ArticlePDF Available

Abstract and Figures

Artificial neural networks are finding many uses in the medical diagnosis application. The goal of this paper is to evaluate artificial neural network in disease diagnosis. Two cases are studied. The first one is acute nephritis disease; data is the disease symptoms. The second is the heart disease; data is on cardiac Single Proton Emission Computed Tomography (SPECT) images. Each patient classified into two categories: infected and non-infected. Classification is an important tool in medical diagnosis decision support. Feed-forward back propagation neural network is used as a classifier to distinguish between infected or non-infected person in both cases. The results of applying the artificial neural networks methodology to acute nephritis diagnosis based upon selected symptoms show abilities of the network to learn the patterns corresponding to symptoms of the person. In this study, the data were obtained from UCI machine learning repository in order to diagnosed diseases. The data is separated into inputs and targets. The targets for the neural network will be identified with 1's as infected and will be identified with 0's as non-infected. In the diagnosis of acute nephritis disease; the percent correctly classified in the simulation sample by the feed-forward back propagation network is 99 percent while in the diagnosis of heart disease; the percent correctly classified in the simulation sample by the feed-forward back propagation network is 95 percent.
Content may be subject to copyright.
IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 2, March 2011
ISSN (Online): 1694-0814 www.IJCSI.org
150
Artificial Neural Networks in Medical Diagnosis
Qeethara Kadhim Al-Shayea
MIS Department, Al-Zaytoonah University of Jordan
Amman, Jordan
Abstract
Artificial neural networks are finding many uses in the medical
diagnosis application. The goal of this paper is to evaluate
artificial neural network in disease diagnosis. Two cases are
studied. The first one is acute nephritis disease; data is the
disease symptoms. The second is the heart disease; data is on
cardiac Single Proton Emission Computed Tomography
(SPECT) images. Each patient classified into two categories:
infected and non-infected. Classification is an important tool in
medical diagnosis decision support. Feed-forward back
propagation neural network is used as a classifier to distinguish
between infected or non-infected person in both cases. The
results of applying the artificial neural networks methodology
to acute nephritis diagnosis based upon selected symptoms
show abilities of the network to learn the patterns
corresponding to symptoms of the person. In this study, the
data were obtained from UCI machine learning repository in
order to diagnosed diseases. The data is separated into inputs
and targets. The targets for the neural network will be
identified with 1's as infected and will be identified with 0's as
non-infected. In the diagnosis of acute nephritis disease; the
percent correctly classified in the simulation sample by the
feed-forward back propagation network is 99 percent while in
the diagnosis of heart disease; the percent correctly classified
in the simulation sample by the feed-forward back propagation
network is 95 percent.
Keywords: Artificial Neural Networks, Medical Diagnosis,
Feed-forward back propagation network, Artificial
Intelligence, and Decision Support Systems.
1. Introduction
Artificial neural networks provide a powerful tool to
help doctors to analyze, model and make sense of
complex clinical data across a broad range of medical
applications. Most applications of artificial neural
networks to medicine are classification problems; that is,
the task is on the basis of the measured features to assign
the patient to one of a small set of classes [1].
Er, Yumusak and Temurtas [2] presented a comparative
chest disease diagnosis which was realized by using
multilayer, probabilistic, learning vector optimization,
and generalized regression.
Das, Turkoglu and Sengur [3] used SAS enterprise
miner 5.2 to construct a neural networks ensemble based
methodology for diagnosing of the heart disease. Three
independent neural networks models used to construct
the ensemble model. The number of neural networks
node in the ensemble model was also increased but no
performance improvement was obtained.
Gil, Johnsson, Garicia, Paya and Fernandez [4]
evaluated the work out of some artificial neural network
models as tools for support in the medical diagnosis of
urological dysfunctions. They developed two types of
unsupervised and one supervised neural network.
Altunay, Telatar, Erogul and Aydur [5] analyzed the
uroflowmetric data and assisted physicians for their
diagnosis. They introduced an expert pre-diagnosis
system for automatically evaluating possible symptoms
from the uroflow signals. The system used artificial
neural networks (ANN) and produced a pre-diagnostic
result.
Moein, Monadjemi and Moallem [6] analyzed the real
procedure of medical diagnosis which usually is
employed by physicians and converted to a machine
implementable format. Then after selecting some
symptoms of eight different diseases, a data set contains
the information of a few hundreds cases was configured
and applied to a MLP neural network. The results of the
experiments and also the advantages of using a fuzzy
approach were discussed as well. Outcomes suggest the
role of effective symptoms selection and the advantages
of data fuzzificaton on a neural networks-based
automatic medical diagnosis system.
