Hybridization of fuzzy GBML approaches for pattern classification problems.
Explore the source record for details and available documents.
Algorithms↗
SEARCH · PubMed Health
Results for “Classification Algorithms”
Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
The role of serum erythropoietin levels in diagnosis and classification of erythrocytosis/polycythemia.
Explore the source record for details and available documents.
Algorithms↗
Classifiability-based omnivariate decision trees.
Top-down induction of decision trees is a simple and powerful method of pattern classification. In a decision tree, each node partitions the available patterns into two or more sets. New nodes are created to handle each of the resulting partitions and the process continues. A node is considered terminal if it satisfies some stopping criteria (for example, purity, i.e., all patterns at the node are from a single class). Decision trees may be univariate, linear multivariate, or nonlinear multivariate depending on whether a single attribute, a linear function of all the attributes, or a nonlinear function of all the attributes is used for the partitioning at each node of the decision tree. Though nonlinear multivariate decision trees are the most powerful, they are more susceptible to the risks of overfitting. In this paper, we propose to perform model selection at each decision node to build omnivariate decision trees. The model selection is done using a novel classifiability measure that captures the possible sources of misclassification with relative ease and is able to accurately reflect the complexity of the subproblem at each node. The proposed approach is fast and does not suffer from as high a computational burden as that incurred by typical model selection algorithms. Empirical results over 26 data sets indicate that our approach is faster and achieves better classification accuracy compared to statistical model select algorithms.
Algorithms↗
Classification of EEG signals using neural network and logistic regression.
Epileptic seizures are manifestations of epilepsy. Careful analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders. The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. As EEG signals are non-stationary, the conventional method of frequency analysis is not highly successful in diagnostic classification. This paper deals with a novel method of analysis of EEG signals using wavelet transform and classification using artificial neural network (ANN) and logistic regression (LR). Wavelet transform is particularly effective for representing various aspects of non-stationary signals such as trends, discontinuities and repeated patterns where other signal processing approaches fail or are not as effective. Through wavelet decomposition of the EEG records, transient features are accurately captured and localized in both time and frequency context. In epileptic seizure classification we used lifting-based discrete wavelet transform (LBDWT) as a preprocessing method to increase the computational speed. The proposed algorithm reduces the computational load of those algorithms that were based on classical wavelet transform (CWT). In this study, we introduce two fundamentally different approaches for designing classification models (classifiers) the traditional statistical method based on logistic regression and the emerging computationally powerful techniques based on ANN. Logistic regression as well as multilayer perceptron neural network (MLPNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. In these methods we used LBDWT coefficients of EEG signals as an input to classification system with two discrete outputs: epileptic seizure or non-epileptic seizure. By identifying features in the signal we want to provide an automatic system that will support a physician in the diagnosing process. By applying LBDWT in connection with MLPNN, we obtained novel and reliable classifier architecture. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The MLPNN based classifier outperformed the LR based counterpart. Within the same group, the MLPNN based classifier was more accurate than the LR based classifier.
Adult↗
Classification of large array surface myoelectric potentials from subjects with and without low back pain.
An algorithm was developed and tested for differentiating between the spatial distribution of large arrays of surface electromyographic (LASE) data from subjects with and without low back pain (LBP). The surface EMG data from 62 channels were collected from the low back of 161 healthy and 44 acute (less than 6-weeks) LBP subjects in three minimum stress postural positions including standing, 20 degrees of trunk flexion (at hip joint) and standing with arms extended forward holding a 1.36kg (3lb) weight in each hand. These data were statistically analyzed and the spatial distribution of the root mean square (RMS) values was used in a multivariate quadratic discriminant model to reclassify the healthy and acute LBP subjects. The most predictive results were obtained from the 'flexion' group of experiments and correctly reclassified 95.5% (42/44) of the acute LBP subjects and 99.4% (160/161) of the healthy subjects. The success rate of this reclassification based on surface distribution of myoelectric potentials was found to be better than the reported patient classifications based on a smaller set of electrode pairs using fewer subjects [Peach JP, McGill SM, Classification of low back pain with use of spectral electromyogram parameters. Spine 23(10):1998;1117-23; Roy SH, De Luca CJ, Emley M, Oddsson LI, Buijs RJ, Levins JA, Newcombe DS, Jabre JF. Classification of back muscle impairment based on the surface electromyographic signal. J Rehabil Res Dev 34(4):1997;405-14 [review]]. The results indicated the potential of the model for clinical patient classification.
