Artificial Neural Networks For Diagnosis Research Articles

Artificial Neural Networks for Diagnosis of Kidney Stones Disease

The foundation of medical care for children with renal stone disease is the assessment of metabolic risk factors, which aims to stop the growth of preexisting calculi and subsequent stone occurrences. In this retrospective analysis, 90 children with kidney stone disease who had been sent to our institution and had undergone clinical testing in accordance with a defined procedure had their metabolic risk factors, clinical histories, and family histories assessed. Our pediatric patients were 10.7 years old on average, with a male to female ratio of 1.14:1.0. In 84.4% of the instances, biochemical abnormalities were discovered. Of the patients, 52.2% (n = 47) had only one urine metabolic risk factor, whereas the remaining 31.1% (n = 28) had several risk factors. Adrenal hypercalciuria. The aim of this work is to compare the performance of all three neural networks on the basis of its accuracy, time taken to build model, and training data set size. We will use Learning vector quantization (LVQ), two layers feed forward perceptron trained with back propagation training algorithm and Radial basis function (RBF) networks for diagnosis of kidney stone disease. In this work we used Waikato Environment for Knowledge Analysis (WEKA) version 3.7.5 as simulation tool which is an open source tool

CT-Scan Method-based Artificial Neural Network for Diagnosis of COVID-19

The Covid-19 epidemic appeared suddenly, with a rapid start and leaping steps, declaring a threat to global health where it was the beginnings of its upbringing in Wuhan, China. Where the World Health Organization announced after confirming the results of human infections in December 2019 that it hurts all aspects of life in general and human health in particular. Therefore, it requires addressing such an epidemic quickly and with tight steps to avoid aggravating the situation, especially the lack of appropriate treatment. The necessity necessitated the use of quarantine for the injured and social distancing, in addition to the use of preventive measures such as masks, hand sterilization, non-contact, and leaving a safe distance. This paper aims to use an ANN algorithm based on CT and some laboratory and clinical parameters to determine whether a person is infected with Covid-19 or not. The results showed that two hidden layers were chosen for the ANN algorithm, where the first hidden layer was installed with ten nodes, while the second hidden layer was selected with five nodes once, ten nodes again, fifteen nodes, and twenty nodes. The results showed the best two hidden layers 10-20 nodes, and the accuracy was 99.43%.

A signal recognition particle-related joint model of LASSO regression, SVM-RFE and artificial neural network for the diagnosis of systemic sclerosis-associated pulmonary hypertension.

Background: Systemic sclerosis-associated pulmonary hypertension (SSc-PH) is one of the most common causes of death in patients with systemic sclerosis (SSc). The complexity of SSc-PH and the heterogeneity of clinical features in SSc-PH patients contribute to the difficulty of diagnosis. Therefore, there is a pressing need to develop and optimize models for the diagnosis of SSc-PH. Signal recognition particle (SRP) deficiency has been found to promote the progression of multiple cancers, but the relationship between SRP and SSc-PH has not been explored. Methods: First, we obtained the GSE19617 and GSE33463 datasets from the Gene Expression Omnibus (GEO) database as the training set, GSE22356 as the test set, and the SRP-related gene set from the MSigDB database. Next, we identified differentially expressed SRP-related genes (DE-SRPGs) and performed unsupervised clustering and gene enrichment analyses. Then, we used least absolute shrinkage and selection operator (LASSO) regression and support vector machine-recursive feature elimination (SVM-RFE) to identify SRP-related diagnostic genes (SRP-DGs). We constructed an SRP scoring system and a nomogram model based on the SRP-DGs and established an artificial neural network (ANN) for diagnosis. We used receiver operating characteristic (ROC) curves to identify the SRP-related signature in the training and test sets. Finally, we analyzed immune features, signaling pathways, and drugs associated with SRP and investigated SRP-DGs' functions using single gene batch correlation analysis-based GSEA. Results: We obtained 30 DE-SRPGs and found that they were enriched in functions and pathways such as "protein targeting to ER," "cytosolic ribosome," and "coronavirus disease-COVID-19". Subsequently, we identified seven SRP-DGs whose expression levels and diagnostic efficacy were validated in the test set. As one signature, the area under the ROC curve (AUC) values for seven SRP-DGs were 0.769 and 1.000 in the training and test sets, respectively. Predictions made using the nomogram model are likely beneficial for SSc-PH patients. The AUC values of the ANN were 0.999 and 0.860 in the training and test sets, respectively. Finally, we discovered that some immune cells and pathways, such as activated dendritic cells, complement activation, and heme metabolism, were significantly associated with SRP-DGs and identified ten drugs targeting SRP-DGs. Conclusion: We constructed a reliable SRP-related ANN model for the diagnosis of SSc-PH and investigated the possible role of SRP in the etiopathogenesis of SSc-PH by bioinformatics methods to provide a basis for precision and personalized medicine.

