Medical Diagnosis Problems Research Articles

Robust BMPM training based on second-order cone programming and its application in medical diagnosis

The Biased Minimax Probability Machine (BMPM) constructs a classifier which deals with the imbalanced learning tasks. It provides a worst-case bound on the probability of misclassification of future data points based on reliable estimates of means and covariance matrices of the classes from the training data samples, and achieves promising performance. In this paper, we develop a novel yet critical extension training algorithm for BMPM that is based on Second-Order Cone Programming (SOCP). Moreover, we apply the biased classification model to medical diagnosis problems to demonstrate its usefulness. By removing some crucial assumptions in the original solution to this model, we make the new method more accurate and robust. We outline the theoretical derivatives of the biased classification model, and reformulate it into an SOCP problem which could be efficiently solved with global optima guarantee. We evaluate our proposed SOCP-based BMPM (BMPMSOCP) scheme in comparison with traditional solutions on medical diagnosis tasks where the objectives are to focus on improving the sensitivity (the accuracy of the more important class, say "ill" samples) instead of the overall accuracy of the classification. Empirical results have shown that our method is more effective and robust to handle imbalanced classification problems than traditional classification approaches, and the original Fractional Programming-based BMPM (BMPMFP).

An algorithm for the recognition of levels of congestion in road traffic problems

Detection and recognition of the level of congestion at an intersection is a very important problem and a valuable source of information in traffic management. Although it is just one of all the aspects that make up a traffic management system, it seems to be a crucial point for gathering information. In this paper, we present a technique based on a k-means clustering algorithm for classification, which has been already successfully used in a number of pattern recognition problems, namely: as an algorithm for face recognition problems and in a number of medical diagnosis problems and it compares very well with the state of the art techniques.

Dual concerns with the dualist approach

AbstractBarbey & Sloman (B&S) attribute all instances of normative base-rate usage to a rule-based system, and all instances of neglect to an associative system. As it stands, this argument is too simplistic, and indeed fails to explain either good or bad performance on the classic Medical Diagnosis problem.

Patella sex determination by 3D statistical shape models and nonlinear classifiers

Sex determination is one of the essential steps in personal identification of an individual from skeletal remains. Most elements of the skeleton have been subjected to discriminant function analysis for sex estimation, but little work has been done in terms of the patella. This paper proposes a new sex determination method from the patella using a novel automated feature extraction technique. A dataset of 228 patellae (95 females and 133 males) was amassed from the William M. Bass Donated Skeletal Collection from the University of Tennessee and was subjected to noninvasive high resolution computed tomography (CT). After the CT data were segmented, a set of features was automatically extracted, normalized, and ranked. The segmentation process with surface smoothing minimizes the noise from enthesophytes and ultimately allows our methods to distinguish variations in patellar morphology. These features include geometric features, moments, principal axes, and principal components. A feature vector of dimension 45 for each subject was then constructed. A set of statistical and supervised neural network classification methods were used to classify the sex of the patellar feature vectors. Nonlinear classifiers such as neural networks have been used in previous research to analyze several medical diagnosis problems, including quantitative tissue characterization and automated chromosome classification. In this paper, different classification methods were compared. Classification success ranged from 83.77% average classification rate using labels from a Fuzzy C-Means (FCM) clustering step, to 90.3% for linear discriminant classification (LDC). We obtained results of 96.02% and 93.51% training and testing classification rates, respectively, using feed-forward backpropagation neural networks (NN). These promising results using newly developed features and the application of nonlinear classifiers encourage the usage of these methods in forensic anthropology for identifying the sex of an individual from incomplete skeletons retaining at least one patella.

Prediction of hepatitis disease based on principal component analysis and artificial immune recognition system

In this study, prediction of hepatitis disease, which is a very common and important disease, was conducted with principal component analysis (PCA) and artificial immune recognition system (AIRS). The proposed approach consists of two stages. Firstly, the feature number of hepatitis disease dataset was reduced to 5 from 19 by principal component analysis (PCA). Secondly, hepatitis disease dataset is normalized in the range of [0, 1]. Normalized input values is classified by using AIRS classifier system. We took the dataset used in our study from the UCI Machine Learning Database. The obtained classification accuracy of our system was 94.12% using 10-fold cross-validation and it was very promising with regard to the other classification applications in Literature for this problem. Testing results were found to be compliant with the expected results that are derived from the physician’s direct diagnosis. The end benefit would be to assist the physician to make the final decision without hesitation. This result is for hepatitis disease but it states that this method can be used confidently for other medical diseases diagnosis problems, too.

