Operational State Recognition of a DC Motor Using Edge Artificial Intelligence.

Edge artificial intelligence (EDGE-AI) refers to the execution of artificial intelligence algorithms on hardware devices while processing sensor data/signals in order to extract information and identify patterns, without utilizing the cloud. In the field of predictive maintenance for industrial applications, EDGE-AI systems can provide operational state recognition for machines and production chains, almost in real time. This work presents two methodological approaches for the detection of the operational states of a DC motor, based on sound data. Initially, features were extracted using an audio dataset. Two different Convolutional Neural Network (CNN) models were trained for the particular classification problem. These two models are subject to post-training quantization and an appropriate conversion/compression in order to be deployed to microcontroller units (MCUs) through utilizing appropriate software tools. A real-time validation experiment was conducted, including the simulation of a custom stress test environment, to check the deployed models' performance on the recognition of the engine's operational states and the response time for the transition between the engine's states. Finally, the two implementations were compared in terms of classification accuracy, latency, and resource utilization, leading to promising results.

Poor stroke risk perception despite moderate public stroke awareness: insight from a cross-sectional national survey in Greece.

BACKGROUND: Although stroke is the fourth cause of death in Western societies, public stroke awareness remains suboptimal. The aim of this study was to estimate stroke risk perception and stroke awareness in Greece through a cross-sectional telephone survey. METHODS: A trained interview team conducted this cross-sectional telephone survey between February and April 2014 using an online structured questionnaire. Participants were selected using random digit dialing of landline and mobile telephone numbers with quota sampling weighted for geographical region based on the most recent General Population Census (2011). RESULTS: Between February and April 2014, 723 individuals (418 women [58%], 47.4 ± 17.8 years) agreed to respond. Among all respondents, 642 (88.8%) were able to provide at least 1 stroke risk factor; 673 respondents (93.08%) were able to provide correctly at least 1 stroke symptom or sign. When asked what would they do in case of acute onset of stroke symptoms, 497 (68.7%) responded that they would either call the ambulance or visit the closest emergency department. Only 35.3%, 18.9%, 17.2%, 20.7%, and 15.0% of respondents with atrial fibrillation, arterial hypertension, dyslipidemia, diabetes mellitus, and current smoking, respectively, considered themselves as being in high risk for stroke. CONCLUSIONS: Stroke risk perception in Greece is low despite moderate public stroke awareness.

ALTAI Tool for Assessing AI-Based Technologies: Lessons Learned and Recommendations from SHAPES Pilots.

Across European countries, the SHAPES Project is piloting AI-based technologies that could improve healthcare delivery for older people over 60 years old. This article aims to present a study developed inside the SHAPES Project to find a theoretical framework focused on AI-assisted technology in healthcare for older people living in the home, to assess the SHAPES AI-based technologies using the ALTAI tool, and to derive ethical recommendations regarding AI-based technologies for ageing and healthcare. The study has highlighted concerns and reservations about AI-based technologies, namely dealing with living at home, mobility, accessibility, data exchange procedures in cross-board cases, interoperability, and security. A list of recommendations is built not only for the healthcare sector, but also for other pilot studies.

Introducing New Paths towards Public Primary Healthcare Services in Greece: Efforts for Scaling-Up Mental Healthcare Services Addressed to Older Adults.

The exponential growth in the aging population challenges the Primary Care Providers (PCPs) who provide health care services to older adults who are considered highly vulnerable and are in need of specialized healthcare services. The development of new policies and the adoption of appropriate health strategies by PCPs may improve the early detection and prevention of mental disorders in older adults. This reduces both queuing and costs in outpatient clinics while preventing stigma for patients and families. To this end, specialized training for PCPs at the Local Primary Health Care Unit (LPHCU) was provided in order to conduct efficient assessments of older adults (65 and above years old, without previously diagnosed depression or dementia, and willing to participate). The assessment is based on the Mini Mental State Examination (MMSE) and Geriatric Depression Scale (GDS). Older adults identified with MMSE <20 and GDS >5 were referred to the psychiatric outpatient clinic. The aim of this study is to discuss evidence-informed policymaking in Greece with a focus on advancing mental health practices and scaling up quality primary healthcare services for older adults.