A Two-stage Approach Using Artificial Neural Networks for Diagnosis of Heart Diseases Based on ECG Data

Background and Aim Most heart diseases show symptoms on ECG, but diagnosing heart disease with ECG requires the knowledge and experience of medical specialized. Because these specialists may not always be available, it is necessary to design tools to diagnose heart disease in these situations. In this paper, a two-stage approach based on artificial neural networks is designed to diagnose heart disease using ECG information.In this study, we aim to propose a two-stage approach using artificial neural network (ANN) to diagnose heart disease based ECG data. Methods & Materials To design the proposed approach, first the ECG data of 861 patients referred to medical centers in Arak, Iran were collected. The data were examined based on the opinions of specialists. Then, 154 features from ECG were used as inputs to the proposed model. In the first stage, an ANN was used to detect the ECG status (usable and unusable). In the second stage, using the usable ECG data, an ANN was used to diagnose the presence or absence of heart disease. Finally, the performance of the two-stage approach was evaluated and its accuracy and precision in determining the ECG quality and heart disease diagnosis were determined. Ethical Considerations This study was approved by the ethics committee of Arak University of Medical Sciences (Code: IR.ARAKMU.REC.1400.138). Results In the proposed approach, the ANN used for the determining the ECG status had a precision of 97.1% and an accuracy of 97.3%. The ANN used for the diagnosis of heart disease had a precision of 95.8% and an accuracy of 95.4%. Conclusion Considering the high efficiency of the proposed approach in determining of ECG status and diagnosing heart disease, it is possible to use this approach to help the treatment staff.

Artificial Neural Network for Diagnosis of Pancreatic Cancer

Cancer is malignant growth or tumour which forms due to an uncontrolled division of cells in a part of body which may even lead to death. These are of different types depending upon the part of body affected. If it is Pancreas then the disease is termed as Pancreatic Cancer. This paper presents an Artificial Neural Network model to diagnose pancreatic cancer based on a set of symptoms. An ANN model is created after analysing the actual procedure of disease diagnosis by the doctor. An approach to detect various stages of cancer affected in pancreas is presented in the paper. Results of the study suggest the advantage of using ANN model instead of manual disease diagnosis.

1H NMR- based metabolomics approaches as non- invasive tools for diagnosis of endometriosis

