FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2007644401> ?p ?o ?g. }

• W2007644401 endingPage "7" @default.
• W2007644401 startingPage "3" @default.
• W2007644401 abstract "It is a pleasure to be associated with the 10 papers that appear in this special issue of Expert Systems, The Journal of Knowledge Engineering. The papers in this special issue focus on medical decision support systems and on feature extraction/selection for automated diagnostic systems. The foundation for any decision support system is a knowledge base containing the necessary rules and facts, acquired from information and data in the field of interest, in our case medicine. There are three general approaches used to acquire such a knowledge base: traditional expert systems; evidence-based methods; and statistical and artificial intelligence methods. Clinical decision-making is a challenging, multifaceted process. Its goals are precision in diagnosis and the institution of efficacious treatment. Achieving these objectives involves access to pertinent data and application of previous knowledge to the analysis of new data in order to recognize patterns and relations. As the volume and complexity of data have increased, use of digital computers to support data analysis has become a necessity. In addition to computerization of standard statistical analysis, several other techniques for computer-aided data classification and reduction, generally referred to as artificial neural networks, have evolved. Our analysis of recent developments shows that the trend is to develop new methods for computer decision-making in medicine and to evaluate critically these methods in clinical practice. Artificial neural networks have been used in different medical diagnoses and the results were compared with physicians' diagnoses and existing classification methods. Many of them found that artificial neural networks have more flexibility in modelling and give reasonable accuracy in prediction. What makes artificial neural networks a promising tool is their capacity to find near-optimum solutions from limited or incomplete data sets and the fact that learning is accomplished through training. In addition to these characteristics, it has been shown that artificial neural networks can combine data of different natures, such as those derived from clinical protocols, from laboratory data obtained from measurements and from features from signals and images, into a single system thus forming an integrated diagnostic system. Medical diagnostic decision support systems have become an established component of medical technology. The main concept of the medical technology is an inductive engine that learns the decision characteristics of the diseases and can then be used to diagnose future patients with uncertain disease states. A number of quantitative models including linear discriminant analysis, logistic regression, k nearest neighbour, kernel density, recursive partitioning and neural networks are being used in medical diagnostic support systems to assist human decision-makers in disease diagnosis. Artificial neural networks have been used in many medical diagnostic decision support system applications because of the belief that they have good predictive power. Unfortunately, there is no theory available to guide an intelligent choice of model based on the complexity of the diagnostic task. In most situations, developers simply pick a single model that yields satisfactory results, or benchmark a small subset of models with cross-validation estimates on the test sets (West & West, 2000a, 2000b; Kordylewski et al., 2001; Kwak & Choi, 2002). Various methodologies of automated diagnosis have been adopted; however, the entire process can generally be subdivided into a number of disjoint processing modules: preprocessing, feature extraction/selection, and classification. Signal/image acquisition, artefact removal, averaging, thresholding, signal/image enhancement and edge detection are the main operations in the course of preprocessing. The accuracy of signal/image acquisition is of great importance since it contributes significantly to the overall classification result. The markers are subsequently processed by the feature extraction module. The module of feature selection is an optional stage, whereby the feature vector is reduced in size including only, from the classification viewpoint, what may be considered as the most relevant features required for discrimination. The classification module is the final stage in automated diagnosis. It examines the input feature vector and based on its algorithmic nature produces a suggestive hypothesis (West & West, 2000a, 2000b; Kordylewski et al., 2001; Kwak & Choi, 2002). Feature extraction is the determination of a feature or a feature vector from a pattern vector. For pattern processing problems to be tractable requires the conversion of patterns to features, which are condensed representations of patterns, ideally containing only salient information. Feature extraction methods are subdivided into (1) statistical characteristics and (2) syntactic descriptions. Feature selection provides a means for choosing the features which are best for classification, based on various criteria. The feature selection process is performed on a set of predetermined features. Features are selected based on either (1) the best representation of a given class of signals, or (2) the best distinction between