Action Potentials↗
Recovering intrinsic images from a single image.
Interpreting real-world images requires the ability distinguish the different characteristics of the scene that lead to its final appearance. Two of the most important of these characteristics are the shading and reflectance of each point in the scene. We present an algorithm that uses multiple cues to recover shading and reflectance intrinsic images from a single image. Using both color information and a classifier trained to recognize gray-scale patterns, given the lighting direction, each image derivative is classified as being caused by shading or a change in the surface's reflectance. The classifiers gather local evidence about the surface's form and color, which is then propagated using the Generalized Belief Propagation algorithm. The propagation step disambiguates areas of the image where the correct classification is not clear from local evidence. We use real-world images to demonstrate results and show how each component of the system affects the results.
Algorithms↗
Algorithm-directed triage of pediatric patients. A prospective study.
An Army corpsman used physician-written triage algorithms to rate the urgency of the chief complaints of 2,000 pediatric outpatients. His ratings agreed with subsequent ratings by physicians in 84% of cases. The corpsman assigned a higher care urgency classification in 15% of cases and a lower classification in only 1.2% of cases. No danger to patients resulted from the algorithm-directed screening. Use of a "nonprofessional" as a triage agent spares the pediatrician, pediatric nurse practitioner, and nurse for providing health care. With increasing use of acute care facilities by patients without appointments, physician-written algorithms allow triage agents who lack formal medical training to determine safely the need for care of patients.
Allied Health Personnel↗
Performance gain in computer-assisted detection schemes by averaging scores generated from artificial neural networks with adaptive filtering.
The authors investigated a new method to optimize artificial neural networks (ANNs) with adaptive filtering used in computer-assisted detection schemes in digitized mammograms and to assess performance changes when averaging classification scores from three sets of optimized schemes. Two independent training and testing image databases involving 978 and 830 digitized mammograms, respectively, were used in this study. In the training data set, initial filtering and subtraction resulted in the identification of 592 mass regions and 3790 suspicious, but actually negative regions. These regions (including both true-positive and negative regions) were segmented into three subsets three times based on the calculation of the values of three features as segmentation indices. The indices were "mass" size multiplied by their digital value contrast, conspicuity, and circularity. Nine ANN-based classifiers were separately optimized using a genetic algorithm for each subset of regions. Each region was assigned three classification scores after applying the three adaptive ANNs. The performance gain of the CAD scheme after averaging the three scores for each suspicious region was tested using an independent data set and a ROC methodology. The experimental results showed that the areas under ROC curves (Az) for the testing database using three sets of optimized ANNs individually were 0.84+/-0.01, 0.83+/-0.01, and 0.84+/-0.01, respectively. The between-index correlations of three A values were 0.013, -0.007, and 0.086. Similar to averaging diagnostic ratings from independent observers, by averaging three ANN-generated scores for each testing region, the performance of the CAD scheme was significantly improved (p<0.001) with Az value of 0.95+/-0.01.
Algorithms↗
Combined malignancy associated change and contextual analysis for computerized classification of cervical cell monolayers.
Previous efforts to automate cervical cell analysis have focused on algorithms that use measurements of high resolution images of individual cells for 'rare event' detection of abnormal cells, sometimes in combination with cluster analysis of low resolution images. A new methodology was developed in which intermediate cell markers (indicating malignancy associated change) and contextual analysis of slide architecture were performed on the same digital images at 0.33 mu pixel resolution. A total of one hundred and forty-six cases that were either negative or at least high grade squamous intraepithelial lesions (HGSIL) were prepared as monolayers, and about 20 fields per slide were analyzed. Features most important for intermediate cell marker analysis were those that measured the variation in nuclear texture measurements across the slide as well as densitometric features. The most discriminatory contextual features were those that measured the variation of the arrangement of cells within a cluster across the slide. Linear discriminants were calculated using the most important features from both types of analysis; they provided smear classification accuracies of 71-86%.
Carcinoma↗
Computerized quantification of structures within ovarian cysts using ultrasound images.
Ovarian cysts are a common type of ovarian mass. The morphology of cysts, as it appears in ultrasound images, is currently used for classification of ovarian pathologies. However, this classification process is based on human interpretation of the sonographic image. In this article, a semiautomatic algorithm for the quantification of ovarian cysts is presented. This algorithm categorizes the structures within a cyst and extracts their quantitative geometric properties (width, characteristic diameter). To assess the validity of the technique, its performance was compared to human classification and manual measurements made by an expert. The results show a good match between automatic evaluations made by a computer and those of an experienced observer, indicating a potential for clinical use.