Heckerling, Canaris, Flach, Tape, Wigton and Gerber
[7] used artificial neural networks (ANN) coupled with
genetic algorithms to evolve combinations of clinical
variables optimized for predicting urinary tract infection.
Francisco, Juan Manuel, Antonio and Daniel [8]
developed a new system from a model based in a multi-
agent system in which each neuronal centre corresponds
with an agent. This system incorporates a heuristic in
order to make it more robust in the presence of possible
inconsistencies. The heuristic used is based on a neural
network (orthogonal associative memory). Knowledge
through training has been added to the system, using
correct patterns of behavior of the urinary tract and
behavior patterns resulting from dysfunctions in two
neuronal centers as a minimum.
Monadjemi and Moallem [9] investigated application of
artificial neural networks in typical disease diagnosis.
The real procedure of medical diagnosis which usually is
employed by physicians was analyzed and converted to
a machine implementable format. The results of the
experiments and also the advantages of using a fuzzy
approach were discussed as well.
Lin [10] presented classification and regression tree
(CART) and case-based reasoning (CBR) techniques to
structure an intelligent diagnosis model aiming to
IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 2, March 2011
ISSN (Online): 1694-0814 www.IJCSI.org
151
provide a comprehensive analytic framework to raise the
accuracy of liver disease diagnosis.
Mazurowski, Habas, Zurada, Lo, Baker and Tourassi
[11] investigated the effect of class imbalance in training
data when developing neural network classifiers for
computer aided medical diagnosis. The investigation is
performed in the presence of other characteristics that
are typical among medical data, namely small training
sample size, large number of features, and correlations
between features.
Zhang, Yan, Zhao and Zhang [12] presented a method
for developing a fully automated computer aided
diagnosis system to help radiologist in detecting and
diagnosing micro-calcifications in digital format
mammograms.
Higuchi, Sato, Makuuchi, Furuse, Takamoto and Takeda
[13] tested a three-layered artificial neural network
analysis of phonocardiogram recordings to diagnose,
automatically and objectively, the condition of the heart
in patients with heart murmurs.
2. Artificial Neural Networks
An artificial neural network (ANN) is a computational
model that attempts to account for the parallel nature of
the human brain. An (ANN) is a network of highly
interconnecting processing elements (neurons) operating
in parallel. These elements are inspired by biological
nervous systems. As in nature, the connections between
elements largely determine the network function. A
subgroup of processing element is called a layer in the
network. The first layer is the input layer and the last
layer is the output layer. Between the input and output
layer, there may be additional layer(s) of units, called
hidden layer(s). Fig.1 represents the typical neural
network. You can train a neural network to perform a
particular function by adjusting the values of the
connections (weights) between elements
Fig.1 A typical neural network
Medical Diagnosis using Artificial Neural Networks is
currently a very active research area in medicine and it is
believed that it will be more widely used in biomedical
systems in the next few years. This is primarily because
the solution is not restricted to linear form. Neural
Networks are ideal in recognizing diseases using scans
since there is no need to provide a specific algorithm on
how to identify the disease. Neural networks learn by
example so the details of how to recognize the disease is
not needed [14].
Based on the way they learn, all artificial neural
networks are divided into two learning categories:
supervised and unsupervised. In supervised learning, the
network is trained by providing it with input and output
patterns. During this phase, the neural network is able to
adjust the connection weights to match its output with
the actual output in an iterative process until a desirable
result is reached. An ANN of the unsupervised learning
type, such as the self-organizing map, the neural
network is provided only with inputs, there are no
known answers. The network must develop its own
representation of the input stimuli by calculating the
acceptable connection weights. That is self-organization
by clustering the input data and find features inherent to
the problem.
2.1 The Proposed Diagnosis Model
Feed-forward neural networks are widely and
successfully used models for classification, forecasting
and problem solving. A typical feed-forward back
propagation neural network is proposed to diagnosis
diseases. It consists of three layers: the input layer, a
hidden layer, and the output layer. A one hidden with 20
hidden layer neurons is created and trained. The input
and target samples are automatically divided into
training, validation and test sets. The training set is used
to teach the network. Training continues as long as the
network continues improving on the validation set. The
test set provides a completely independent measure of
network accuracy. The information moves in only one
direction, forward, from the input nodes, through the
hidden nodes and to the output nodes. There are no
cycles or loops in the network. The proposed neural
networks are shown in Fig.2 and Fig.3.
