MEC-Based Jamming-Aided Anti-Eavesdropping with Deep Reinforcement Learning for WBANs

Wireless body area network (WBAN) suffers secure challenges, especially the eavesdropping attack, due to constraint resources. In this article, deep reinforcement learning (DRL) and mobile edge computing (MEC) technology are adopted to formulate a DRL-MEC-based jamming-aided anti-eavesdropping (DMEC-JAE) scheme to resist the eavesdropping attack without considering the channel state information. In this scheme, a MEC sensor is chosen to send artificial jamming signals to improve the secrecy rate of the system. Power control technique is utilized to optimize the transmission power of both the source sensor and the MEC sensor to save energy. The remaining energy of the MEC sensor is concerned to ensure routine data transmission and jamming signal transmission. Additionally, the DMEC-JAE scheme integrates with transfer learning for a higher learning rate. The performance bounds of the scheme concerning the secrecy rate, energy consumption, and the utility are evaluated. Simulation results show that the DMEC-JAE scheme can approach the performance bounds with high learning speed, which outperforms the benchmark schemes.

Machine-learning based prediction of hypo- and hyperglycemia from electronic health records (Preprint)

BACKGROUND The increasing need for blood glucose (BG) management in hospitalized patients poses high demands on clinical staff and health care systems alike. Acute decompensations of BG levels (hypo- and hyperglycemia) adversely affect patient outcomes and safety. OBJECTIVE Acute BG decompensations pose a frequent and significant risk for inpatients. Ideally, proactive measures are taken before BG levels derail. We have generated a broadly applicable multiclass classification model for predicting decompensation events from patients’ electronic health records to indicate where adjustments of patient monitoring and/or therapeutic interventions are required. METHODS A retrospective cohort study was conducted of patients hospitalized at a tertiary hospital in Bern, Switzerland. Using patient details and routine data from electronic health records (EHRs), a multiclass prediction model for BG decompensation events (< 3.9 mmol/L (hypoglycemia), or > 10, > 13.9, or > 16.7 mmol/L (representing different degrees of hyperglycemia)) was generated, based on a second-level ensemble of gradient-boosted binary trees. RESULTS 63’579 hospital admissions of 33’212 patients were included in this study. The multiclass prediction model reached a specificity of 93.0%, 98.5%, and 93.6% and a sensitivity of 69.6%, 63.0%, and 65.5%, for the main categories of interest. i.e., non-decompensated cases, hypo- or hyperglycemia, respectively. The median prediction horizon was seven and four hours for hypo- and hyperglycemia, respectively. CONCLUSIONS EHRs hold the potential to reliably predict all kinds of BG decompensations. Readily available patient details and routine laboratory data can support the decisions for proactive interventions and thus help to reduce the detrimental health effects of hypo- and hyperglycemia.

Organizational, Technical and Behavioral Factors Associated with Malaria Routine Data Reporting among Health Workers in Selected Health Facilities in Trans-Nzoia County, Kenya

Purpose: Malaria remains to be among the primary causes of sickness, infirmity and cases of deaths and has continued to negatively affect health and socio-economic progress in the country. Rapid reporting of malaria cases could avert prospective epidemics which would lead to a high proportion of sickness and deaths. The study, therefore, sought to assess the determinants of malaria routine data reporting among health workers in selected health facilities in Trans-Nzoia County. Methodology: A descriptive cross-sectional study was conducted to evaluate the organizational, technical, and behavioral aspects that influence the reporting of malaria routine data among health workers. The sample size was 123 health facilities that were selected randomly based on their strata. Research tools that were utilized were structured questionnaires, focused group discussion, and key informant interview guide. Chi-square (χ2) was used to test the hypothesis with a p ≤ 0.05 being considered significant. Findings: The findings on socio-demographic characteristics indicated that majority of the research participants were females 76(62.6%), had college education 85(69.1%) and 81 (65.9%) had worked in the health facility for 5 to 10 years. Most 76(61.8%) of the health facilities were Level 3 (Health Centres). There was significant relationship between level of health facility and malaria routine data reporting at (χ2 =9.999, df=3, p-value = 0.019). Other organizational factors that had significant association with malaria routine data reporting (p< 0.001) include inadequate budget, low staffing, poor ICT infrastructure and complex data management procedures. In terms of technical aspects, limited training on technologies had significant relationship with malaria routine data reporting (p< 0.001). Regarding behavioral aspects, identified factors include lack of incentives and inadequate resources. Unique contribution to theory, practice and policy: The outcomes of the study provide proof for support, tactical organization, and collaboration in the health sector in Trans-Nzoia County as well as to the other developmental agencies working in the field of malaria control. The study recommends that the county government of Trans-Nzoia should provide adequate funds and ICT infrastructure to boost malaria routine data reporting. The county department of health with support from the national government through Division of National Malaria Program (DNMP )should consistently conduct in-service training, support supervision and data quality audits.