Detection of ECG Arrhythmia using a differential expert system approach based on principal component analysis and least square support vector machine

Changes in the normal rhythm of a human heart may result in different cardiac arrhythmias, which may be immediately fatal or cause irreparable damage to the heart sustained over long periods of time. The ability to automatically identify arrhythmias from ECG recordings is important for clinical diagnosis and treatment. In this study, we have detected on ECG Arrhythmias using principal component analysis (PCA) and least square support vector machine (LS-SVM). The approach system has two stages. In the first stage, dimension of ECG Arrhythmias dataset that has 279 features is reduced to 15 features using principal component analysis. In the second stage, diagnosis of ECG Arrhythmias was conducted by using LS-SVM classifier. We took the ECG Arrhythmias dataset used in our study from the UCI (from University of California, Department of Information and Computer Science) machine learning database. Classifier system consists of three stages: 50–50% of training-test dataset, 70–30% of training-test dataset and 80–20% of training-test dataset, subsequently, the obtained classification accuracies; 96.86%, 100% ve 100%. The end benefit would be to assist the physician to make the final decision without hesitation. This result is for ECG Arrhythmias disease but it states that this method can be used confidently for other medical diseases diagnosis problems, too.

Automated identification of cancerous smears using various competitive intelligent techniques

In this study the performance of various intelligent methodologies is compared in the task of pap-smear diagnosis. The selected intelligent methodologies are briefly described and explained, and then, the acquired results are presented and discussed for their comprehensibility and usefulness to medical staff, either for fault diagnosis tasks, or for the construction of automated computer-assisted classification of smears. The intelligent methodologies used for the construction of pap-smear classifiers, are different clustering approaches, feature selection, neuro-fuzzy systems, inductive machine learning, genetic programming, and second order neural networks. Acquired results reveal the power of most intelligent techniques to obtain high quality solutions in this difficult problem of medical diagnosis. Some of the methods obtain almost perfect diagnostic accuracy in test data, but the outcome lacks comprehensibility. On the other hand, results scoring high in terms of comprehensibility are acquired from some methods, but with the drawback of achieving lower diagnostic accuracy. The experimental data used in this study were collected at a previous stage, for the purpose of combining intelligent diagnostic methodologies with other existing computer imaging technologies towards the construction of an automated smear cell classification device.

A new medical decision making system: Least square support vector machine (LSSVM) with Fuzzy Weighting Pre-processing

The use of machine learning tools in medical diagnosis is increasing gradually. This is mainly because the effectiveness of classification and recognition systems has improved in a great deal to help medical experts in diagnosing diseases. This study aims at diagnosing Liver Disorder with a new hybrid machine learning method. By hybridizing LSSVM with Fuzzy Weighting Pre-processing, a method was obtained to solve this diagnosis problem via classifying Liver Disorder. Fuzzy Weighting Pre-processing stage was developed firstly in our study. This Liver Disorder dataset is a very commonly used dataset in literature relating the use of classification systems for Liver Disorder Diagnosis and it was used in this study to compare the classification performance of our proposed method with regard other studies. We obtained a classification accuracy of 94.29%, which is the highest one reached so far. This result is for Liver Disorder but it states that this method can be used confidently for other medical diseases diagnosis problems, too.