Fig.2 The proposed acute nephritis diagnosis neural network
IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 2, March 2011
ISSN (Online): 1694-0814 www.IJCSI.org
152
Fig.3 The proposed heart disease diagnosis neural network
Feed-forward neural network allows signals to travel
one-way only; from source to destination; there is no
feedback. The hidden neurons are able to learn the
pattern in data during the training phase and mapping
the relationship between input and output pairs. Each
neuron in the hidden layer uses a transfer function to
process data it receives from input layer and then
transfers the processed information to the output neurons
for further processing using a transfer function in each
neuron.
The output of the hidden layer can be represented by
YNx1 = f(WNxM XM,1 + bN,1 ) (1)
where Y is a vector containing the output from each of
the N neurons in a given layer, W is a matrix containing
the weights for each of the M inputs for all N neurons, X
is a vector containing the inputs, b is a vector containing
the biases and f(·) is the activation function [15].
3. Experimental Results
3.1 Data Analysis
Symptoms, images or signals are the data used in
medical diagnosis. The data set is obtained from UCI
Machine Learning Repository.
3.1.1 Acute Nephritis Diagnosis Data
The data was created by a medical expert as a data set to
test the expert system, which will perform the
presumptive diagnosis of one of the urinary system
diseases.
The main idea of this data set is to construct the neural
network model, which will perform the presumptive
diagnosis of acute nephritis. Acute nephritis of renal
pelvis origin occurs considerably more often at women
than at men. It begins with sudden fever, which reaches,
and sometimes exceeds 40C. The fever is accompanied
by shivers and one- or both-side lumbar pains, which are
sometimes very strong.
This dataset contains 120 patients. Table 1 presents the
patient symptom data which are considered as diagnosis
variables. The dataset contains 120 samples. 90 sample
used in training the network while 30 samples used in
testing the network.
Table 1: Diagnosis variable of datasets used in the study
Patients symptom data
N
o. Diagnosis Variable Name
1 Temperature of patient {35C-42C}
2 Occurrence of nausea {yes, no}
3 Lumbar pain {yes, no}
4 Urine pushing
(Continuous need for urination)
{yes, no}
5 Micturition pains {yes, no}
6 Burning of urethra, itch, swelling of
urethra outlet {yes, no}
3.1.2 Heart Disease Diagnosis Data
The dataset describes diagnosing of cardiac Single
Proton Emission Computed Tomography (SPECT)
images. Each of the patients is classified into two
categories: normal and abnormal. The database of 267
SPECT image sets (patients) was processed to extract
features that summarize the original SPECT images. As
a result, 44 continuous feature patterns were created for
each patient. The pattern was further processed to obtain
22 binary feature patterns. SPECT data has 267
instances that are described by 23 binary attributes. The
dataset contains 267 samples. 80 sample used in training
the network while 187 samples used in testing the
network.
3.2 Performance Evaluation
Neural network toolbox from Matlab 7.9 is used to
evaluate the performance of the proposed networks.
Acute nephritis of renal pelvis origin is the first disease
to be diagnosed. A two-layer feed-forward network with
6 inputs and 20 sigmoid hidden neurons and linear
output neurons was created.
Such net can fit multi-dimensional mapping problems
arbitrarily well, given consistent data and enough
neurons in its hidden layer as shown in Fig.2.
Levenberg-Marquardt back propagation algorithm was
used with train the network. Training automatically
stops when generalization stops improving, as indicated
by an increase in the mean square error (MSE) of the
validation samples.
The results of applying the artificial neural networks
methodology to distinguish between healthy and
unhealthy person based upon selected symptoms showed
very good abilities of the network to learn the patterns
corresponding to symptoms of the person. The network
was simulated in the testing set (i.e. cases the network
has not seen before). The results were very good; the
network was able to classify 99% of the cases in the
testing set. Fig.4 shows the training state values.
Best validation performance is 2.8548e-007 at epoch 7
as shown in Fig.5. The mean squared error (MSE) is the
average squared difference between outputs and targets.
Lower values are better while zero means no error.
IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 2, March 2011
ISSN (Online): 1694-0814 www.IJCSI.org
153
Fig.4
Fig.5
Table 2: The Mean Square Error (MSE) and Regression values for the
training, validation and testing.
MSE R
Training 5.11986e-8 9.99999e-1
Validation 2.85475e-7 9.99999e-1
Testing 1.13132e-6 9.99997e-1
The percent correctly classified in the simulation sample
by the feed-forward back propagation network is 99
percent. The MSE is equal to 3.96199e-5 and the
regression is equal to 9.99936e-1.
