Diagnosis of liver disease by using CMAC neural network approach

A neural network-based method is presented for the diagnosis and classification of patients infected with hepatotropic viral disease. The non-invasive approach makes use of real-time pathological data in form of liver function tests and specific virological markers during training. The unknown patients, not included in the training set, are then processed through the trained neural network model. Experimental results demonstrate that the proposed method is able to effectively diagnose the disease and classifies its stage to be acute, chronic or cirrhosis. In addition, performance analysis is carried out for various supervised and unsupervised neural network models with optimal topologies. The topological architectures are chosen after experimenting with various training algorithms using diverse parameters such as different activation functions between layers, number of hidden layers, and number of neurons. It is concluded that the performance of the multilayered supervised feedforward neural network is the most accurate even with small data set. Whereas, the unsupervised Kohonen's selforganising maps do not perform well for the subject task under similar conditions.

Journal of medical systems, 2011

We designed an artificial neural network (ANN) to diagnose cirrhosis in patients with chronic HBV infection. Routine laboratory data (PT, INR, platelet count, direct bilirubin, AST/ALT, AST/PLT) and age were collected from 144 patients. Cirrhosis in these patients was diagnosed by liver biopsy. The ANN's ability was assessed using receiver-operating characteristic (ROC) analysis and the results were compared with a logistic regression model. Our results indicate that the neural network analysis is likely to provide a non-invasive, accurate test for diagnosing cirrhosis in chronic HBV-infected patients, only based on routine laboratory data.

Dicle Medical Journal / Dicle Tip Dergisi, 2015

Hepatit hastalığının teşhisi için çok katmanlı sinir ağı (MLNN) ve sigmoid aktivasyon fonksiyonu uygulanmıştır. Yöntemler: Yapay sinir ağları (YSA) tıbbi tanı için halen yaygın olarak kullanılan etkili araçlardır. Donanım tabanlı mimarilerde aktivasyon fonksiyonları YSA davranışında önemli rol oynamaktadır. Sigmoid fonksiyonu yumuşak tepkisi nedeniyle en sık kullanılan aktivasyon fonksiyonudur. Bu nedenle, sigmoid fonksiyonu ve yaklaşımları aktivasyon fonksiyonu olarak uygulanmıştır. Veri kümesi UCI makine öğrenme veri tabanından alınmıştır. Bulgular: Hepatit hastalığının tanısı için, MLNN yapısı hayata geçirilmiş ve Levenberg Morquardt (LM) algoritması öğrenme için kullanılmıştır. Hepatit hastalığını sınıflandıran yöntemimiz 10-kat çapraz doğrulama yoluyla 91.9%'den 93.8%'e doğruluklar sağlamıştır. Sonuç: Yapay sinir ağları ve aynı veri setini kullanarak hepatit hastalığını teşhis eden önceki çalışma ile karşılaştırıldığında, bizim sonuçlarımız sinir ağı tabanlı donanımın boyutunu ve maliyetini azaltması bakımından umut vericidir. Böylece, donanım tabanlı tanı sistemleri sigmoid fonksiyonu yaklaşımları kullanılarak etkili bir şekilde geliştirilebilir. Anahtar kelimeler: Hepatit hastalığı tanısı, çok katmanlı sinir ağı, 10-kat çapraz doğrulama, sigmoid aktivasyon fonksiyonu yaklaşımları ABSTRACT Objective: Implementation of multilayer neural network (MLNN) with sigmoid activation function for the diagnosis of hepatitis disease. Methods: Artificial neural networks (ANNs) are efficient tools currently in common use for medical diagnosis. In hardware based architectures activation functions play an important role in ANN behavior. Sigmoid function is the most frequently used activation function because of its smooth response. Thus, sigmoid function and its close approximations were implemented as activation function. The dataset is taken from the UCI machine learning database. Results: For the diagnosis of hepatitis disease, MLNN structure was implemented and Levenberg Morquardt (LM) algorithm was used for learning. Our method of classifying hepatitis disease produced an accuracy of 91.9% to 93.8% via 10 fold cross validation. Conclusion: When compared to previous work that diagnosed hepatitis disease using artificial neural networks and the identical data set, our results are promising in order to reduce the size and cost of neural network based hardware. Thus, hardware based diagnosis systems can be developed effectively by using approximations of sigmoid function.

International Journal of Engineering and Technology, 2016

Neural Network(NN) is widely used in medical research because of its cost effectiveness and easy-to-use systems. NN plays an important role in the decision support system. The sole reason to use the efficient NN model is to manage the rapidly increasing medical data effectively and use these data points for accurate prediction of diseases and thereby providing better health care to the patients. In this paper we have made use of two classification algorithmsi.e. feedforwardbackpropagation neural network(FFBPNN) and Cascade Correlationfeedforward network (CCFFN) and compared the performance of both the algorithms on the basis of sensitivity, specificity and accuracy. The experiment is done on Bupa liver dataset using FFBPNN and CCFFN model using different set of neurons which are trained with Levenberg-Marquardt training algorithm(trainlm) and ResilientBackpropagationtraining algorithm (trainrp). This paper has provided the comparative analysis among different classifiers using two different training algorithmsto find the benign and malignant patients.

