Artificial Neural Networks in Diagnosis of Liver Diseases

Abstract

Abstract. Liver diseases have severe patients' consequences, being one of the main causes of premature death. These facts reveal the centrality of one`s daily habits, and how important it is the early diagnosis of these kind of illnesses, not only to the patients themselves, but also to the society in general. Therefore, this work will focus on the development of a diagnosis support system to these kind of maladies, built under a formal framework based on Logic Programming, in terms of its knowledge representation and reasoning procedures, complemented with an approach to computing grounded on Artificial Neural Networks.

Complex Analysis of Medical Data with Data Mining Usage

“…No need of knowledge formalization; orientation to parallel processing; possibility of multidimensional data and knowledge processing without increase in labor input [21] Difficulties in explanation of neural network functioning results [22]; impossibility to guarantee repeatability and uniqueness of obtaining results [23] Each of these methods has its advantages and shortcomings, and many of them have restrictions in the character of the analyzed data. The problem is that a single method may only solve a narrow task of the data analysis which is not enough for decision-making.…”

Identification of exacerbation risk in patients with liver dysfunction using machine learning algorithms

“…By the anti-function calculation of the contact function f −1 , the generalized linear model Eq (7) can be obtained Eq (8).ŷ…”

“…Jose et al adopted an artificial neural network (ANN)) as a diagnosis support tool to assist the clinical decision-making. The ANN achieved 95.4% accuracy on the test set [8]. Nevertheless, ANN, as a black box model, is poorly clinically interpretable.…”