Heart disease is the second disease to be diagnosed. A
two-layer feed-forward network with 22 inputs and 20
sigmoid hidden neurons and linear output neurons was
created.
Such net can fit multi-dimensional mapping problems
arbitrarily well, given consistent data and enough
neurons in its hidden layer as shown in Fig.3.
Levenberg-Marquardt back propagation algorithm was
used with train the network. The results of applying the
artificial neural networks methodology to distinguish
between normal and abnormal person based upon binary
feature patterns extracted from SPECT images showed
very good abilities of the network to learn the patterns.
The network was simulated in the testing set. The results
were very good; the network was able to classify 95% of
the cases in the testing set. Fig.6 shows the training state
values.
Best validation performance is 0.088329 at epoch 3 as
shown in Fig.7.
Fig.6
Fig.7
Table 3: The Mean Square Error (MSE) and Regression values for the
training, validation and testing.
MSE R
Training 4.86802e-3 9.92593e-1
Validation 8.83292e-2 8.50794e-1
Testing 7.47611e-2 8.72846e-1
The percent correctly classified in the simulation sample
by the feed-forward back propagation network is 95
percent. The MSE is equal to 2.78711e-2 and the
regression is equal to 9.50148e-1.
IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 2, March 2011
ISSN (Online): 1694-0814 www.IJCSI.org
154
4. Conclusions
This study aimed to evaluate artificial neural network in
disease diagnosis. The feed-forward back propagation
neural network with supervised learning is proposed to
diagnose the disease. Artificial neural networks showed
significant results in dealing with data represented in
symptoms and images. Results showed that the proposed
diagnosis neural network could be useful for identifying
the infected person.
References
[1] R. Dybowski and V. Gant, Clinical Applications of
Artificial Neural Networks, Cambridge University Press,
2007.
[2] O. Er, N. Yumusak and F. Temurtas, "Chest disease
diagnosis using artificial neural networks", Expert
Systems with Applications, Vol.37, No.12, 2010, pp.
7648-7655.
[3] R. Das, I. Turkoglu and A. Sengur, "Effective diagnosis of
heart disease through neural networks ensembles", Expert
Systems with Applications, Vol.36, No.4, 2009, pp. 7675-
7680.
[4] D. Gil, M. Johnsson, J. M. Garicia Chemizo, A. S. Paya
and D. R. Fernandez, "Application of Artificial Neural
Networks in the Diagnosis of Urological Dysfunctions",
Expert Systems with Applications, Vol.36, No.3, 2009,
pp. 5754-5760.
[5] S. Altunay, Z. Telatar, O. Erogul and E. Aydur, "A New
Approach to urinary system dynamics problems:
Evaluation and classification of uroflowmeter signals
using artificial neural networks", Expert Systems with
Applications, Vol.36, No.3, 2009, pp. 4891-4895.
[6] S. Moein, S. A. Monadjemi and P. Moallem, "A Novel
Fuzzy-Neural Based Medical Diagnosis System",
International Journal of Biological & Medical Sciences,
Vol.4, No.3, 2009, pp. 146-150.
[7] P. S. Heckerling, G. Canaris, S. D. Flach, T. G. Tape, R. S.
Wigton and B. S. Gerber, "Predictors of urinary tract
infection based on artificial neural networks and genetic
algorithms", International Journal of Medical Informatics;
Vol.76, No.4, 2007, pp. 289-296.
[8] M. P. Francisco, G. C. Juan Manuel, S. P. Antonio and R.
F. Daniel, "A robust model of the neuronal regulator of
the lower urinary tract based on artificial neural
networks", Neurocomputing, Vol.71, No.4-6, 2008, pp.
743-754.
[9] S. A. Monadjemi and P. Moallem, "Automatic Diagnosis of
Particular Diseases Using a Fuzzy-Neural Approach",
International Review on Computers & Software, Vol.3,
No.4, 2008, pp. 406-411.
[10] R. Lin, "An intelligent model for liver disease diagnosis",
Artificial Intelligence in Medicine, Vol.47, No.1, 2009,
pp. 53-62.
[11] M. A. Mazurowski, P. A. Habas, J. M. Zurada, J. Y. Lo, J.
A. Baker and G. D. Tourassi, "Training Neural Network
Classifiers for Medical Decision Making: The Effects of
Imbalanced Datasets on Classification Performance",
Special Issue on Advances in Neural Networks Research:
IJCNN ’07, 2007 International Joint Conference on
Neural Networks IJCNN’07 Orlando, Florida, USA,
April, 2008, Vol.21, No.3, pp. 427-436,
http://ci.louisville.edu/zurada/publications/mazurowski.nn
.2008.pdf.