classes. Therefore, feature selection plays an important role in classifying systems such as neural networks. For the purpose of classification problems, the classifying system has usually been implemented with rules using if–then clauses, which state the conditions of certain attributes and resulting rules. However, it has proved to be a difficult and time-consuming method. From the viewpoint of managing large quantities of data, it would still be most useful if irrelevant or redundant attributes could be segregated from relevant and important ones, although the exact governing rules may not be known. In this case, the process of extracting useful information from a large data set can be greatly facilitated (West & West, 2000a, 2000b; Kordylewski et al., 2001; Kwak & Choi, 2002; Übeyli, 2007a; 2007b; 2007c; 2007d; 2007e; 2007f; 2008a; 2008b; 2008c; Übeyli et al., 2008). We hope that the collected papers of this issue provide the reader with an excellent discussion of the issues facing the developer of medical decision support systems, the techniques of which medical decision support systems they comprise, and the issues surrounding the effective combination of those techniques. Salem et al. (2009), in their paper ‘Augmentation of a nearest neighbour clustering algorithm with a partial supervision strategy for biomedical data classification’, propose a partial supervision strategy for a recently developed clustering algorithm to act as a classifier. The proposed method (nearest neighbour clustering algorithm) offers classification capability with less a priori knowledge, where a small number of data objects from the entire data set are used as labelled objects to guide the clustering process towards a better search space. The authors examine its applicability and reliability using data sets from two real-world problems: retinal images and breast cancer data. The proposed nearest neighbour clustering algorithm has the ability to classify pixels of retinal images into those belonging to blood vessels and others not belonging to blood vessels, and it also has the ability to classify breast tumours as benign or malignant. Experimental results show that the proposed algorithm offers an improvement in classification accuracy over other classifiers. Polat et al. (2009), in their paper ‘Comparison of different classifier algorithms for diagnosing macular and optic nerve diseases’, compare classifier algorithms including the C4.5 decision tree classifier, the least squares support vector machine and the artificial immune recognition system for diagnosing macular and optic nerve diseases from pattern electroretinography signals. In order to show the test performance of the classifier algorithms, the classification accuracy, receiver operating characteristics curves, and sensitivity and specificity values are used. The classification results obtained demonstrate that the least squares support vector machine classifier is a robust and effective classifier system for the determination of macular and optic nerve diseases. Hussain et al. (2009), in their paper ‘Electromyography signal analysis using wavelet transform and higher order statistics to determine muscle contraction’, investigate the usefulness of a wavelet based noise removal technique of surface electromyography signal processing and analyse the signals using higher order statistics. The results show that although wavelet function Daubechies of order 2 is the best choice among other wavelets to denoise the surface electromyography signal, higher order statistics are preferable for suppressing Gaussian white noise. Karlιk et al. (2009), in their paper ‘Differentiating types of muscle movements using a wavelet based fuzzy clustering neural network’, consider four different arm movements (elbow extension, elbow flexion, wrist supination and wrist pronation) in the analysis of muscle contraction. Wavelet parameters of myoelectric signals received from the muscles for these different movements are used as features to classify electromyogram signals by a fuzzy clustering neural network. The results show that the proposed wavelet based fuzzy clustering neural network method gives better classification accuracies for the electromyogram signals than other previously reported techniques. Uhmn et al. (2009), in their paper ‘A study on application of single nucleotide polymorphism and machine learning techniques to diagnosis of chronic hepatitis’, use several machine learning techniques to predict susceptibility to the liver disease chronic hepatitis from single nucleotide polymorphism data. They apply a backtracking technique to a couple of feature selection algorithms, forward selection and backward elimination, and show that the proposed technique is beneficial in finding better solutions by experiment. The authors evaluate the possibility of machine learning techniques, support vector machine, decision tree, decision rule and k nearest neighbour algorithm, as a tool to diagnose chronic hepatitis. Sunay et al. (2009), in their paper ‘Feasibility of probabilistic neural networks, Kohonen self-organizing maps and fuzzy clustering for source localization of ventricular focal arrhythmias from intravenous catheter measurements’, investigate the feasibility of several pattern classification and neural network approaches for the localization of the source of ventricular arrhythmias from sparse measurements acquired from within coronary