The physiological monitoring of older people using wearable sensors has shown great potential in improving their quality of life and preventing undesired events related to their health status. Nevertheless, creating robust predictive models from data collected unobtrusively in home environments can be challenging, especially for vulnerable ageing population. Under that premise, we propose an activity recognition scheme for older people exploiting feature extraction and machine learning, along with heuristic computational solutions to address the challenges due to inconsistent measurements in non-standardized environments. In addition, we compare the customized pipeline with deep learning architectures, such as convolutional neural networks, applied to raw sensor data without any pre- or post-processing adjustments. The results demonstrate that the generalizable deep architectures can compensate for inconsistencies during data acquisition providing a valuable alternative.
Investigating the health status of agricultural workers is a challenging goal. Contradictory outcomes concerning farmers’ health are reported in the literature. In this cross-sectional study, certain clinical and neurobehavioral health outcomes were compared between farmers and non-farmers living in the same rural area. Farmers (328) and non-farmers (347), matched per age and sex, were selected randomly in an agricultural area in West Greece. Both groups underwent haematological and biochemical examinations and were administered two neurobehavioral tests, namely the Mini-Mental State Examination (MMSE) and the Montgomery-Åsberg Depression Rating Scale (MADRS). Sociodemographic, personal medical, nutritional and lifestyle data were recorded. According to personal statements, farmers suffered from hypertension, cardiovascular, orthopaedic and ENT problems in higher frequency. Haematocrit, haemoglobin and serum cholinesterase’s activity were found to be lower among farmers. Lower prevalence of hypertension and better performances on MMSE and MADRS tests were recorded in young farmers in relation to young non-farmers, while these findings were reversed in older ages. Odds Ratios were calculated through multivariate logistic regression models. Factors affecting these impairments remain to be clarified.
28 January 2019 in BMC Medical Informatics and Decision Making
Frailty is a common clinical syndrome in ageing population that carries an increased risk for adverse health outcomes including falls, hospitalization, disability, and mortality. As these outcomes affect the health and social care planning, during the last years there is a tendency of investing in monitoring and preventing strategies. Although a number of electronic health record (EHR) systems have been developed, including personalized virtual patient models, there are limited ageing population oriented systems. We exploit the openEHR framework for the representation of frailty in ageing population in order to attain semantic interoperability, and we present the methodology for adoption or development of archetypes. We also propose a framework for a one-to-one mapping between openEHR archetypes and a column-family NoSQL database (HBase) aiming at the integration of existing and newly developed archetypes into it. The requirement analysis of our study resulted in the definition of 22 coherent and clinically meaningful parameters for the description of frailty in older adults. The implemented openEHR methodology led to the direct use of 22 archetypes, the modification and reuse of two archetypes, and the development of 28 new archetypes. Additionally, the mapping procedure led to two different HBase tables for the storage of the data. In this work, an openEHR-based virtual patient model has been designed and integrated into an HBase storage system, exploiting the advantages of the underlying technologies. This framework can serve as a base for the development of a decision support system using the openEHR’s Guideline Definition Language in the future.
Past ischemic stroke (IS) patients display suppressed adiponectin (ADPN) levels a few months after disease onset. It is still unclear whether hypoadiponectinemia is already present by the early stages of stroke or occurs as a delayed effect of the acute ischemic reaction. In the present study we investigated ADPN levels acutely after an IS. Serum ADPN was measured in 82 consecutive acute IS patients, and 30 stroke-free subjects of similar age and sex distributions. Patients had significantly lower ADPN levels than controls. Higher ADPN was significantly associated with reduced odds for IS accounting for age, sex and high-density lipoproteins. This association was strengthened after further adjustments for potential confounders. ADPN levels remained suppressed even 6 months after stroke. ADPN is significantly suppressed already by the early phases of stroke, and remains unchanged 6 months later. We propose a stable-over-time anti-inflammatory role of ADPN in IS, unrelated to the acute ischemic reaction.
Acute ischemic stroke (AIS) remains a major cause of long-term disability and death worldwide, posing significant challenges to healthcare systems. Timely diagnosis is crucial, as acute phase therapeutic options are highly time-sensitive and most effective when administered early in the disease course. In this context, serum biomarkers have emerged as a promising and complementary tool to aid in the rapid and accurate diagnosis, prognosis, and therapeutic monitoring of AIS. This narrative review aims to provide a comprehensive overview of the current landscape of serum biomarkers relevant to AIS. These biomarkers are categorized based on the underlying pathophysiological mechanisms they reflect, including markers of inflammation and oxidative stress, neuronal and endothelial injury, and those related to hemostasis and fibrinolysis. Their biological significance is evaluated through the spectrum of their diagnostic sensitivity and specificity and their potential integration into clinical practice. In addition, many of these biomarkers offer prognostic insights, helping to predict the likelihood of complications, recurrent stroke, or poor functional recovery. Furthermore, their role as a potential tool for the differential diagnosis of patients presenting with minor or nonspecific neurological symptoms and therapeutic monitoring is emphasized. Despite the promising potential of these biomarkers, their translation into routine clinical use remains limited.
Endothelial nitric oxide synthase (eNOS) G894T polymorphism has been previously associated with vascular diseases including stroke, but often with conflicting results. Experimental evidence suggests that some eNOS modalities may be important in preventing stroke, while others may be important during the dynamic inflammatory processes triggered at the acute phase of stroke. Thus, we examined the possible association of eNOS G894T variation with stroke severity and functional outcome. One hundred and eight consecutive patients with first ever acute atherothrombotic or lacunar stroke, and 193 stroke-free subjects were recruited. Demographic data, medical history, and vascular risk factors were collected. Assessments for stroke severity and functional outcome were carried out on admission and at one month post-stroke, respectively. eNOS G894T genotypes were produced using a standard restriction-fragment-length polymorphism technique. eNOS G894T polymorphism genotypic distributions did not differ between stroke patients and controls, as well as between each stroke subtype and controls. Carriage of T allele (GT and TT genotypes versus GG) was not significantly associated with either stroke severity or functional outcome in the univariate analysis. However, after accounting for age, gender and stroke severity, the presence of T allele strongly predicted poor outcome [odd ratio 8·49 (95% confidence intervals 1·57-46·0)]. Further adjustments for other important confounders could not alter the above significant association. Carriers of the eNOS 894T allele are at increased risk for adverse outcome at one month post-stroke, independently of severity and other confounding factors. Therapeutic interventions targeting patients with this unfavorable mutation may be an appealing approach.