In recent years, liver diseases have increased to a great extent in a way that it has turned into one of the most fatal diseases in the world. On time diagnosis of this disease can be effective in the prevention of its bad effects, its control and remedy. With technology advancement and changing many issues in software industry, doctors have developed a tendency towards intelligent systems for better diagnosis. Thus, in this paper, we have diagnosed liver sickness using fuzzy logic by obtaining important laboratory parameters. We have used two types of triangular membership function and Gussy membership function per 3 membership function for each input and output and also the design of reference table (search) to construct fuzzy heuristic system and we have managed to compare 243 rules. At the end, we were able to reach to 79/83% of accuracy with the appropriate choice of input parameters, the number and type of membership functions. Keywords: Liver Sickness, Fuzzy logic, Reference Table, Fuzzy Heuristic System, Membership Function.

Proceedings of the 8th conference on …, 2008

Haya Shida, Subscribe (Full Service), Register (Limited Service, Free), Login. Search: The ACM Digital Library The Guide. ...

The accessibility of large amounts of medicinal data in clinics and hospitals pointers to the focus on reliable information analysis software to exploit useful information. Many tools tried to diagnosis hepatitis disease but still there is a deficiency of analyzing the biological data of Hepatitis illness in the world, where millions of people are killed in the world by this disease. This research aims at investigating the neural network algorithm for hepatitis disease. The data mining processes applied on the UCI dataset. Our investigation model examined different types of neural network algorithms (Quick, Multiple, Dynamic and RBFN) with different factors such as data size, learning cycle, and processing time to achieve the diagnosis accuracy and estimated error. The Multiple neural networks proved the best performance compared with Quick, Dynamic, and RBF neural network algorithms.

International Journal of Computing and Digital Systems, 2022

The liver is a crucial and big organ in the human body, impacts the digestion system. Due to Liver diseases (LDs), so many deaths are occurred in worldwide that nearly 2 million deaths per year. The main LD complications are cirrhosis that 11th position in universal deaths, and others hepatocellular carcinoma and viral hepatitis that 16th leading position for global deaths. Fortunately, 3.5% of deaths are occurred due to LD. The capability of an ML approach for controlling LD can be identified through their factors, co-factors as well as complications respectively. In this research, we gather the personal and clinical information about1460 individuals with 17 LD feature attributes include diagnosis class attribute from 2018 to 2020 with good questionnaire from north coastal districts of A.P., India hospitals, and reputed clinical centers. We apply machine learning (ML) models like Logistic Regression (LR), SVM with RBF kernel, Naive Bayes (NB), KNN, and Decision Tree (DT or Tree). As per the ML model's analysis, the DT model presents the superior classification accuracy that value is 0.9712 (97.12%) than other experimental ML models for the collected LD dataset. Our proposal model incremental hidden layer (HL) neurons ANN (Artificial Neural Network) solutes LD detection with the highest classification and testing accuracy that the value is 0.999 (99.9%) at the 30 HL neurons.

2023

Liver disease is a liver disease caused by viruses, alcohol, lifestyle and others. Someone often does not realize or is late to know liver disease so that when examined liver disease is severe, it would be better if treatment is done early by knowing the symptoms suffered. Data mining can help diagnose liver disease more easily, especially to help doctors determine whether patients suffer from liver disease or not, with symptoms almost close to liver disease. The process of diagnosing liver disease is carried out by a classification process and the result is that the patient suffers from liver or not. This research uses a data mining classification method using an artificial neural network method, namely Multilayer Perceptron. The Indian Liver Patient Dataset (ILPD) used in this study was obtained from the UCI Machine Learning Repository. The division of the data set over the training data and test data is done by Cross Validation. Performance measurement of the method uses confusion matrix. Based on the research conducted, it was found that the application of Multilayer Perceptron resulted in varying accuracy based on testing with different Fold values with the highest accuracy of 83.70% when the Fold was 7, and the lowest accuracy of 80.57% when the Fold was 3. Then the average accuracy of all Fold tests is 82.13%

Journal of Network Communications and Emerging Technologies (JNCET), 2020

In the last couple of decades, the diagnosis of liver diseases using computational techniques was heavily investigated. This study focuses on the using of a Neural Network ensemble-based method for effective diagnosis of liver diseases. In this study, a Neural Network ensemble-based method was proposed to predict liver diseases. Although ANN and other classification approaches have been heavily investigated in recent years, the using of ensemble-based approaches to predict liver diseases has not been thoroughly investigated. The proposed model relies on using five different ANN nodes. Using the commonly used Indian Liver Patient Dataset, which is provided by the University of California, Irvine, and SAS software suite evaluates the accuracy of the proposed model. The obtained results indicate that in the validation phase the classification accuracy of the proposed model to predict liver diseases is 74.35%. Also, in terms of important classification metrics such as specificity, sensitivity, precision, false-positive rate, false-negative rate and F_1(F-measure) in the training phase the proposed model achieved the rates 36.36%, 89.28%, 78.12%, 63.64 %, 10.72% and 83.33%, respectively. The results are very promising for researchers and practitioners working in related fields. Index Terms-Liver diseases; classification; artificial neural networks; ensemble-based methods; SAS software suite.