veins. Specifically, they study the Kohonen self-organizing maps and fuzzy C-means clustering methods for the construction of the target vector in neural networks from experimental high-resolution activation-time patterns. They also study two neural network techniques, probabilistic neural networks and backpropagation networks, for training and testing procedures. The results show that the combination of the probabilistic neural networks, Kohonen self-organizing maps and fuzzy C-means clustering approaches is feasible in catheter-based epicardial arrhythmia source localization. Melek and Sadeghian (2009), in their paper ‘A theoretic framework for intelligent expert systems in medical encounter evaluation’, describe the development of a neuro-fuzzy medical diagnosis expert system that can be used by physicians in their daily practice. The proposed expert system allows general physicians and interns to follow their natural process in patient assessment while helping them arrive at the final diagnosis more quickly and efficiently. The use of systematic assessment and learning tools increases the end user's acceptance and adoption of the expert system due to its resemblance to the line of reasoning of medical experts and specialists. Moreover, the expert system approach can be extended to provide intelligent tools for evaluation and management of patient encounters in other medical specialties. Delen (2009), in his paper ‘Analysis of cancer data: a data mining approach’, reports a research project aimed at developing prediction models and explaining prognostic factors of prostate cancer survivability. Four modelling techniques are used: a traditional statistical logistic regression model, together with three machine learning techniques (decision trees, artificial neural networks and support vector machines). A k-fold cross-validation methodology is used in model building, evaluation and comparison. The results show that support vector machines are the most accurate predictor for the analysed domain, followed by artificial neural networks and decision trees. González Navarro and Belanche Muñoz (2009), in their paper ‘Gene subset selection in microarray data using entropic filtering for cancer classification’, describe an entropic filtering algorithm for feature selection as a workable method to generate a relevant subset of genes. This is a fast feature selection method based on finding feature subsets that jointly maximize the normalized multivariate conditional entropy with respect to classification ability of tumours. The entropic filtering algorithm is tested in combination with several machine learning algorithms on five public domain microarray data sets. It is found that this combination offers subsets yielding similar or much better accuracies than using the full set of genes. Mehta et al. (2009), in their paper ‘Detection and delineation of P and T waves in 12-lead electrocardiograms’, present an efficient method for the detection and delineation of P and T waves in 12-lead electrocardiograms using a support vector machine. Digital filtering techniques are used to remove power line interference and baseline wander. The performance of the algorithm is validated using original simultaneously recorded 12-lead electrocardiogram recordings from the standard CSE electrocardiogram multi-lead measurement library. Delineation performance of the algorithm is validated by calculating the mean and standard deviation of the differences between automatic and manual annotations. The proposed method successfully detects all kinds of morphologies of P and T waves. Many individuals contributed to this special issue. I would like to thank the Editors-in-Chief of Expert Systems, Lucia Rapanotti and Jon G. Hall, for their enthusiasm and continuing support for the special issue. Many of the original reviewers helped in the preparation of the issue, and I thank them greatly for their help. Thanks also to those in Wiley-Blackwell's Expert Systems' office who have made this special issue available in good time. Elif Derya Übeyli Elif Derya Übeyli (http://edubeyli.etu.edu.tr/) is an Associate Professor at the Department of Electrical and Electronics Engineering, TOBB University of Economics and Technology. She obtained a PhD degree in electronics and computer technology from Gazi University in 2004. She has worked on a variety of topics including biomedical signal processing, neural networks, optimization and artificial intelligence. She has worked on several projects related to biomedical signal acquisition, processing and classification. Dr Übeyli has served (or is currently serving) as a program organizing committee member of national and international conferences. She is an editorial board member of several scientific journals (Journal of Engineering and Applied Sciences, International Journal of Soft Computing, Research Journal of Applied Sciences, Research Journal of Medical Sciences, Scientific Journals International/Electrical, Mechanical, Manufacturing, and Aerospace Engineering, The Open Medical Informatics Journal, Bulletin of the International Scientific Surgical Association, Nano Science and Nano Technology: An Indian Journal). She is Associate Editor of Expert Systems. Moreover, she is voluntarily serving as a technical publication reviewer for many respected scientific journals and conferences. She has published 109 journal papers and 42 conference papers on her research areas." @default.