A Cybersecurity Culture Survey Targeting Healthcare Critical Infrastructures.

Recent studies report that cybersecurity breaches noticed in hospitals are associated with low levels of personnel's cybersecurity awareness. This work aims to assess the cybersecurity culture in healthcare institutions from middle- to low-income EU countries. The evaluation process was designed and performed via anonymous online surveys targeting individually ICT (internet and communication technology) departments and healthcare professionals. The study was conducted in 2019 for a health region in Greece, with a significant number of hospitals and health centers, a large hospital in Portugal, and a medical clinic in Romania, with 53.6% and 6.71% response rates for the ICT and healthcare professionals, respectively. Its findings indicate the necessity of establishing individual cybersecurity departments to monitor assets and attitudes while underlying the importance of continuous security awareness training programs. The analysis of our results assists in comprehending the countermeasures, which have been implemented in the healthcare institutions, and consequently enhancing cybersecurity defense, while reducing the risk surface.

The role of local primary healthcare units in increasing immunization uptake among children in vulnerable social groups through vaccination campaigns.

The objective of this study was to evaluate the potential of a tailored health promotion and vaccination campaign conducted by a Local Primary Health Care Unit (LPHCU), in increasing children's immunization uptake of vulnerable social groups. The LPHCU of Ampelokipi, Larissa, Greece conducted an immunization campaign in accordance with the National Vaccination Program within a Roma settlement of Larissa, a population of approximately 4500 people, including 1500 children aged 2 months to 16 years. To ensure community engagement, the settlement's Roma mediator and the associated Medical Social Centre participated in the design and implementation of the campaign, facilitating coherent and precise communications about the campaign goals and methods. The campaign consisted of peer-to-peer communications with parents/guardians, followed by medical examination and vaccination of children, as well as scheduling of appointments for monitoring children's development. The communication messages presented vaccines as a health solution to parents and advised about personal hygiene and healthy diet habits. House-to-house health promotion visits were conducted to all houses of the settlement. From April 2019 to March 2020, a total of 704 vaccines were administered to 381 Roma children, conforming to the National Vaccination Programme of Greece. Our study demonstrated that LPHCU's have the potential to enhance confidence between healthcare providers and vulnerable social groups, towards disease prevention and to increase immunization uptake. Vaccination campaigns should be organized systematically at central country level, as part of continuing efforts of health promotion programs. Local health care providers can play a significant role in national campaigns for increasing vaccination coverage among vulnerable groups.

Hospitals' Cybersecurity Culture during the COVID-19 Crisis.

The coronavirus pandemic led to an unprecedented crisis affecting all aspects of the concurrent reality. Its consequences vary from political and societal to technical and economic. These side effects provided fertile ground for a noticeable cyber-crime increase targeting critical infrastructures and, more specifically, the health sector; the domain suffering the most during the pandemic. This paper aims to assess the cybersecurity culture readiness of hospitals' workforce during the COVID-19 crisis. Towards that end, a cybersecurity awareness webinar was held in December 2020 targeting Greek Healthcare Institutions. Concepts of cybersecurity policies, standards, best practices, and solutions were addressed. Its effectiveness was evaluated via a two-step procedure. Firstly, an anonymous questionnaire was distributed at the end of the webinar and voluntarily answered by attendees to assess the comprehension level of the presented cybersecurity aspects. Secondly, a post-evaluation phishing campaign was conducted approximately four months after the webinar, addressing non-medical employees. The main goal was to identify security awareness weaknesses and assist in drafting targeted assessment campaigns specifically tailored to the health domain needs. This paper analyses in detail the results of the aforementioned approaches while also outlining the lessons learned along with the future scientific routes deriving from this research.

20-year trends of characteristics and outcomes of stroke patients with atrial fibrillation.