Accurate and reliable diagnosis and classification using probabilistic ensemble simplified fuzzy ARTMAP

In this paper, an accurate and effective probabilistic plurality voting method to combine outputs from multiple simplified fuzzy ARTMAP (SFAM) classifiers is presented. Five ELENA benchmark problems and five medical benchmark data sets have been used to evaluate the applicability and performance of the proposed probabilistic ensemble simplified fuzzy ARTMAP (PESFAM) network. Among the five benchmark problems in ELENA project, PESFAM outperforms the SFAM and multi-layer perceptron (MLP) classifier. In addition, the effectiveness of the proposed PESFAM is delineated in medical diagnosis applications. For the medical diagnosis and classification problems, PESFAM achieves 100 percent in accuracy, specificity, and sensitivity based on the 10-fold crossvalidation and these results are superior to those from other classification algorithms. In addition, a posteri probability of the predicted class can be used to measure the prediction reliability of PESFAM. The experiments demonstrate the potential of the proposed multiple SFAM classifiers in offering an optimal solution to the data-ordering problem of SFAM implementation and also as an intelligent medical diagnosis tool.

FUZZY METHODS FOR MEDICAL DIAGNOSIS

ABSTRACT This paper argues that fuzzy representations are appropriate in applications where there are major sources of imprecision and/or uncertainty. Case studies of fuzzy approaches to specific problems of medical diagnosis and classification are described in support of this argument. The case studies are in the areas of categorical consistency, diagnostic monitoring, and scoring. The solutions use a variety of fuzzy methods, including clustering, fuzzy set aggregation, and type-2 fuzzy set modeling of linguistic approximations. It is concluded that the fuzzy approach to the development of artificial intelligence in application systems in beneficial in these contexts because of the need to focus on uncertainty as a main issue.

A learning method of immune multi-agent neural networks

Many different learning algorithms for neural networks have been developed, with advantages offered in terms of network structure, initial values of some parameters, learning speed, and learning accuracy. If we train the networks only on good examples, without noise and shortage, the neural network can be trained to classify, with reasonable accuracy, target patterns or random patterns, but not both. To solve this problem, we propose a learning method of immune multi-agent neural networks (IMANNs), which have agents of macrophages, B-cells and T-cells. Each agent employs a different type of neural network. Because the agents work cooperatively and competitively, IMANNs can automatically classify the training dataset into some subclasses. In this paper, two types of IMANNs are described and their classification capabilities are compared. In order to verify the effectiveness of our proposed method, we used two datasets: the dataset of the MONK’s problem (as a traditional classification problem) and a dataset from a medical diagnosis problem (hepatobiliary disorders).

Using uncorrelated discriminant analysis for tissue classification with gene expression data

The classification of tissue samples based on gene expression data is an important problem in medical diagnosis of diseases such as cancer. In gene expression data, the number of genes is usually very high (in the thousands) compared to the number of data samples (in the tens or low hundreds); that is, the data dimension is large compared to the number of data points (such data is said to be undersampled). To cope with performance and accuracy problems associated with high dimensionality, it is commonplace to apply a preprocessing step that transforms the data to a space of significantly lower dimension with limited loss of the information present in the original data. Linear Discriminant Analysis (LDA) is a well-known technique for dimension reduction and feature extraction, but it is not applicable for undersampled data due to singularity problems associated with the matrices in the underlying representation. This paper presents a dimension reduction and feature extraction scheme, called Uncorrelated Linear Discriminant Analysis (ULDA), for undersampled problems and illustrates its utility on gene expression data. ULDA employs the Generalized Singular Value Decomposition method to handle undersampled data and the features that it produces in the transformed space are uncorrelated, which makes it attractive for gene expression data. The properties of ULDA are established rigorously and extensive experimental results on gene expression data are presented to illustrate its effectiveness in classifying tissue samples. These results provide a comparative study of various state-of-the-art classification methods on well-known gene expression data sets.

A multiple decision trees architecture for medical diagnosis: The differentiation of opening snap, second heart sound split and third heart sound

In this paper a Decision Support System Architecture is proposed for the heart sound diagnosis problem, and in general for complex medical diagnosis problems. It is based on the division of a complex diagnostic problem into simpler sub-problems; each of them is handled by a specialized decision tree. This Multiple Decision Trees Architecture in general consists of a network of detection decision trees and arbitration decision trees, and can also incorporate other classification methods as well (e.g. patterns recognition, neural networks, etc.). The initial motivation for developing this Multiple Decision Trees Architecture has been the problem of differentiation among Opening Snap (OS), 2nd Heart Sound Split (A2_P2), and 3rd Heart Sound (S3), which is a crucial and at the same time difficult and complicated part of the heart sound diagnosis problem. The Multiple Decision Tree Architecture developed for the above diagnosis/differentiation problem has been tested with real heart sound signals, and its performance and generalisation capabilities were found to be higher than the previous ‘traditional’ architectures.