Co-establishing an infrastructure for routine data collection to address disparities in infant mortality: planning and implementation

Background Efforts to address infant mortality disparities in Ohio have historically been adversely affected by the lack of consistent data collection and infrastructure across the community-based organizations performing front-line work with expectant mothers, and there is no established template for implementing such systems in the context of diverse technological capacities and varying data collection magnitude among participating organizations. Methods Taking into account both the needs and limitations of participating community-based organizations, we created a data collection infrastructure that was refined by feedback from sponsors and the organizations to serve as both a solution to their existing needs and a template for future efforts in other settings. Results By standardizing the collected data elements across participating organizations, integration on a scale large enough to detect changes in a rare outcome such as infant mortality was made possible. Datasets generated through the use of the established infrastructure were robust enough to be matched with other records, such as Medicaid and birth records, to allow more extensive analysis. Conclusion While a consistent data collection infrastructure across multiple organizations does require buy-in at the organizational level, especially among participants with little to no existing data collection experience, an approach that relies on an understanding of existing barriers, iterative development, and feedback from sponsors and participants can lead to better coordination and sharing of information when addressing health concerns that individual organizations may struggle to quantify alone.

Automated provision of clinical routine data for a complex clinical follow-up study: A data warehouse solution

A deep integration of routine care and research remains challenging in many respects. We aimed to show the feasibility of an automated transformation and transfer process feeding deeply structured data with a high level of granularity collected for a clinical prospective cohort study from our hospital information system to the study’s electronic data capture system, while accounting for study-specific data and visits. We developed a system integrating all necessary software and organizational processes then used in the study. The process and key system components are described together with descriptive statistics to show its feasibility in general and to identify individual challenges in particular. Data of 2051 patients enrolled between 2014 and 2020 was transferred. We were able to automate the transfer of approximately 11 million individual data values, representing 95% of all entered study data. These were recorded in n = 314 variables (28% of all variables), with some variables being used multiple times for follow-up visits. Our validation approach allowed for constant good data quality over the course of the study. In conclusion, the automated transfer of multi-dimensional routine medical data from HIS to study databases using specific study data and visit structures is complex, yet viable.

Risk Indicators Improve the Prescription Quality of Drugs with Anticholinergic Properties in Nursing Homes

Aim: The objective of this study was to assess the impact of a collaborative therapeutic optimization program on the rate of potentially inappropriate prescription of drugs with anticholinergic properties in nursing homes. Methods: Quasi-experimental study in 37 nursing homes in France. The intervention included the use of quality indicators for prescriptions combined with educational sessions and dedicated materials for nursing home staff (unlimited access to study material for staff, including nurses, general practitioners, pharmacists). Indicators were calculated based on routine data collected from an electronic pill dispenser system. The primary outcome was the presence of at least one prescription containing ≥1 drug from a list of 12 drugs with anticholinergic properties. A difference-in-differences analysis was conducted at 18 months as well as propensity score weighting to minimize any potential indication bias. A generalized estimating equation model estimated the probability of being prescribed at least one target drug at any time during a 9-month period for each resident. Results: In total, 33 nursing homes (intervention group: n = 10; control group: n = 23) were included, totalling 8137 residents. There was a decrease in the use of drugs with anticholinergic properties over time in both groups, as well as a decline in the intervention group compared to the control group (Odds Ratio: 0.685, 95% CI: 0.533, 0.880; p < 0.01) that was attributable to the intervention. An estimated 49 anticholinergic properties drug prescriptions were avoided by the intervention. Conclusion: This study found that an intervention based on indicators derived from routine prescription data was effective in reducing use of drugs with anticholinergic properties prescriptions in nursing homes.

Seismic activity on the territory of Slovakia in 2020

The National Network of Seismic Stations of Slovakia (NNSS) consists of eight short period and six broadband permanent seismic stations and a data centre located at the Earth Science Institute of the Slovak Academy of Sciences (ESI SAS). The NNSS recorded and detected 11229 seismic events from all epicentral distances in 2020. Totally 96 earthquakes originated in the territory of Slovakia in 2020. This paper provides basic information on the configuration of the NNSS, routine data processing, seismic activity on the territory of Slovakia in 2020 as well as macroseismic observations collected in 2020.

The association between midwifery staffing levels and the experiences of mothers on postnatal wards: cross sectional analysis of routine data

Background Women have consistently reported lower satisfaction with postnatal care compared with antenatal and labour care. The aim of this research was to examine whether women's experience of inpatient postnatal care in England is associated with variation in midwifery staffing levels. Methods Analysis of data from the National Maternity Survey in 2018 including 17,611 women from 129 organisations. This was linked to hospital midwifery staffing numbers from the National Health Service (NHS) Workforce Statistics and the number of births from Hospital Episode Statistics. A two-level logistic regression model was created to examine the association of midwifery staffing levels and experiences in post-natal care. Results The median full time equivalent midwives per 100 births was 3.55 (interquartile range 3.26 to 3.78). Higher staffing levels were associated with less likelihood of women reporting delay in discharge (adjusted odds ratio [aOR] 0.849, 95% CI 0.753 to 0.959, p=0.008), increased chances of women reporting that staff always helped in a reasonable time aOR1.200 (95% CI 1.052, 1.369, p=0.007) and that they always had the information or explanations they needed aOR 1.150 (95% CI 1.040, 1.271, p=0.006). Women were more likely to report being treated with kindness and understanding with higher staffing, but the difference was small and not statistically significant aOR 1.059 (0.949, 1.181, p=0.306). Conclusions Negative experiences for women on postnatal wards were more likely to occur in trusts with fewer midwives. Low staffing could be contributing to discharge delays and lack of support and information, which may in turn have implications for longer term outcomes for maternal and infant wellbeing.