A Real-Time Classification System of Thalassemic Pathologies Based on Artificial Neural Networks

Abstract

Thalassemias are pathologies that derive from genetic defects of the globin genes. The most common defects among the population affect the genes that are involved in the synthesis of alpha and beta chains. The main aspects of these pathologies are well explained from a biochemical and genetic point of view. The diagnosis is fundamentally based on hematologic and genetic tests. A genetic analysis is particularly important to determine the carriers of alpha-thalassemia, whose identification by means of the hematologic parameters is more difficult in comparison with heterozygotes for alpha-thalassemia. This work investigates the use of artificial neural networks (ANNs) for the classification of thalassemic pathologies using the hematologic parameters resulting from hemochromocytometric analysis only. Different combinations of ANNs are reported, which allow thalassemia carriers to be discriminated from normals with 94% classification accuracy, 92% sensitivity, and 95% specificity. On the basis of these results, an automated system that allows real-time support for diagnoses is proposed. The automated system interfaces a hemochromo analyzer to a simple PC.

Differential Diagnostics of Thalassemia Minor by Artificial Neural Networks Model

“…There are previous studies that are concerned with the problem of identifying TM patients from a healthy population using ANNs . These studies proved the usefulness of the ANNs method and were able to separate various thalassemia types among general datasets of CBC.…”

“…Therefore, several attempts were previously made to identify the condition by a simple blood count with varying degrees of success. The use of complete blood count (CBC) parameters to screen for thalassemia can be divided into three major approaches: index based on a single parameter , index based on several parameters , and index based on a nonlinear approach .…”

“…Adding chromatography HB typing improves the results but requires additional costly analysis . The only study that applied the ANN approach for thalassemia and had been based on only four blood parameters achieved a sensitivity value of 0.92 and a specificity value of 0.95 .…”

Predicting Rotator Cuff Tears Using Data Mining and Bayesian Likelihood Ratios

“…For some diseases, determining the diagnosis, prognosis or treatment planning is a primary challenging task for doctors and thus the predictive data mining model is a useful tool to use patient-specific information to predict an outcome of interest at an individual patient level and support clinical decision-making [14], [16]. Predictive data mining methods, such as artificial neural networks (ANNs) and decision trees, have been used successfully to predict the outcomes of medical diagnostic processes [14], [17]; Examples include identification of patients at high risk of postinduction hypotension during general anesthesia [18], prediction of acute coronary occlusion, early diagnosis of acute myocardial infarction [19], [20], prediction of thalassemic pathologies [21], diagnosis of ovarian cancer [22], and prediction of outcomes following treatment of internal shoulder derangements [23].…”

Thalassaemia classification by neural networks and genetic programming

“…In order to narrow the diagnostic target down to the differentiation between thalassaemic patients, persons with thalassaemia trait and normal subjects, an alternative automated diagnostic tool is required. Recently, a successful implementation of a neural network [1,2], a k-nearest neighbour technique [2] and a support vector machine [2] as a thalassaemic diagnostic tool has been reported. However, the tool can only differentiate between two types of thalassaemic gene carriers and normal subjects.…”