An evolutionary system for neural logic networks using genetic programming and indirect encoding

Nowadays, intelligent connectionist systems such as artificial neural networks have been proved very powerful in a wide area of applications. Consequently, the ability to interpret their structure was always a desirable feature for experts. In this field, the neural logic networks (NLN) by their definition are able to represent complex human logic and provide knowledge discovery. However, under contemporary methodologies, the training of these networks may often result in non-comprehensible or poorly designed structures. In this work, we propose an evolutionary system that uses current advances in genetic programming that overcome these drawbacks and produces neural logic networks that can be arbitrarily connected and are easily interpretable into expert rules. To accomplish this task, we guide the genetic programming process using a context-free grammar and we encode indirectly the neural logic networks into the genetic programming individuals. We test the proposed system in two problems of medical diagnosis. Our results are examined both in terms of the solution interpretability that can lead in knowledge discovery, and in terms of the achieved accuracy. We draw conclusions about the effectiveness of the system and we propose further research directions.

A model for single and multiple knowledge based networks

The inherent black-box nature of neural networks is an important drawback with respect to the problem of explanation of neural network responses. Although several articles have tackled the problem of rule extraction from a single neural network, just a few papers have investigated rule extraction from several combined neural networks. In this article we describe how to translate symbolic rules into the Discretized Interpretable Multi-Layer Perceptron (DIMLP) and how to extract rules from one or several combined neural networks. Our approach consists of characterizing discriminant hyperplane frontiers. Unordered rules are extracted in polynomial time with respect to the size of the problem and the size of the network. Moreover, the degree of matching between extracted rules and neural network responses is 100% on training examples. We applied single DIMLP networks to 17 data sets related to medical diagnosis and medical prognosis problems. Results based on 10-fold cross-validation showed that the DIMLP model was on average as accurate as standard multi-layer perceptrons (MLP). Furthermore, DIMLP networks were significantly more accurate than CN2 on eight problems, whereas only on one problem CN2 was better than DIMLP. Finally, a non-Hodgkin lymphoma diagnosis problem based on classification of electrophoresis gels was defined. It turned out that ensembles of DIMLP networks were significantly more accurate than CN2 (96.1%±1.4 versus 82.7%±4.0). Finally, symbolic rules revealed the presence of five important spots for the discrimination of the class of Lymphocyte Leukemia/Chronic Lymphoid Leukemia (Lc/LLc), and the class of Centrocytic Lymphoma (Cc).

Substance use in the general hospital

Introduction: People misusing substances are overrepresented in health settings. Substance misuse can also be an underlying factor complicating medical diagnosis and management. Aims: (i) To establish the prevalence of substance misuse in the general hospital inpatient population; and (ii) to examine the relationship between medical diagnosis and substance misuse problem as identified by screening tools. Method: This study adopted a three-step screening approach including a prospective questionnaire survey, interview, and case note review. Subjects included all adult patients admitted to a London teaching hospital over a 1-week period. Results: Seventy percent completed the questionnaire. Twenty-three percent was currently smoking, 14% was rated positive for alcohol misuse, and 12% positive for drug misuse. Only 65% of patients was screened for smoking, 54% for alcohol, and 9% for other substances. Conclusions: People misusing one substance were more likely to be misusing others, hence the importance of screening all patients for all substances. Doctors were screening a small percentage of patients and they identified and intervened with only the severe ones.

