Logic Programming and Artificial Neural Networks in Breast Cancer Detection

Abstract

Abstract. About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

Intelligent Noninvasive Diagnosis of Aneuploidy: Raw Values and Highly Imbalanced Dataset

“…ANNs have been widely used in medical applications for the prediction of cancer [18]- [20], Parkinson disease [21], and other serious diseases [22]- [24]. The major difference between statistical methods and ANNs in classification is that ANNs have the ability to learn and store information by examples that are presented one by one.…”

An Artificial Intelligence Approach to Thrombophilia Risk

“…It stands for a new approach to the problem of Thrombophilia Risk, which is centred on a formal framework based on LP for Knowledge Representation and Reasoning, is subject to formal proof, being complemented with an ANN approach to computing that caters for the handling of incomplete, unknown, or even self-contradictory information. The extensions of the predicates that make the universe of discourse are given in terms of QoIs and DoCs that stand, respectively, for the arguments Quality-of-Information and one's Degree-of-Confidence that the predicates argument values fit into a given interval considering their respective domains, being the data/information/knowledge under analyse either unknown, incomplete, or even self-contradictory (Neves et al, 2015;Neves, Silva, Neves, & Vicente, 2016). The presented approach presents a worthy performance in the diagnosis of thrombophilia, due to the sensitivity and specificity which exhibited values near 96%.…”

“…Martins et al (2015) developed a decision support system using ANNs to evaluate the acute coronary syndrome predisposing with an overall accuracy higher than 95%. Neves et al (2015) presented a computer-aided diagnostics system, based on ANNs, aiming an early detection of breast cancer. This risk assessment model includes genetic risk factors and hormonal factors.…”