• W2007644401 created "2016-06-24" @default.
• W2007644401 creator A5042153931 @default.
• W2007644401 date "2009-02-01" @default.
• W2007644401 modified "2023-10-17" @default.
• W2007644401 title "Advances in medical decision support systems" @default.
• W2007644401 cites W1967803810 @default.
• W2007644401 cites W1974688913 @default.
• W2007644401 cites W1997397465 @default.
• W2007644401 cites W2004360581 @default.
• W2007644401 cites W2008229347 @default.
• W2007644401 cites W2015011285 @default.
• W2007644401 cites W2028470104 @default.
• W2007644401 cites W2029503776 @default.
• W2007644401 cites W2043877529 @default.
• W2007644401 cites W2073586020 @default.
• W2007644401 cites W2088021801 @default.
• W2007644401 cites W2091666972 @default.
• W2007644401 cites W2093559204 @default.
• W2007644401 cites W2113788419 @default.
• W2007644401 cites W2113890143 @default.
• W2007644401 cites W2133647570 @default.
• W2007644401 cites W2146231764 @default.
• W2007644401 cites W2146267746 @default.
• W2007644401 cites W2149273020 @default.
• W2007644401 cites W2158228201 @default.
• W2007644401 cites W2161039340 @default.
• W2007644401 doi "https://doi.org/10.1111/j.1468-0394.2008.00503.x" @default.
• W2007644401 hasPublicationYear "2009" @default.
• W2007644401 type Work @default.
• W2007644401 sameAs 2007644401 @default.
• W2007644401 citedByCount "4" @default.
• W2007644401 countsByYear W20076444012012 @default.
• W2007644401 countsByYear W20076444012018 @default.
• W2007644401 countsByYear W20076444012019 @default.
• W2007644401 crossrefType "journal-article" @default.
• W2007644401 hasAuthorship W2007644401A5042153931 @default.
• W2007644401 hasBestOaLocation W20076444011 @default.
• W2007644401 hasConcept C107327155 @default.
• W2007644401 hasConcept C154945302 @default.
• W2007644401 hasConcept C2522767166 @default.
• W2007644401 hasConcept C41008148 @default.
• W2007644401 hasConceptScore W2007644401C107327155 @default.
• W2007644401 hasConceptScore W2007644401C154945302 @default.
• W2007644401 hasConceptScore W2007644401C2522767166 @default.
• W2007644401 hasConceptScore W2007644401C41008148 @default.
• W2007644401 hasIssue "1" @default.
• W2007644401 hasLocation W20076444011 @default.
• W2007644401 hasOpenAccess W2007644401 @default.
• W2007644401 hasPrimaryLocation W20076444011 @default.
• W2007644401 hasRelatedWork W1596801655 @default.
• W2007644401 hasRelatedWork W2130043461 @default.
• W2007644401 hasRelatedWork W2350741829 @default.
• W2007644401 hasRelatedWork W2358668433 @default.
• W2007644401 hasRelatedWork W2376932109 @default.
• W2007644401 hasRelatedWork W2382290278 @default.
• W2007644401 hasRelatedWork W2390279801 @default.
• W2007644401 hasRelatedWork W2748952813 @default.
• W2007644401 hasRelatedWork W2899084033 @default.
• W2007644401 hasRelatedWork W2530322880 @default.
• W2007644401 hasVolume "26" @default.
• W2007644401 isParatext "false" @default.
• W2007644401 isRetracted "false" @default.
• W2007644401 magId "2007644401" @default.
• W2007644401 workType "article" @default.