A carregar...
Projeto de investigação
Associate Laboratory of Energy, Transports and Aeronautics
Financiador
Autores
Publicações
Implementation of neural networks to frontal electroencephalography for the identification of the transition responsiveness/unresponsiveness during induction of general anesthesia
Publication . Ferreira, Ana Isabel Leitão; Vide, Sérgio; Nunes, Catarina S.; Neto, Joaquim; Amorim, Pedro; Mendes, Joaquim
Objective: General anesthesia is a reversible drug-induced state of altered arousal characterized by loss of responsiveness (LOR) due to brainstem inactivation. Precise identification of the LOR during the induction of general anesthesia is extremely important to provide personalized information on anesthetic requirements and could help maintain an adequate level of anesthesia throughout surgery, ensuring safe and effective care and balancing the avoidance of intraoperative awareness and overdose. So, main objective of this paper was to investigate whether a Convolutional Neural Network (CNN) applied to bilateral frontal electroencephalography (EEG) dataset recorded from patients during opioid-propofol anesthetic procedures identified the exact moment of LOR. Material and methods: A clinical protocol was designed to allow for the characterization of different clinical endpoints throughout the transition to unresponsiveness. Fifty (50) patients were enrolled in the study and data from all was included in the final dataset analysis. While under a constant estimated effect-site concentration of 2.5 ng/mL of remifentanil, an 1% propofol infusion was started at 3.3 mL//h until LOR. The level of responsiveness was assessed by an anesthesiologist every six seconds using a modified version of the Richmond Agitation-Sedation Scale (aRASS). The frontal EEG was acquired using a bilateral bispectral (BIS VISTA (TM) v2.0, Medtronic, Ireland) sensor. EEG data was then split into 5-second epochs, and for each epoch, the anesthesiologist's classification was used to label it as responsiveness (no-LOR) or unresponsiveness (LOR). All 5-second epochs were then used as inputs for the CNN model to classify the untrained segment as no-LOR or LOR. Results: The CNN model was able to identify the transition from no-LOR to LOR successfully, achieving 97.90 +/- 0.07% accuracy on the cross-validation set. Conclusion: The obtained results showed that the proposed CNN model was quite efficient in the responsiveness/unresponsiveness classification. We consider our approach constitutes an additional technique to the current methods used in the daily clinical setting where LOR is identified by the loss of response to verbal commands or mechanical stimulus. We therefore hypothesized that automated EEG analysis could be a useful tool to detect the moment of LOR, especially using machine learning approaches.
A statistical assessment of drilling effects on glass fiber-reinforced polymeric composites
Publication . Martins, Ana; Carvalho, Alda; Bragança, Ivo; Barbosa, Inês; Barbosa, Joaquim; Loja, Amélia
Fiber-reinforced composites are extensively used in many components and structures in various industry sectors, and the need to connect and assemble such types of components may require drilling operations. Although drilling is a common machining process; when dealing with fiber-reinforced composite materials, additional and specific problems may arise that can com-promise mechanical integrity. So, the main goal of this work is to assess how various input variables impact two main outcomes in the drilling process: the exit-adjusted delamination factor and the maximum temperature on the bottom surface where the drilling tool exits. The input variables include the type of drilling tools used, the operating speeds, and the thickness of the plates being drilled. By using Analysis of Variance (ANOVA), the analysis aims to identify which factors significantly influence damage and exit temperature. The results demonstrate that the influence of tools and drilling parameters is critical, and those selections impact the quality of the hole and the extent of the induced damage to the surrounding area. In concrete, considering the initially selected set of tools, the BZT03 tool does not lead to high-quality holes when drilling medium- and high-thickness plates. In contrast, the Dagger tool shows potential to reduce exit hole damage while also lowering temperature.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
6817 - DCRRNI ID
Número da atribuição
UIDB/50022/2020