Image reconstruction for electromagnetic field visualization by an inverse problem solution

The purpose of this article is to apply an inverse approach for image reconstruction during electromagnetic field visualization. The reconstruction of the images is formulated as an inverse problem. For the image color model, the Poisson equation with open boundary condition is imposed. The color source densities have been evaluated from the color distributions for electromagnetic field data set. The Generalized Vector Sampled Pattern Matching method is applied to solve an ill posed linear system of equations for the corresponding inverse problem. The new color distributions are generated and visualized using the obtained color source densities. With the proposed inverse approach the dark parts of the images can be reduced or completely removed. This article collects several examples for electromagnetic field visualization of the most commonly used sensor coil. Visualization techniques facilitate the examination of unknown data sets and play an integral role in modeling and investigation of electromagnetic devices. The field distribution is of main importance considering many identification, NDT or EMC problems (1). The Finite Element Method (FEM) or Boundary Element Method (BEM) are usually used for investigation of varies electromechanical devices. The results obtained are visualized using different visualization techniques. Sometimes the images are with not good quality or the data obtained do not correspond to the area of interest. To obtain new results, new FEM or BEM calculations are required which are accompanied by a lot of efforts and computational time. This is one of the main difficulties building interactive simulation and visualization systems. Many problems in medical diagnosis, as well as in industry quality control, require reducing the dark spots of the images. In order to reconstruct the images we propose an approach using formulation and solution of the inverse problem over the image. The image quality depends on the image resolution and color distribution. The image is considered as a 2D-distribution of color components - Red, Green, and Blue (RGB). The 2D-Poisson equation in Cartesian coordinate system is imposed to be satisfied by each of RGB color components with homogeneous open boundary conditions. In order to determine the color component distribution in the image part of interest we calculate the distribution of color component source densities utilizing Green functions. The inverse problem for color source densities

An Orientation-Independent Imaging Technique for the Classification of Blood Cells

This study presents an orientation independent imaging technique for the classification and recognition of blood cells with relevant applications to related problems in cytometry and medical diagnosis. The proposed method integrates three important aspects towards its practical implementation: 1. The use of the principal component (PC) transform to reorient in an optimal fashion the image data and to make of the feature matching an orientation independent process; 2. The establishment of similarity measures to quantify the matching process of the shape of the blood cell populations with any chosen degree of certainty; and 3. The application of the recognition and classification processes once all the similarity measurements are gathered. An extension of this two-dimensional (2-D) method to a three-dimensional (3-D) base is proposed. Results of this technique using real-world image data of blood cell populations are given. It is appropriate to note that although the images used here are real-world samples of blood cell populations, other samples containing different biological specimens could have been used just as well.

A general scheme for automatic generation of search heuristics from specification dependencies

The paper presents and evaluates the power of a new scheme that generates search heuristics mechanically for problems expressed using a set of functions or relations over a finite set of variables. The heuristics are extracted from a parameterized approximation scheme called Mini-Bucket elimination that allows controlled trade-off between computation and accuracy. The heuristics are used to guide Branch-and-Bound and Best-First search. Their performance is compared on two optimization tasks: the Max-CSP task defined on deterministic databases and the Most Probable Explanation task defined on probabilistic databases. Benchmarks were random data sets as well as applications to coding and medical diagnosis problems. Our results demonstrate that the heuristics generated are effective for both search schemes, permitting controlled trade-off between preprocessing (for heuristic generation) and search.

A novel large-memory neural network as an aid in medical diagnosis applications.

This paper describes the application of a large memory storage and retrieval (LAMSTAR) neural network to medical diagnosis and medical information retrieval problems. The network is based on Minsky's knowledge-lines (k-lines) theory of memory storage and retrieval in the central nervous system. It employs arrays of self-organized map modules, such that the k-lines are implemented via link weights (address correlation) that are being updated by learning. The network also employs features of forgetting and of interpolation and extrapolation, thus being able to handle incomplete data sets. It can deal equally well with exact and fuzzy information, thus being specifically applicable to medical diagnosis where the diagnosis is based on exact data, fuzzy patient interview information, patient history, observed images, and test records. Furthermore, the network can be operated in closed loop with Internet search engines to intelligently use data from the Internet in a higher hierarchy of learning. All of the above features are shown to make the LAMSTAR network suitable for medical diagnosis problems that concern large data sets of many categories that are often incomplete and fuzzy. Applications of the network to three specific medical diagnosis problems are described: two from nephrology and one related to an emergency-room drug identification problem. It is shown that the LAMSTAR network is hundreds and thousands times faster in its training than back-propagation-based networks when used for the same problem and with exactly the same information.