Energy-Efficient Edge and Cloud Image Classification with Multi-Reservoir Echo State Network and Data Processing Units.

In an era dominated by Internet of Things (IoT) devices, software-as-a-service (SaaS) platforms, and rapid advances in cloud and edge computing, the demand for efficient and lightweight models suitable for resource-constrained devices such as data processing units (DPUs) has surged. Traditional deep learning models, such as convolutional neural networks (CNNs), pose significant computational and memory challenges, limiting their use in resource-constrained environments. Echo State Networks (ESNs), based on reservoir computing principles, offer a promising alternative with reduced computational complexity and shorter training times. This study explores the applicability of ESN-based architectures in image classification and weather forecasting tasks, using benchmarks such as the MNIST, FashionMnist, and CloudCast datasets. Through comprehensive evaluations, the Multi-Reservoir ESN (MRESN) architecture emerges as a standout performer, demonstrating its potential for deployment on DPUs or home stations. In exploiting the dynamic adaptability of MRESN to changing input signals, such as weather forecasts, continuous on-device training becomes feasible, eliminating the need for static pre-trained models. Our results highlight the importance of lightweight models such as MRESN in cloud and edge computing applications where efficiency and sustainability are paramount. This study contributes to the advancement of efficient computing practices by providing novel insights into the performance and versatility of MRESN architectures. By facilitating the adoption of lightweight models in resource-constrained environments, our research provides a viable alternative for improved efficiency and scalability in modern computing paradigms.

A soft systems approach of asthma management in children based on therapeutic education and e-learning.

One of the most common respiratory chronic diseases is asthma, with 5-16 % of world prevalence. In chronic disease, prevention, diagnosis, management, and palliation are the strategies for a care model; the patient-self management is fundamental with the so-called therapeutic education (TE) to train the patient in the necessary skills. The challenge of TE grows when the patient is a child or a person with special needs, even more in public health care in low- and middle-income countries. This is a problematic human situation, that needs soft system thinking. In this research, the analytic hierarchy process was used to determine the perceived importance of the factors that affect children's asthma health care in a public health institution in Mexico. The soft systems methodology (SSM) was applied to learn about the disease self-management, in order to obtain activities models and an action plan. According to AHP, human resources and education were percived as the most important among the factors that affect children health care within the institution. The perceived importance of two main subfactors (human resources training and TE) was around 34 %, which emphasizes the need to generate strategies for the improvement of the education of patients and health care providers. In MSS, the rich vision, the CATWOE, the root definition, and an activities model were proposed, including the application of an instructional design methodology (ADDIE) for the development of learning objects of asthma for children. Desirable and feasible actions and recommendations include the update of the national clinical practice guides, the use of control measures such as the Asthma Control Test, and a daily asthma diary to register the daily status of the breathing capacity, the drug administration, and the potential trigger events. The proposed model can be used as part of a systemic patient-and-family centered approach for chronic care model (CCM), particularly in diseases unsuitable for prevention interventions.

Portable Pocket colposcopy performs comparably to standard-of-care clinical colposcopy using acetic acid and Lugol's iodine as contrast mediators: an investigational study in Peru.