So far, non-invasive diagnostic approaches such as ultrasound, magnetic resonance imaging, or blood tests do not have sufficient diagnostic power for endometriosis disease. Lack of a non-invasive diagnostic test contributes to the long delay between onset of symptoms and diagnosis of endometriosis. The present study focuses on the identification of predictive biomarkers in serum by pattern recognition techniques and uses partial least square discriminant analysis, multi-layer feed forward artificial neural networks (ANNs) and quadratic discriminant analysis (QDA) modeling tools for the early diagnosis of endometriosis in a minimally invasive manner by (1)H- NMR based metabolomics. This prospective cohort study was done in Pasteur Institute, Iran in June 2013. Serum samples of 31 infertile women with endometriosis (stage II and III) who confirmed by diagnostic laparoscopy and 15 normal women were collected and analyzed by nuclear magnetic resonance spectroscopy. The model was built by using partial least square discriminant analysis, QDA, and ANNs to determine classifier metabolites for early prediction risk of disease. The levels of 2- methoxyestron, 2-methoxy estradiol, dehydroepiandrostion androstendione, aldosterone, and deoxy corticosterone were enhanced significantly in infertile group. While cholesterol and primary bile acids levels were decreased. QDA model showed significant difference between two study groups. Positive and negative predict value levels obtained about 71% and 78%, respectively. ANNs provided also criteria for detection of endometriosis. The QDA and ANNs modeling can be used as computational tools in noninvasive diagnose of endometriosis. However, the model designed by QDA methods is more efficient compared to ANNs in diagnosis of endometriosis patients.

Artificial neural network in diagnosis of urothelial cell carcinoma in urine cytology.

To build up an artificial neural network (ANN) model in the diagnosis of urothelial cell carcinoma (UCC) in urine cytology smears. We randomly selected a total of 115 urine cytology samples, out of which 59 were histopathology proven UCC cases and remaining 56 were benign cases from routine cytology samples. All the carcinoma cases were proven on histopathology. Image morphometric analysis was performed on Papanicolaou's stained smears to study nuclear area, diameter, perimeter, standard deviation of nuclear area, and integrated gray density. Detailed cytological features were also studied in each case by two independent observers and were semi-quantitatively graded. The back propagation ANN model was designed as 17-11-3 with the help of heuristic search. The cases were randomly partitioned as training, validation, and testing sets by the program. There were 79 cases for training set, 18 cases for validation set and 18 cases for test set. In the training set, ANN was able to diagnose all the malignant and benign cases. In the test set, all the benign and malignant cases were diagnosed correctly. However, one of the low grade cases was diagnosed as high grade UCC by ANN model. We successfully built an ANN model in urine from the visual and morphometric data to identify the benign and malignant cases. In addition, the system can also identify the low grade and high grade UCC cases.

Artificial Neural Networks for Diagnosis of Kidney Stones Disease

Artificial Neural networks are often used as a powerful discriminating classifier for tasks in medical diagnosis for early detection of diseases. They have several advantages over parametric classifiers such as discriminate analysis. The objective of this paper is to diagnose kidney stone disease by using three different neural network algorithms which have different architecture and characteristics. The aim of this work is to compare the performance of all three neural networks on the basis of its accuracy, time taken to build model, and training data set size. We will use Learning vector quantization (LVQ), two layers feed forward perceptron trained with back propagation training algorithm and Radial basis function (RBF) networks for diagnosis of kidney stone disease. In this work we used Waikato Environment for Knowledge Analysis (WEKA) version 3.7.5 as simulation tool which is an open source tool. The data set we used for diagnosis is real world data with 1000 instances and 8 attributes. In the end part we check the performance comparison of different algorithms to propose the best algorithm for kidney stone diagnosis. So this will helps in early identification of kidney stone in patients and reduces the diagnosis time.

Artificial neural network in diagnosis of metastatic carcinoma in effusion cytology

To build an artificial neural network (ANN) model for the detection of carcinoma in effusion cytology. We selected a total of 114 effusion cytology cases consisting of 57 each benign and malignant case. In all these cases, detailed cytological features, image morphometric data, densitometric data, and chromatin textural data were collected. Based on these data, we made a back propagation ANN model for diagnosing malignancy in effusion cytology. This network was designed as 25-2-1 (input nodes-hidden nodes-output node). Online back propagation method was applied for training the network. The training of the network was continued until the network error was reduced to 0.000654. Simultaneously, we also performed logistic regression (LR) analysis test to compare with ANN model performance. ANN model worked excellent after adequate training. With the help of this model, it was possible to identify correctly all the malignant cases in validation and test set. The result of the multivariate LR analysis was also similar as that of ANN model and all the cases were also classified correctly. In this study, we successfully constructed an ANN model to diagnose metastatic carcinoma in effusion cytology. ANN is very promising in the diagnosis of metastatic carcinoma in effusion cytology. In future, ANN model may help the cytopathologist to diagnose the difficult cases in effusion fluid.