[12] G. Zhang, P. Yan, H. Zhao and X. Zhang, "A Computer
Aided Diagnosis System in Mammography Using
Artificial Neural Networks", 2008 International
Conference on BioMedical Engineering and Informatics,
2008, Vol.2, pp. 823-826.
[13] K. Higuchi, K. Sato, H. Makuuchi, A. Furuse, S.
Takamoto and H. Takeda, "Automated diagnosis of heart
disease in patients with heart murmurs: application of a
neural network technique", Journal of Medical
Engineering & Technology, Vol.30, No.2, 2006, pp. 61-
68.
[14] J. B. Siddharth Jonathan and K.N. Shruthi, "A Two Tier
Neural Inter-Network Based Approach to Medical
Diagnosis Using K-Nearest Neighbor Classification for
Diagnosis Pruning", web page available at
http://infolab.stanford.edu/~jonsid/nimd.pdf.
[15] J. A. Freeman and D. M. Skapura, Neural networks:
algorithms, applications and programming techniques,
Addison Wesley Longman, 1991.
Qeethara Kadhim Abdul Rahman Al-Shayea, has received Ph. D. in
Computer Science, Computer Science Department, University of
Technology, Iraq, 2005. She received her M.Sc. degree in Computer
Science, Computer Science Department from University of
Technology, Iraq, 2000. She has received her High Diploma degree in
information Security from Computer Science Department, University
of Technology, Iraq, 1997. She has received B. Sc. Degree in
Computer Science Department from University of Technology, Iraq,
1992. She joined in September (2001-2006), Computer Science
Department, University of Technology, Iraq as assistant professor. She
joined in September 2006, Department of Management Information
Systems Faculty of Economics & Administrative Sciences Al-
Zaytoonah University of Jordan as assistant professor. She is interested
in Artificial intelligent, image processing, computer vision and coding
theory.
... Precise prediction of healthcare parameters, such as the diagnosis of diseases [3,26] and prediction of patient outcomes [25,27], is a challenging and important task that can directly facilitate patient care delivery processes and reduce treatment duration and costs for both patients and healthcare providers [50]. However, the presence of missing values, especially in large datasets, is an unavoidable problem when analyzing medical datasets. ...
Article
Full-text available
The availability of data in the healthcare domain provides great opportunities for the discovery of new or hidden patterns in medical data, which can eventually lead to improved clinical decision making. Predictive models play a crucial role in extracting this unknown information from data. However, medical data often contain missing values that can degrade the performance of predictive models. Autoencoder models have been widely used as non-linear functions for the imputation of missing data in fields such as computer vision, transportation, and finance. In this study, we assess the shortcomings of autoencoder models for data imputation and propose modified models to improve imputation performance. To evaluate, we compare the performance of the proposed model with five well-known imputation techniques on six medical datasets and five classification methods. Through extensive experiments, we demonstrate that the proposed non-linear imputation model outperforms the other models for all degrees of missing ratios and leads to the highest disease classification accuracy for all datasets.
... Networks trained with different biomarkers as input and the respective medical diagnosis as output could be utilised particularly for the diagnosis of rare and thus often overlooked diseases. The applicability of such diagnosis models has been evaluated for acute nephritis, abnormal cardiac behaviour, carcinoma, valve stenosis and other diseases [115,116]. ...
Article
Full-text available
Neural networks for deep-learning applications, also called artificial neural networks, are important tools in science and industry. While their widespread use was limited because of inadequate hardware in the past, their popularity increased dramatically starting in the early 2000s when it became possible to train increasingly large and complex networks. Today, deep learning is widely used in biomedicine from image analysis to diagnostics. This also includes special topics, such as forensics. In this review, we discuss the latest networks and how they work, with a focus on the analysis of biomedical data, particularly biomarkers in bioimage data. We provide a summary on numerous technical aspects, such as activation functions and frameworks. We also present a data analysis of publications about neural networks to provide a quantitative insight into the use of network types and the number of journals per year to determine the usage in different scientific field.
... After performing the ROI analysis, features showing small overlap between GGO and non GGO tissues were selected for the classification purpose. The classifier used is the three layer artificial neural network (ANN) [20]. For the implementation, we have used NPR tool from MATLAB wherein a 3-neuron input layer, 10-neuron hidden layer and 1-neuron output layer with only two desired outputs [0,1] framework was created. ...