OBJECTIVE: Our goal was to develop a tele-colposcopy platform for primary-care clinics to improve screening sensitivity and access. Specifically, we developed a low-cost, portable Pocket colposcope and evaluated its performance in a tertiary healthcare centre in Peru. DESIGN AND SETTING: Images of the cervix were captured with a standard-of-care and Pocket colposcope at la Liga Contra el Cáncer in Lima, Peru. POPULATION: Two hundred Peruvian women with abnormal cytology and/or human papillomavirus positivity were enrolled. METHODS: Images were collected using acetic acid and Lugol's iodine as contrast agents. Biopsies were taken as per standard-of-care procedures. MAIN OUTCOME MEASURES: After passing quality review, images from 129 women were sent to four physicians who provided a diagnosis for each image. RESULTS: Physician interpretation of images from the two colposcopes agreed 83.1% of the time. The average sensitivity and specificity of physician interpretation compared with pathology was similar for the Pocket (sensitivity = 71.2%, specificity = 57.5%) and standard-of-care (sensitivity = 79.8%, specificity = 56.6%) colposcopes. When compared with a previous study where only acetic acid was applied to the cervix, results indicated that adding Lugol's iodine as a secondary contrast agent improved the percent agreement between colposcopes for all pathological categories by up to 8.9% and the sensitivity and specificity of physician interpretation compared with pathology by over 6.0 and 9.0%, respectively. CONCLUSIONS: The Pocket colposcope performance was similar to that of a standard-of-care colposcope when used to identify precancerous and cancerous lesions using acetic acid and Lugol's iodine during colposcopy examinations in Peru. TWEETABLE ABSTRACT: The Pocket colposcope performance was similar to that of a standard-of-care colposcope when identifying cervical lesions.

Evidence of previous avian influenza infection among US turkey workers.

The threat of an influenza pandemic is looming, with new cases of sporadic avian influenza infections in man frequently reported. Exposure to diseased poultry is a leading risk factor for these infections. In this study, we used logistic regression to investigate serological evidence of previous infection with avian influenza subtypes H4, H5, H6, H7, H8, H9, H10, and H11 among 95 adults occupationally exposed to turkeys in the US Midwest and 82 unexposed controls. Our results indicate that farmers practising backyard, organic or free-ranging turkey production methods are at an increased risk of infection with avian influenza. Among these farmers, the adjusted odds ratios (ORs) for elevated microneutralization assay titres against avian H4, H5, H6, H9, and H10 influenza strains ranged between 3.9 (95% CI 1.2-12.8) and 15.3 (95% CI 2.0-115.2) when compared to non-exposed controls. The measured ORs were adjusted for antibody titres against human influenza viruses and other exposure variables. These data suggest that sometime in their lives, the workers had been exposed to low pathogenicity avian influenza viruses. These findings support calls for inclusion of agricultural workers in priority groups in pandemic influenza preparedness efforts. These data further support increasing surveillance and other preparedness efforts to include not only confinement poultry facilities, but more importantly, also small scale farms.

Deep vein thrombosis and anticoagulant therapy.

This article focuses on deep vein thrombosis (DVT) and anticoagulant therapy. The risk factors, pathophysiology, prevention, and detection of DVT are explained. Anticoagulants such as unfractionated heparin (UFH), low molecular weight heparin (enoxaparin), and warfarin are discussed. The article also reviews nursing assessment and monitoring of patients with DVT as well as patient education on anticoagulants.

A broadband multimedia collaborative system for advanced teleradiology and medical imaging diagnosis.

This paper presents a new telemedicine system currently in routine clinical usage, developed within the European Union (EU) ACTS BONAPARTE project (1). The telemedicine system is developed on an asynchronous transfer mode (ATM) multimedia hardware/software platform comprising the following set of telemedicine services: synchronous cooperative work, high-quality video conference, multimedia mail, medical image digitizing, processing, storing and printing, and local and remote transparent database access. The medical information handled by the platform conforms to the Digital Imaging and Communications in Medicine (DICOM) 3.0 medical imaging standard. The telemedicine system has been installed for clinical routines in three Spanish hospitals since November 1997 and has been used in an average of one/two clinical sessions per week. At each clinical session, a usability and clinical evaluation of the system was carried out. Evaluation is carried out through direct observation of interactions and questionnaire-based subjective data. The usability evaluation methodology and the results of the system usability study are also presented in this article. The experience gained from the design, development, and evaluation of the telemedicine system is providing an indepth knowledge of the benefits and difficulties involved in the installation and clinical usage of this type of high-usability and advanced multimedia telemedicine system in the field of teleradiology and collaborative medical imaging diagnosis.