Algorithms↗
Feature subset selection by genetic algorithms and estimation of distribution algorithms. A case study in the survival of cirrhotic patients treated with TIPS.
The transjugular intrahepatic portosystemic shunt (TIPS) is an interventional treatment for cirrhotic patients with portal hypertension. In the light of our medical staff's experience, the consequences of TIPS are not homogeneous for all the patients and a subgroup dies in the first 6 months after TIPS placement. Actually, there is no risk indicator to identify this subgroup of patients before treatment. An investigation for predicting the survival of cirrhotic patients treated with TIPS is carried out using a clinical database with 107 cases and 77 attributes. Four supervised machine learning classifiers are applied to discriminate between both subgroups of patients. The application of several feature subset selection (FSS) techniques has significantly improved the predictive accuracy of these classifiers and considerably reduced the amount of attributes in the classification models. Among FSS techniques, FSS-TREE, a new randomized algorithm inspired on the new EDA (estimation of distribution algorithm) paradigm has obtained the best average accuracy results for each classifier.
Algorithms↗
Automatic detection of gait events: a case study using inductive learning techniques.
One of the problems which occurs in the development of a control system for functional electrical stimulation of the lower limbs is to detect accurately specific events within the gait cycle. We present a method for the classification of phases of the gait cycle using the artificial intelligence technique of inductive learning. Both the terminology of inductive learning and the algorithm used for the analyses are fully explained. Given a set of examples of sensor data from the gait events that are to be detected, the inductive learning algorithm is able to produce a decision tree (or set of rules) which classify the data using a minimum number of sensors. The nature of the redundancy of the sensor set is examined by progressively removing combinations of sensors and noting the effect on both the size of the decision trees produced and their classification accuracy on 'unseen' testing data. Since the algorithm is able to calculate which sensors are more important (informative), comparisons with the intuitive appreciation of sensor importance of five researchers in the fields were made, revealing that those sensors which appear intuitively most informative may, in fact, provide the least information. Comparison results with the standard statistical classification technique of linear discriminant analysis are also presented, showing the relative simplicity of the inductively derived rules together with their good classification accuracy. In addition to the control of FES, such techniques are also applicable to automatic gait analysis and the construction of expert systems for diagnosis of gait pathologies.
Algorithms↗
Spectroscopic diagnosis of cervical intraepithelial neoplasia (CIN) in vivo using laser-induced fluorescence spectra at multiple excitation wavelengths.
BACKGROUND AND OBJECTIVE: The diagnostic contribution of cervical tissue fluorescence spectra acquired in vivo at 380 and 460 nm excitation were analyzed using a general multivariate statistical algorithm. MATERIALS AND METHODS: The primary steps of the algorithm are to: (1) preprocess data to reduce interpatient and intrapatient variation of tissue spectra from the same diagnostic category, without a priori information, (2) dimensionally reduce the pre-processed spectral data using Principal Component Analysis, and (3) develop a probability based classification scheme based on logistic discrimination using the diagnostically useful principal components. The algorithm was tested on cervical tissue spectra acquired from 165 sites at 380 nm excitation and from 147 sites at 460 nm excitation. A retrospective and prospective estimate of the algorithm's performance was determined. RESULTS: At 460 nm excitation, (1) SILs can be differentiated from normal squamous tissues with an average sensitivity and specificity of 91% +/- 1.3 and 75.5% +/- 1, respectively; furthermore, (2) high grade SILs can be differentiated from low grade SILs with an average sensitivity and specificity of 80% +/- 4 and 76% +/- 5, respectively. In addition, using tissue spectra at 380 nm excitation, SILs can be differentiated from normal columnar epithelia and inflammation with an average sensitivity and specificity of 77% +/- 1 and 72% +/- 9, respectively. CONCLUSIONS: Fluorescence spectra at multiple excitation wavelengths are essential for the detection and differential diagnosis of SILs at colposcopy.
Algorithms↗
Identification of a new marker of hepatocellular carcinoma by serum protein profiling of patients with chronic liver diseases.