Artificial neural network in diagnosis of lobular carcinoma of breast in fine‐needle aspiration cytology

In this study, we applied artificial neural network (ANN) for the diagnosis of lobular carcinoma in fine-needle aspiration cytology (FNAC) material. We selected a total of 64 cases of histology proven breast lesions consisting of 20 fibroadenomas, 28 infiltrating ductal carcinomas (IDC), and 16 infiltrating lobular carcinomas (ILC). Detailed cytomorphological features were studied on representative Haematoxylin-Eosin (H&E) and May-Grunwald Giemsa stained slides. Image morphometric analysis was performed on Haematoxylin-Eosin stained smears to study nuclear area, diameter, perimeter, roundness, convex area, and convex perimeter. Both the qualitative cytological features and objective morphometric data were collected and a total of 18 variables were studied. Back propagation ANN was designed and this data were used as input values. ANN network was designed as 34-17-3. There were a total of 34 first layers neurons, 17 hidden neurons and three output neurons. The total cases were randomly divided automatically by the program into three groups: training set (40), validation set (8), and test set (16). After the successful training, the program was able to differentiate all the benign and lobular carcinoma cases and majority of the ductal carcinoma cases. In test set, the ANN program successfully classified all the cases of benign, and ILC cases and six of seven IDC cases. A suitably designed ANN may be able to diagnose the lobular carcinoma of breast on FNAC material. ANN is an efficient software program with immense potential.

An optimal tumor marker group-coupled artificial neural network for diagnosis of lung cancer

Background Epidemiological statistics has shown that there are approximately 1.2 million new cases of lung cancer diagnosed every year and the death rate of these patients is 17.8%. Earlier diagnosis is key to promote the five-year survival rate of these cancer patients. Some tumor markers have been found to be valuable for earlier diagnosis, but a single marker has limitation in its sensitivity and specificity of cancer diagnosis. To improve the efficiency of diagnosis, several distinct tumor marker groups are combined together using a mathematical evaluation model, called artificial neural network (ANN). Lung cancer markers have been identified to include carcinoembryonic antigen, carcinoma antigen 125, neuron specific enolase, β 2-microglobulin, gastrin, soluble interleukin-6 receptor, sialic acid, pseudouridine, nitric oxide, and some metal ions. Methods These tumor markers were measured through distinct experimental procedures in 50 patients with lung cancer, 40 patients with benign lung diseases, and 50 cases for a normal control group. The most valuable were selected into an optimal tumor marker group by multiple logistic regression analysis. The optimal marker group-coupled ANN model was employed as an intelligent diagnosis system. Results We have presented evidence that this system is superior to a traditional statistical method, its diagnosis specificity significantly improved from 72.0% to 100.0% and its accuracy increased from 71.4% to 92.8%. Conclusions The ANN-based system may provide a rapid and accurate diagnosis tool for lung cancer.

Improved Application of Paraconsistent Artificial Neural Networks in Diagnosis of Alzheimer's Disease

Improved Application of Paraconsistent Artificial Neural Networks in Diagnosis of Alzheimer's Disease

Improved Application of Paraconsistent Artificial Neural Networks in Diagnosis of Alzheimer's Disease

