An Artificial Intelligence Approach to Thrombophilia Risk

Abstract

Thrombophilia stands for a genetic or an acquired tendency to hypercoagulable states, frequently as venous thrombosis. Venous thromboembolism, represented mainly by deep venous thrombosis and pulmonary embolism, is often a chronic illness, associated with high morbidity and mortality. Therefore, it is crucial to identify the cause of the disease, the most appropriate treatment, the length of treatment or prevent a thrombotic recurrence. This work will focus on the development of a diagnosis decision support system in terms of a formal agenda built on a Logic Programming approach to knowledge representation and reasoning, complemented with a computational framework based on Artificial Neural Networks. The proposed model has been quite accurate in the assessment of thrombophilia predisposition (accuracy close to 95%). Furthermore, the model classified properly the patients that really presented the pathology, as well as classifying the disease absence (sensitivity and specificity higher than 95%).

Customers’ satisfaction assessment in water laboratories

“…The artificial neural networks (ANNs) approach to data processing enables not only that data are processed in a system context but also to capture complex or unknown relationships between inputs and outputs (Vicente et al 2012;Vilhena et al 2017). ANNs simulate the structure of the human brain, being populated by artificial neurons, with a valuable set of activation functions (Haykin 2009).…”

“…Typically used is a hillclimbing approach that begins with an initial architecture that is adjusted with the purpose of decreasing the internal measure of error (e.g., the mean squared error) (Haykin 2009). In recent years, several studies have demonstrated the effectiveness of ANNs in multiple contexts such as environment (Ahmed 2017;Ruben et al 2018), health (Vilhena et al 2017;Neves et al 2018), and education (Figueiredo et al 2020).…”

“…The assessment of ANNs models performance can be done using the confusion matrix (Vilhena et al 2017). Table 2 presents the confusion matrix for the ANN model shown in Figure 8 (the values refer to an average concerning 20 experiments).…”

“…Therefore, the predictions of customers' satisfaction using the ANN model are satisfactory, achieving accuracies higher than 90%. The confusion matrix also allows to compute the Sensitivity, Specificity, Positive Predictive Value (PPV), and the Negative Predictive Value (NPV) of the model (Vilhena et al 2017). The sensitivity and specificity for training and test sets were 94.0, 88.9, 90.3, and 91.7%, respectively.…”

Mediation Model of Service Quality and Behavioural Intention to Use of Artificial Intelligence Security Technology in UAE

“…Because of the difficulty of use, lack of support for job performance, and inability to meet expectations, employees' dissatisfaction with AI security technologies has a negative effect on their intention to use them in the future.With regard to balancing the world's superpowers and maintaining its security in the future, the UAE will face challenges related to its geographic scope and military's ability to employ modern technology. However, there are few empirical studies on the service quality (SQ) of artificial intelligence (AI) used by government agencies in the United Arab Emirates to safeguard properties (Salih et al, 2017) and effectiveness of AI services available in the United Arab Emirates (Vilhena et al, 2017).…”