Article
Full-text available
Lung cancer is one of the most profound causes of cancer‐related deaths in the world. Early detection is known to significantly improve the chances of survival. Several detection and diagnostic methods are used for this purpose. CT is one of the most widely used non‐invasive medical imaging modalities in this domain. The biggest challenge faced by radiologists in this case is detection and diagnosis of cancerous lung nodules. The growth of ground glass opacity (GGO) lesions is an indication of malignancy. However, GGO is difficult to capture for physicians as it manifests in the form of tiny, faint shadows. This research paper proposes an approach for aiding GGO identification in CT lung images for improved lung cancer prognosis. In the proposed approach, morphological reconstruction is used for segmentation. Once the region of interest (ROI) is extracted, statistical analysis using mean, standard deviation, variance, entropy, skewness, kurtosis, minimum grey scale value, maximum grey scale value and range is performed. The same statistical measures are determined for normal lung and distribution plot is drawn for comparison. It is observed that maximum grey‐scale value demonstrates minimum overlap of approximately 7.4%. To reduce this, a joint feature by summing values of feature mean, skewness, and maximum grey‐scale value was used. This approach reduced the overlap to approximately 1.32%. Lastly, ANN was used for classification of GGO and non‐GGO lung tissue with an achieved accuracy of 99.5%.
... Neural networks were introduced in modern information technologies as a key tool for machine learning. Till today, there have been advanced ways of using neural networks for helping and/or solving problems, such as in quantum chemistry [9][10][11], pattern recognition [12,13], sequence recognition [14,15], data mining [16,17], finance [18][19][20][21], medical diagnosis [22][23][24][25][26], visualization [27,28], solving PDEs [29][30][31][32], ocean modelling and coastal engineering [33], geomorphology [34], simulating properties of many-body open quantum systems [35], etc. ...
Preprint
Full-text available
Recently, a novel type of neural networks: the physics-informed neural networks, were discovered to have a great deal of applications in computational physics. By integrating knowledge of physical laws and processes in the form of partial differential equations, fast convergence and effective solutions are obtained. With the field of rapidly evolving quantum information theory, we combine classical information processing, quantum manipulation and processing, with physics-informmed neural networks to accomplish a hybrid quantum machine learning model. Usage: Secondary publications and information retrieval purposes.
... When advanced technology and healthcare experts are unavailable, diagnosing and controlling heart disease is incredibly challenging [5]. Many people's lives can be saved with a good, solid diagnosis and treatment [6]. A physician's evaluation of the patient's medical history, physical examination report, and analysis of concerning symptoms are used to diagnose heart diseases. ...
Article
Full-text available
A great diversity comes in the field of medical sciences because of computing capabilities and improvements in techniques, especially in the identification of human heart diseases. Nowadays, it is one of the world’s most dangerous human heart diseases and has very serious effects the human life. Accurate and timely identification of human heart disease can be very helpful in preventing heart failure in its early stages and will improve the patient’s survival. Manual approaches for the identification of heart disease are biased and prone to interexaminer variability. In this regard, machine learning algorithms are efficient and reliable sources to detect and categorize persons suffering from heart disease and those who are healthy. According to the recommended study, we identified and predicted human heart disease using a variety of machine learning algorithms and used the heart disease dataset to evaluate its performance using different metrics for evaluation, such as sensitivity, specificity, F-measure, and classification accuracy. For this purpose, we used nine classifiers of machine learning to the final dataset before and after the hyperparameter tuning of the machine learning classifiers, such as AB, LR, ET, MNB, CART, SVM, LDA, RF, and XGB. Furthermore, we check their accuracy on the standard heart disease dataset by performing certain preprocessing, standardization of dataset, and hyperparameter tuning. Additionally, to train and validate the machine learning algorithms, we deployed the standard K-fold cross-validation technique. Finally, the experimental result indicated that the accuracy of the prediction classifiers with hyperparameter tuning improved and achieved notable results with data standardization and the hyperparameter tuning of the machine learning classifiers.
Article
With the advent of extrusion additive manufacturing (AM), fabrication of high-performance thermoset composites without the need of tooling has become a reality. However, finding an optimal set of printing parameters for these thermoset composites during extrusion requires tedious experimentation as composite ink properties can vary significantly with respect to environmental parameters such as temperature and relative humidity. Addressing this challenge, this study presents a novel optimization framework that utilizes computer vision and deep learning (DL) to optimize the calibration and printing processes of thermoset composite AM. Unlike traditional DL models where printing parameters are determined prior to printing, our proposed framework dynamically and autonomously adjusts the printing parameters during extrusion. A novel DL integrated extrusion AM system is developed to determine the optimal printing parameters including print speed, road width, and layer height for a given composite ink. This closed loop system is consisted of a computer communicating with an extrusion AM system, a camera to perform in-situ imaging and several high accuracy convolution neural networks (CNNs) selecting the ideal process parameters for composite AM. The results show that our proposed process optimization framework was able to autonomously determine these parameters for a carbon fiber-composite ink. Consequently, specimens with complex geometries could be fabricated without visible defects and with maximum fiber alignment and thus enhancing the mechanical performance of the specimen’s composite material. Moreover, our proposed framework minimizes a labor-intensive procedure required to additively manufacture thermoset composites by optimizing the extrusion process without any user intervention.