Problem statement: The visual analysis of Electroencephalogram (EEG) activity has shown useful as a complementary tool in Alzheimer Disease (AD diagnosis) when the diagnosis remains uncertain, in addition to be used in some clinical protocols. However, this analysis is subject to the inherent equipment imprecision, biological artifact, electrical records, and subjective physician interpretation of the visual analysis variation. The Artificial Neural Network (ANN) could be a helpful tool, appropriate to address problems such as prediction and pattern recognition. Approach: In this study, it was used a new class of ANN, namely the Paraconsistent Artificial Neural Network (PANN), which is capable of handling uncertain, inconsistent, and paracomplete information, for recognizing predetermined patterns of EEG activity and to assess its value as a possible complementary method for AD diagnosis. Thirty three AD patients and thirty four controls patients of EEG records were obtained during relaxed wakefulness. It was considered as normal patient pattern, the background EEG activity between 8.0 Hz and 12.0 Hz (with an average frequency of 10.0 Hz), allowing a range of 0.5 Hz. Results: The PANN was able to recognize waves that belonging to their respective bands of clinical use (theta, delta, alpha, and beta), leading to an agreement with the clinical diagnosis at 80% of sensitivity and at 73% of specificity. Conclusion: Supported by results, the PANN could be a promising tool to manipulate EEG analysis, bearing in mind the following considerations: the growing interest of specialists in EEG visual analysis and the ability of the PANN to deal in directly imprecise, inconsistent and paracomplete data, providing an interesting quantitative and qualitative analysis.

Diagnostic study on arrhythmia cordis based on particle swarm optimization-based support vector machine

Diagnosis of arrhythmia cordis is very significant to ensure human health and save human lives. Support vector machine (SVM) is a new machine learning method based on statistical learning theory, which can solve the classification problem with small sampling, non-linear and high dimension. However, the practicability of SVM is affected due to the difficulty of selecting appropriate SVM parameters. Particle swarm optimization (PSO) is a new optimization method, which is motivated by social behavior of bird flocking or fish schooling. The optimization method not only has strong global search capability, but also is very easy to implement. Thus, in the study, the proposed PSO-SVM model is applied to diagnosis of arrhythmia cordis, in which PSO is used to determine free parameters of support vector machine. The experimental data from MIT-BIH ECG database are used to illustrate the performance of proposed PSO-SVM model. The experimental results indicate that the PSO-SVM method can achieve higher diagnostic accuracy than artificial neural network in diagnosis of arrhythmia cordis.

Design of an Artificial Neural Network for Diagnosis of Facial Pain Syndromes

A classification scheme for facial pain syndromes describing seven categories has previously been proposed. Based on this classification scheme and a binomial (yes/no) facial pain questionnaire, we have designed and trained an artificial neural network (ANN) and as an initial feasibility assessment of such an ANN system examined its ability to recognize and correctly diagnose patients with different facial pain syndromes. One hundred patients with facial pain were asked to respond to a facial pain questionnaire at the time of their initial visit. After interview, an independent diagnosis was assigned to each patient. The patients’ responses to the questionnaire and their diagnoses were input to an ANN. The ANN was able to retrospectively predict the correct diagnosis for 95 of 100 patients (95%), and prospectively determine a correct diagnosis of trigeminal neuralgia Type 1 with 84% sensitivity and 83% specificity in 43 new patients. The ability of the ANN to accurately predict a correct diagnosis for the remaining types of facial pain was limited by our clinic sample size and hence less exposure to those categories. This is the first demonstration of the utilization of an ANN to diagnose facial pain syndromes.

The use of artificial neural networks in decision support in cancer: A systematic review

Artificial neural networks have featured in a wide range of medical journals, often with promising results. This paper reports on a systematic review that was conducted to assess the benefit of artificial neural networks (ANNs) as decision making tools in the field of cancer. The number of clinical trials (CTs) and randomised controlled trials (RCTs) involving the use of ANNs in diagnosis and prognosis increased from 1 to 38 in the last decade. However, out of 396 studies involving the use of ANNs in cancer, only 27 were either CTs or RCTs. Out of these trials, 21 showed an increase in benefit to healthcare provision and 6 did not. None of these studies however showed a decrease in benefit. This paper reviews the clinical fields where neural network methods figure most prominently, the main algorithms featured, methodologies for model selection and the need for rigorous evaluation of results.

