A non-symbolic implementation of abdominal pain estimation in childhood

Mantzaris, Dimitrios; Anastassopoulos, George; Adamopoulos, Adam; Gardikis, Stefanos

doi:10.1016/j.ins.2008.06.015

Cited by 16 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method subtracts the MSE of an ANN structure with the MSE of ANN architecture abated with a node in hidden layer. If the subtraction is negative, the algorithm adds a neuron in the hidden layer, otherwise, the algorithm removes the last neuron in the hidden layer and the procedure terminates [50]. It is mentioned that the algorithm starts with two neurons in the hidden layer so that the MLP has the ability to classify the cases and consequently, the determination of dementia type and its appropriate medication.…”

Section: Resultsmentioning

confidence: 99%

Artificial Neural Networks for Estimation of Dementias Types

Mantzaris

Vrizas

Trougkakos

et al. 2014

AIA

Self Cite

View full text Add to dashboard Cite

In the last decades, there is a vivid interest of many researchers about algorithms with natural procedure similarities. Artificial Neural Networks (ANNs) are wide known algorithms, which have been developed in order to solve complex combinational problems and can be proven as a powerful tool in medical research. This paper implements computational algorithms, which were based on artificial neural networks for the dementia's types distinguish. Diversity of ANN architectures are implemented and assessed for correct prediction of types of dementia, based on available cases. The obtained results prove that ANNs have the ability to be incorporated in the field of Neurology.

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial Neural Networks for Estimation of Dementias Types

Mantzaris

Vrizas

Trougkakos

et al. 2014

AIA

Self Cite

View full text Add to dashboard Cite

show abstract

“…The number of neurons for PNNs' output layer is seven and is based on coding of possible diagnosis according to [12]. The values of spread and the MSE for the PNNs with the best performance are recorded, correspondingly, in the 1 st and 2 nd column of the Table 1.…”

Section: Resultsmentioning

confidence: 99%

“…The possible diagnosis stages are discharge, observation, no findings, focal appendicitis, phlegmonous or supurative appendicitis, gangrenous appendicitis and peritonitis. These factors and the diagnosis stages are well described in Table 2 and Table 1, correspondingly, in [12]. As presented in [12], the possible stages of abdominal pain examination are seven, whereof four stages demand operative treatment and three are referred for conservative treatment.…”

Section: Data Collectionmentioning

confidence: 98%

See 1 more Smart Citation

An Evolutionary Technique for Medical Diagnostic Risk Factors Selection

Mantzaris

Anastassopoulos

Iliadis

et al. 2009

IFIP Advances in Information and Communication Technology

Self Cite

View full text Add to dashboard Cite

This study proposes an Artificial Neural Network (ANN) and Genetic Algorithm model for diagnostic risk factors selection in medicine. A medical disease prediction may be viewed as a pattern classification problem based on a set of clinical and laboratory parameters. Probabilistic Neural Networks (PNNs) were used to face a medical disease prediction. Genetic Algorithm (GA) was used for pruning the PNN. The implemented GA searched for optimal subset of factors that fed the PNN to minimize the number of neurons in the ANN input layer and the Mean Square Error (MSE) of the trained ANN at the testing phase. Moreover, the available data was processed with Receiver Operating Characteristic (ROC) analysis to assess the contribution of each factor to medical diagnosis prediction. The obtained results of the proposed model are in accordance with the ROC analysis, so a number of diagnostic factors in patient's record can be omitted, without any loss in clinical assessment validity.

show abstract

“…The advantages of using neural network approaches in diagnosis are their generalization ability in addressing both the nonlinear and fuzzy nature of the patients' data. Neural networks have been applied in building diagnosis models for various diagnoses [1,20,13,4,28,8], these diagnosis models have the capability to transform the nonlinear or fuzzy patients' data into simplified black-box structures. In this paper, a neural network based classification unit is proposed to perform diagnosis of hypoglycemic episodes in T1DM patients.…”

Section: Introductionmentioning

confidence: 99%

Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks

Chan

Ling

Dillon

et al. 2010

IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

Hypoglycemia is dangerous for Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, we have developed a classification unit with hybridizing the approaches of neural networks and genetic algorithm to identify the presences of hypoglycemic episodes for TIDM patients. The proposed classification unit is built and is validated by using the real T1DM patients' data sets collected from Department of Health, Government of Western Australia. Experimental results show that the proposed neural network based classification unit can achieve more accurate results on both trained and unseen T1DM patients' data sets compared with those developed based on the commonly used classification methods for medical diagnosis including statistical regression, fuzzy regression and genetic programming.

show abstract

A non-symbolic implementation of abdominal pain estimation in childhood

Cited by 16 publications

References 30 publications

Artificial Neural Networks for Estimation of Dementias Types

Artificial Neural Networks for Estimation of Dementias Types

An Evolutionary Technique for Medical Diagnostic Risk Factors Selection

Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks

Contact Info

Product

Resources

About