Article
Using computational models, engineers and researchers are able to observe the results of their research beyond the range of their tested experimental parameters. Process modelling resembles the approximation behaviour. This paper reports the development of a mathematical model in predicting the water flux from Pre-Treated Palm Oil Mill Effluent (POME) using Direct Contact Membrane Distillation (DCMD). This model allows the identification for the range of feed temperature and feed velocity, in which optimal operating conditions (maximum production of water flux) can be obtained. An artificial neural network (ANN) was selected to predict the production of flux at various temperatures due to its capability to predict any nonlinear system. A multilayer Feedforward Artificial Neural Network (FANN) model consisting of 1 hidden layer with 13 hidden neurons, was developed with three input variables (feed temperature, feed velocity and membrane) and one output (permeate water flux) with 18 experimental data points. The lowest mean square error (MSE) obtained was 0.0034, while the regression coefficient (R) values for training, validation, and testing were 0.9859, 0.9986, and 0.9984, respectively. The most sensitive parameter was the feed temperature compared to feed velocity. The usage of this model may lead to the development of efficient and economical designs for separation processes.
Article
Full-text available
Automatic diagnosis of diseases always has been of interest as an interdisciplinary study amongst computer and medical science researchers. In this paper, application of artificial neural networks in typical disease diagnosis has been investigated. The real procedure of medical diagnosis which usually is employed by physicians was analyzed and converted to a machine implementable format. Then after selecting some symptoms of eight different diseases, a data set contains the information of a few hundreds cases was configured and applied to a MLP neural network. The results of the experiments and also the advantages of using a fuzzy approach were discussed as well. Outcomes suggest the role of effective symptoms selection and the advantages of data fuzzificaton on a neural networks-based automatic medical diagnosis system. Employing ETM diseases as the case study, system eventually gets through the 97.5% of correct detection of abnormal cases.
Article
Full-text available
The neuronal regulator of the lower urinary tract is a very complex nervous system that consists of a heterogeneous group of neuronal centres. We have developed a new system from a model based in a multi-agent system in which each neuronal centre corresponds with an agent. This system incorporates a heuristic in order to make it more robust in the presence of possible inconsistencies. The heuristic used is based on a neural network (orthogonal associative memory). Knowledge through training has been added to the system, using correct patterns of behaviour of the urinary tract and behaviour patterns resulting from dysfunctions in two neuronal centres as a minimum. The experiments prove that the model is robust and its functioning coincides with the behaviour of the biological system. This work fulfils the expectations of providing a model of the regulator system that allows breaking the problem into simple modules each with its own entity.
Article
Full-text available
In the last decades, several tools and various methodologies have been proposed by the researchers for developing effective medical decision support systems. Moreover, new methodologies and new tools are continued to develop and represent day by day. Diagnosing of the heart disease is one of the important issue and many researchers investigated to develop intelligent medical decision support systems to improve the ability of the physicians. In this paper, we introduce a methodology which uses SAS base software 9.1.3 for diagnosing of the heart disease. A neural networks ensemble method is in the centre of the proposed system. This ensemble based methods creates new models by combining the posterior probabilities or the predicted values from multiple predecessor models. So, more effective models can be created. We performed experiments with the proposed tool. We obtained 89.01% classification accuracy from the experiments made on the data taken from Cleveland heart disease database. We also obtained 80.95% and 95.91% sensitivity and specificity values, respectively, in heart disease diagnosis.
Article
Uroflowmetry is a measuring method, which provides numerical and graphical information about patient’s lower urinary tract dynamics by measuring and plotting the rate of change in urine volume. The main purpose of this study is to analyze the uroflowmetric data and to assist physicians for their diagnosis. An expert pre-diagnosis system is implemented for automatically evaluating possible symptoms from the uroflow signals. The system uses artificial neural networks (ANN) and produces a pre-diagnostic result. The outputs of ANN are classified into three groups, which are, “healthy”, “possible pathologic” and “pathologic”. The ANN is trained using back-propagation method and the inputs of the ANN are the extracted features, which are selected according to the suggestions of urology specialists. The proposed system is trained and validated using a dataset of patients, who have already diagnosed by the specialists.