Surface-enhanced laser desorption ionization time-of-flight mass spectrometry (SELDI-TOF MS) is a proteomic technique that enables the profiling of proteins present in any biological material studied. We used this approach to identify new biomarkers of hepatocellular carcinoma (HCC) in the sera of patients with cirrhosis. Sera from 82 patients with cirrhosis, either without (n = 38) or with (n = 44) HCC, were analyzed by SELDI-TOF MS, and the results of the two groups were compared. The most efficient protein peaks leading to discrimination of patients with HCC were selected (receiver operative characteristic curves). The highest-scoring peak combination was established in a first group of serum samples (multinomial regression) and was tested in an independent group. The protein corresponding to the highest discrimination was purified and characterized further. The intensity of 30 protein peaks significantly differed between cirrhotic patients with and without HCC. An algorithm including the six highest-scoring peaks allowed correct classification (presence or absence of HCC) of 92.5% of patients in the test sample set and 90% in the validation sample set. The highest discriminating peak (8900 Da) was purified further and was characterized as the C-terminal part of the V10 fragment of vitronectin. An in vitro study suggested that the increase of the 8900-Da fragment in the serum of patients with HCC may proceed from the cleavage of native vitronectin with metalloproteases, a family of enzymes whose activity is enhanced in HCC. In conclusion, global protein profiling is an efficient approach that enabled us to identify a catalytic fragment ofvitronectin as a new serum marker of HCC in patients with chronic liver diseases.
Aged↗
Proteomic signature of human cancer cells.
We assessed proteomic profiles as biomarkers for monitoring cell phenotypes. Protein expression profiles were obtained by fluorescence two-dimensional difference gel electrophoresis (2-D-DIGE), in which quantitative ability is improved by labeling proteins with fluorescent dyes prior to electrophoresis. Integrated protein spot intensities were analyzed by a statistical approach. The proteomic data of two groups of cell lines: (1) adenocarcinoma (AC) cell lines derived from lung, pancreas and colon tissues and (2) lung cancer cell lines with different histological backgrounds, including AC, squamous cell carcinoma and small cell carcinoma, were assessed on the basis of prior biological information. Hierarchical clustering analysis and principal component analysis were used to divide the cell lines into subgroups on the basis of similarities between their protein expression profiles. The majority of cell lines were grouped according to their organ of origin or histological background. A machine-learning algorithm selected 32 protein spots that were responsible for the classification. The results indicate that proteomic data generated by 2-D-DIGE can provide a signature of essential cell phenotypes, suggesting that it might be possible to apply this technique to developing tumor markers that could identify the organ of origin of metastatic tumors and contribute to the differential diagnosis of lung cancer.
Cell Line, Tumor↗
Three-dimensional reconstruction of single particles in electron microscopy image processing.
Three-dimensional electron microscopy of single macromolecular assemblies has made large strides forward over the last decade. A large number of image processing techniques have been developed and many have found general distribution. For the proper usage of the wide range of available techniques, a clear concept of all processing steps is essential. This chapter provides step-by-step instruction for the three-dimensional reconstruction of an unknown macromolecule. Where possible, the limitations of the techniques are explained. The chapter attempts to be sufficiently general such so as not to adhere to a single image processing system. Described are alignment techniques for two and three dimensions, classification procedures, and the usage of three-dimensional reconstruction algorithms.
Algorithms↗
Quantitative structure-activity relationship modeling of polycyclic aromatic hydrocarbon mutagenicity by classification methods based on holistic theoretical molecular descriptors.
Various polycyclic aromatic hydrocarbons (PAHs), ubiquitous environmental pollutants, are recognized mutagens and carcinogens. A homogeneous set of mutagenicity data (TA98 and TA100,+S9) for 32 benzocyclopentaphenanthrenes/chrysenes was modeled by the quantitative structure-activity relationship classification methods k-nearest neighbor and classification and regression tree, using theoretical holistic molecular descriptors. Genetic algorithm provided the selection of the best subset of variables for modeling mutagenicity. The models were validated by leave-one-out and leave-50%-out approaches and have good performance, with sensitivity and specificity ranges of 90-100%. Mutagenicity assessment for these PAHs requires only a few theoretical descriptors of their molecular structure.
Environmental Pollutants↗
A novel information geometric approach to variable selection in MLP networks.
In this paper, a novel information geometric-based variable selection criterion for multi-layer perceptron networks is described. It is based on projections of the Riemannian manifold defined by a multi-layer perceptron network on submanifolds defined by multi-layer perceptron networks with reduced input dimension. We show how the divergence between models can be used as a criterion for an efficient search in the space of networks with different inputs. Then, we show how the posterior probabilities of the models can be evaluated to rank the projected models. Finally, we test our algorithm on synthetic and real data, and compare its performances with other methods reported in literature.
Algorithms↗