Pulmonary tuberculosis (PTB) remains a worldwide public health problem. Diagnostic algorithms to identify the best combination of diagnostic tests for PTB in each setting are needed for resource optimization. We developed one artificial neural network model for classification (multilayer perceptron-MLP) and another risk group assignment (self-organizing map-SOM) for PTB in hospitalized patients in a high complexity hospital in Rio de Janeiro City, using clinical and radiologic data collected from 315 presumed PTB cases admitted to isolation rooms from March 2003 to December 2004 (TB prevalence = 21.5 %). The MLP model included 7 variables-radiologic classification, age, gender, cough, night sweats, weight loss and anorexia. The sensitivity of the MLP model was 96.0 % (95 % CI ±2.0), the specificity was 89.0 % (95 % CI ±2.0), the positive predictive value was 72.5 % (95 % CI ±3.5) and the negative predictive value was 98.5 % (95 % CI ±0.5). The variable with the highest discriminative power was the radiologic classification. The high negative predictive value found in the MLP model suggests that the use of this model at the moment of hospital admission is safe. SOM model was able to correctly assign high-, medium- and low-risk groups to patients. If prospective validation in other series is confirmed, these models can become a tool for decision-making in tertiary health facilities in countries with limited resources.
Resumo Diversas aplicações na engenharia estão relacionadas em ambientes cujo a alta taxa de eventos e a rara ocorrência são uma dificuldade a ser superada. Este artigo tem como proposta apresentar a nova estratégia de seleção de elétrons no sistema de filtragem Online do detector ATLAS, no CERN, utilizando técnicas multivariadas, como Redes Neurais, para selecionar eficientemente e reduzir o custo de processamento na fazenda de computadores durante a filtragem. Dentro desse contexto, serão apresentadas as estratégias de treinamento das redes e correção das eficiências mediante ao crescimento do empilhamento de eventos ocasionado pelo aumento da luminosidade das colisões para o cenário de 2017.
Objective: To analyze the effect of cryotherapy on muscle stiffness after exercise-induced muscle damage. Design: A leg-to-leg comparison model. Setting: University research laboratory. Participants: Thirty (30) untrained men (21.1 ± 1.6 years, 177.6 ± 6.4 cm, 75.9 ± 10.0 kg, and 15.9 ± 2.9% fat mass) with no history of lower-limb injury and no experience in resistance training. Intervention: All participants underwent a plyometric exercise program to induce muscle damage; however, randomly, one leg was assigned to a treatment condition and subjected twice to cold-water immersion of the lower limb at 10°C (±1°C) for 10 minutes, while the other leg was assigned to control. Main Outcomes Measures: Longitudinal stiffness and passive transverse stiffness were evaluated on the soleus and gastrocnemius muscles at 4 moments: pre-exercise, immediately after exercise, 24 hours, and 72 hours after the damage protocol. Furthermore, pressure pain threshold (PPT) and maximal voluntary isometric contraction (MVIC) were also assessed in the same periods. Results: No significant differences between control and cryotherapy were observed in regard to MVIC (P = 0.529), passive longitudinal stiffness (P = 0.315), and passive transverse stiffness (P = 0.218). Only a significant decrease was observed in PPT on the soleus muscle in the cryotherapy compared with the control leg immediately after exercise (P = 0.040). Conclusions: The results show that cryotherapy had no influence on muscle stiffness. However, cryotherapy had a positive effect on PPT immediately after exercise.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.