Artificial neural networks for diagnosis and survival prediction in colon cancer

ANNs are nonlinear regression computational devices that have been used for over 45 years in classification and survival prediction in several biomedical systems, including colon cancer. Described in this article is the theory behind the three-layer free forward artificial neural networks with backpropagation error, which is widely used in biomedical fields, and a methodological approach to its application for cancer research, as exemplified by colon cancer. Review of the literature shows that applications of these networks have improved the accuracy of colon cancer classification and survival prediction when compared to other statistical or clinicopathological methods. Accuracy, however, must be exercised when designing, using and publishing biomedical results employing machine-learning devices such as ANNs in worldwide literature in order to enhance confidence in the quality and reliability of reported data.

ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES

A procedure is presented for fault diagnosis of rolling element bearings through artificial neural network (ANN). The characteristic features of time-domain vibration signals of the rotating machinery with normal and defective bearings have been used as inputs to the ANN consisting of input, hidden and output layers. The features are obtained from direct processing of the signal segments using very simple preprocessing. The input layer consists of five nodes, one each for root mean square, variance, skewness, kurtosis and normalised sixth central moment of the time-domain vibration signals. The inputs are normalised in the range of 0.0 and 1.0 except for the skewness which is normalised between −1.0 and 1.0. The output layer consists of two binary nodes indicating the status of the machine—normal or defective bearings. Two hidden layers with different number of neurons have been used. The ANN is trained using backpropagation algorithm with a subset of the experimental data for known machine conditions. The ANN is tested using the remaining set of data. The effects of some preprocessing techniques like high-pass, band-pass filtration, envelope detection (demodulation) and wavelet transform of the vibration signals, prior to feature extraction, are also studied. The results show the effectiveness of the ANN in diagnosis of the machine condition. The proposed procedure requires only a few features extracted from the measured vibration data either directly or with simple preprocessing. The reduced number of inputs leads to faster training requiring far less iterations making the procedure suitable for on-line condition monitoring and diagnostics of machines.

Artificial neural networks for diagnosis and prognosis in prostate cancer.

The application of artificial neural networks (ANNs), especially feed-forward neural networks (FFNNs), has become very popular for diagnosis and prognosis in clinical medicine, often accompanied by exaggerated statements of their potential. The excitement stems mainly from the fact that ANNs were developed as attempts to model the decision process of the human brain. Traditionally, logistic regression models and proportional hazard regression models have been used in these applications. In this article, FFNNs are introduced as flexible, nonlinear regression models and necessary precautions for their use are discussed. Furthermore, the results of a literature survey of applications of ANNs in prostate cancer published between 1999 and 2001 are described; most applications suffer from methodologic deficiencies. It is concluded that there is so far no evidence that the application of ANNs provide real progress in the field of diagnosis and prognosis in prostate cancer.

Acute pulmonary embolism: cost-effectiveness analysis of the effect of artificial neural networks on patient care.

To evaluate the cost-effectiveness of artificial neural networks for diagnosis in patients suspected of having acute pulmonary embolism who are typically referred for pulmonary angiography. Four diagnostic strategies were explored to help define the diagnostic role of neural networks in patients suspected of having pulmonary embolism in whom nondiagnostic ventilation-perfusion lung scans were obtained. First, a network was used to determine which patients could be directly referred for treatment without angiography. Second, the network was applied to determine in which patients treatment could be withheld. Third, the network was used to distinguish patients in whom the network gave indeterminate responses and who should proceed to angiography. Each strategy was compared with use of angiography in terms of morbidity, mortality, and cost per life saved. The use of the neural network reduced the average cost per patient by more than one-half relative to the cost of angiography. Morbidity and mortality rates were also comparable to or lower than those associated with angiography. The results were consistent regardless of the prevalence of disease. The use of neural networks in the diagnosis of pulmonary embolism is a promising way to improve cost-effectiveness in the care of patients with nondiagnostic lung scans.