Article
Chronic obstructive pulmonary, pneumonia, asthma, tuberculosis, lung cancer diseases are the most important chest diseases. These chest diseases are important health problems in the world. In this study, a comparative chest diseases diagnosis was realized by using multilayer, probabilistic, learning vector quantization, and generalized regression neural networks. The chest diseases dataset were prepared by using patient’s epicrisis reports from a chest diseases hospital’s database.
Article
In this article, we evaluate the work out of some artificial neural network models as tools for support in the medical diagnosis of urological dysfunctions. We develop two types of unsupervised and one supervised neural network. This scheme is meant to help the urologists in obtaining a diagnosis for complex multi-variable diseases and to reduce painful and costly medical treatments since neurological dysfunctions are difficult to diagnose. The clinical study has been carried out using medical registers of patients with urological dysfunctions. The proposal is able to distinguish and classify between ill and healthy patients.
Article
Among women who present with urinary complaints, only 50% are found to have urinary tract infection. Individual urinary symptoms and urinalysis are not sufficiently accurate to discriminate those with and without the diagnosis. We used artificial neural networks (ANN) coupled with genetic algorithms to evolve combinations of clinical variables optimized for predicting urinary tract infection. The ANN were applied to 212 women ages 19-84 who presented to an ambulatory clinic with urinary complaints. Urinary tract infection was defined in separate models as uropathogen counts of > or =10(5) colony-forming units (CFU) per milliliter, and counts of > or =10(2) CFU per milliliter. Five-variable sets were evolved that classified cases of urinary tract infection and non-infection with receiver-operating characteristic (ROC) curve areas that ranged from 0.853 (for uropathogen counts of > or =10(5) CFU per milliliter) to 0.792 (for uropathogen counts of > or =10(2) CFU per milliliter). Predictor variables (which included urinary frequency, dysuria, foul urine odor, symptom duration, history of diabetes, leukocyte esterase on urine dipstick, and red blood cells, epithelial cells, and bacteria on urinalysis) differed depending on the pathogen count that defined urinary tract infection. Network influence analyses showed that some variables predicted urine infection in unexpected ways, and interacted with other variables in making predictions. ANN and genetic algorithms can reveal parsimonious variable sets accurate for predicting urinary tract infection, and novel relationships between symptoms, urinalysis findings, and infection.
Article
Liver disease, the most common disease in Taiwan, is not easily discovered in its initial stage; early diagnosis of this leading cause of mortality is therefore highly important. The design of an effective diagnosis model is therefore an important issue in liver disease treatment. This study accordingly employs classification and regression tree (CART) and case-based reasoning (CBR) techniques to structure an intelligent diagnosis model aiming to provide a comprehensive analytic framework to raise the accuracy of liver disease diagnosis. Based on the advice and assistance of doctors and medical specialists of liver conditions, 510 outpatient visitors using ICD-9 (International Classification of Diseases, 9th Revision) codes at a medical center in Taiwan from 2005 to 2006 were selected as the cases in the data set for liver disease diagnosis. Data on 340 patients was utilized for the development of the model and on 170 patients utilized to perform comparative analysis of the models. This paper accordingly suggests an intelligent model for the diagnosis of liver diseases which integrates CART and CBR. The major steps in applying the model include: (1) adopting CART to diagnose whether a patient suffers from liver disease; (2) for patients diagnosed with liver disease in the first step, employing CBR to diagnose the types of liver diseases. In the first phase, CART is used to extract rules from health examination data to show whether the patient suffers from liver disease. The results indicate that the CART rate of accuracy is 92.94%. In the second phase, CBR is developed to diagnose the type of liver disease, and the new case triggers the CBR system to retrieve the most similar case from the case base in order to support the treatment of liver disease. The new case is supported by a similarity ratio, and the CBR diagnostic accuracy rate is 90.00%. Actual implementation shows that the intelligent diagnosis model is capable of integrating CART and CBR techniques to examine liver diseases with considerable accuracy. The model can be used as a supporting system in making decisions regarding liver disease diagnosis and treatment. The rules extracted from CART are helpful to physicians in diagnosing liver diseases. CBR can retrieve the most similar case from the case base in order to solve a new liver disease problem and can be of great assistance to physicians in identifying the type of liver disease, reducing diagnostic errors and improving the quality and effectiveness of medical treatment.