 and 3 × 3 transceiver antenna array is realized for LoS communication, providing methods for n×n optimal antenna placement, which can be used in short-range LoS communication and non-scattering environment communication, such as coupling train communication and inter-satellite communication. Simulation results show that the 2 × 2 rectangular antenna array is more suitable for the communication of coupling trains, while the 3 × 3 circular arc antenna array is more suitable for virtual coupling trains according to antenna configurations. Moreover, the 2 × 2 antenna rectangular configuration proposed in this paper has reached the optimal channel in inter-satellite communication, which lays a foundation for the deployment of communication systems.

COVID-19 in Multimorbid Patients-A Controlled Microcost Description Analysis of Diagnosis Related Group (DRG)-Case Series in Acute Care without Non-Invasive Ventilation

Diagnosis-related cost analyzes are important for health economic planning and decision-making. They form the basis for further developing of remuneration systems for health services. The rapid increase in hospital stays by COVID-19 patients requires a valid and exact calculation of the treatment costs. COVID-19 patients with many accompanying illnesses increase the requirements for a cost calculation. The focus of this work is to carry out a DRG-related micro-cost analysis, considering the age, length of stay and comorbidities of COVID-19 patients. So far, there is little information about treatment costs for multimorbid patients with COVID-19 who have not received invasive ventilation. The method is based on a standardized cost unit calculation for determining the treatment costs in a German hospital. The costs (€) of inpatients treated with COVID-19 were compared with a control group of the same DRGs of patients without COVID-19. The average total costs for inpatient treatment were €2866. The highest share of costs falls on nursing, personnel, and material costs of the non-medical infrastructure. Frequent comorbidities were heart failure, diabetes mellitus, other respiratory diseases, dizziness, and impairment of the musculoskeletal system.

A multicenter propensity score matched analysis in 73,843 patients of an association of nutritional risk with mortality, length of stay and readmission rates

BACKGROUND

The reported prevalences and effects of nutritional risk vary widely in the literature because of both methodological differences (e.g., screening tools and statistical analyses) and different patient populations.

OBJECTIVE

In this study the authors analyzed in-hospital mortality, 30-d mortality, readmission within 4 mo, and justified length of stay (jLoS) (determined by governmental assessment to justify financial compensation) in hospitalized patients nutritionally at risk compared with hospitalized patients not at risk.

DESIGN

This was a multicenter retrospective cohort study in 6 Belgian hospitals among inpatients in 2018. Propensity score matching was applied, including comorbidity score and exact matching for hospital, age group, sex, type of admission, living situation, and medical specialty.

RESULTS

In total, 73,843 of 85,677 patients were screened at admission, with 16,141 found to have nutritional risk (prevalence of 21.9%). Oncology patients had the highest risk prevalence of 38.3%, whereas patients receiving plastic or reconstructive surgery had a prevalence of 5.2%. Patients nutritionally at risk had higher odds of dying in the hospital (5.1% compared with 3.3%; OR: 1.56; 95% CI: 1.37, 1.76), dying within 30 d of admission (6.8% compared with 4.3%; OR: 1.62; 95% CI: 1.45, 1.81) and being readmitted within 4 mo after discharge (35.5% compared with 32.9%; OR: 1.12; 95% CI: 1.07, 1.18). These differences were consistent across hospitals. The association between being nutritionally at risk and jLoS was ambiguous.

CONCLUSIONS

One out of 5 patients included in this study was nutritionally at risk. Using propensity score matching, higher odds of in-hospital mortality, readmission, and 30-d mortality were observed. In contrast to oft-reported increased length of stay with poor nutrition, propensity matched data for jLoS suggested that this association was less pronounced in this cohort.

Predicting Postoperative Length of Stay for Isolated Coronary Artery Bypass Graft Patients Using Machine Learning

Purpose

Predictive analytics (PA) is a new trending approach in the field of healthcare that uses machine learning to build a prediction model using supervised learning algorithms. Isolated coronary artery bypass grafting (iCABG), an open-heart surgery, is commonly performed in the treatment of coronary heart disease.

Aim

The aim of this study was to develop and evaluate a model to predict postoperative length of stay (PLoS) for iCABG patients using supervised machine learning techniques, and to identify the features with the highest contribution to the model.

Methods

This is a retrospective study that uses historic data of adult patients who underwent isolated CABG (iCABG). After initial data pre-processing, data imputation using the kNN method was applied. The study used five prediction models using Naïve Bayes, Decision Tree, Random Forest, Logistic Regression and k Nearest Neighbor algorithms. Data imbalance was managed using the following widely used methods: oversampling, undersampling, "Both", and random over-sampling examples (ROSE). The features selection process was conducted using the Boruta method. Two techniques were applied to examine the performance of the models, (70%, 30%) split and cross-validation, respectively. Models were evaluated by comparing their performance using AUC and other metrics.

Results

In the final dataset, six distinct features and 621 instances were used to develop the models. A total of 20 models were developed using R statistical software. The model generated using Random Forest with "Both" resampling method and cross-validation technique was deemed the best fit (AUC=0.81; F1 score=0.82; and recall=0.82). Attributes found to be highly predictive of PLoS were pulmonary artery systolic, age, height, EuroScore II, intra-aortic balloon pump used, and complications during operation.

Conclusion

This study demonstrates the significance and effectiveness of building a model that predicts PLoS for iCABG patients using patient specifications and pre-/intra-operative measures.