Background The accurate knowledge of secular trends in prevalence, characteristics and outcomes of patients with ischemic stroke and atrial fibrillation allows better projections into the future. Aim We aimed to report the overall, age- and sex-specific secular trends of characteristics and outcomes of patients with acute ischemic stroke (AIS) and atrial fibrillation between 1993 and 2012 in the Athens Stroke Registry. Methods We used Joinpoint regression analysis to calculate the average annual percent changes and 95% confidence intervals. Results Among 3314 stroke patients, 1044 (31.5%) had atrial fibrillation. Between 1993 and 2012, there was an average annual reduction of 0.8% (95% CI: -1.5%; 0.0%) in the proportion of atrial fibrillation patients among all AIS patients, whereas the proportion of newly diagnosed atrial fibrillation patients among all atrial fibrillation patients increased annually by an average of 7.1% (95% CI: 5.4%;8.9%). Among all atrial fibrillation patients, there was an average annual reduction of 2.9% (95% CI: -2.7; -3.2%) in the proportion of previously known atrial fibrillation patients, followed by an annual average reduction of 2.4% (95% CI: -1.2; -3.6%) in the proportion of previously known atrial fibrillation patients not receiving any antithrombotic treatment at admission. During that period, there was an increase in the average annual proportion of previously known atrial fibrillation patients treated with anticoagulants (6.4%, 95% CI: 1.2;11.9%) and aspirin (2.3%, 95% CI: -0.4;5.0%) at admission; an average annual increase in the proportion of atrial fibrillation patients who were prescribed anticoagulant was apparent both for patients with mRS<4 (3.5%) and mRS: 4-5 (7.2%), while the proportion of atrial fibrillation patients who were prescribed aspirin or no antithrombotic at discharge was annually reduced (5.8% for mRS<4; 1.6% for mRS: 4-5 and 7.1% for mRS<4;5.3% for mRS: 4-5 respectively). Stroke recurrences were annually reduced by an average of 5.8% (95% CI: -8.6; -3.0%), along with cardiovascular events (6.5%, 95% CI: -8.3; -4.7%) and deaths (7.9%, 95% CI: -9.2; -6.5%). Conclusions Between 1993 and 2012, the proportion of atrial fibrillation patients on proper antithrombotic treatment and the rate of newly diagnosed atrial fibrillation increased significantly. Rates of stroke recurrence, cardiovascular events, and mortality reduced significantly.

Age- and sex-specific analysis of patients with embolic stroke of undetermined source.

OBJECTIVE: To investigate whether the correlation of age and sex with the risk of recurrence and death seen in patients with previous ischemic stroke is also evident in patients with embolic stroke of undetermined source (ESUS). METHODS: We pooled datasets of 11 stroke registries from Europe and America. ESUS was defined according to the Cryptogenic Stroke/ESUS International Working Group. We performed Cox regression and Kaplan-Meier product limit analyses to investigate whether age (<60, 60-80, >80 years) and sex were independently associated with the risk for ischemic stroke/TIA recurrence or death. RESULTS: Ischemic stroke/TIA recurrences and deaths per 100 patient-years were 2.46 and 1.01 in patients <60 years old, 5.76 and 5.23 in patients 60 to 80 years old, 7.88 and 11.58 in those >80 years old, 3.53 and 3.48 in women, and 4.49 and 3.98 in men, respectively. Female sex was not associated with increased risk for recurrent ischemic stroke/TIA (hazard ratio [HR] 1.15, 95% confidence interval [CI] 0.84-1.58) or death (HR 1.35, 95% CI 0.97-1.86). Compared with the group <60 years old, the 60- to 80- and >80-year groups had higher 10-year cumulative probability of recurrent ischemic stroke/TIA (14.0%, 47.9%, and 37.0%, respectively, p < 0.001) and death (6.4%, 40.6%, and 100%, respectively, p < 0.001) and higher risk for recurrent ischemic stroke/TIA (HR 1.90, 95% CI 1.21-2.98 and HR 2.71, 95% CI 1.57-4.70, respectively) and death (HR 4.43, 95% CI 2.32-8.44 and HR 8.01, 95% CI 3.98-16.10, respectively). CONCLUSIONS: Age, but not sex, is a strong predictor of stroke recurrence and death in ESUS. The risk is ≈3- and 8-fold higher in patients >80 years compared with those <60 years of age, respectively. The age distribution in the ongoing ESUS trials may potentially influence their power to detect a significant treatment association.