Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Classification Algorithms”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 595 records · Page 33Linked to original sources
PubMed2004

Characterization of digital medical images utilizing support vector machines.

BACKGROUND: In this paper we discuss an efficient methodology for the image analysis and characterization of digital images containing skin lesions using Support Vector Machines and present the results of a preliminary study. METHODS: The methodology is based on the support vector machines algorithm for data classification and it has been applied to the problem of the recognition of malignant melanoma versus dysplastic naevus. Border and colour based features were extracted from digital images of skin lesions acquired under reproducible conditions, using basic image processing techniques. Two alternative classification methods, the statistical discriminant analysis and the application of neural networks were also applied to the same problem and the results are compared. RESULTS: The SVM (Support Vector Machines) algorithm performed quite well achieving 94.1% correct classification, which is better than the performance of the other two classification methodologies. The method of discriminant analysis classified correctly 88% of cases (71% of Malignant Melanoma and 100% of Dysplastic Naevi), while the neural networks performed approximately the same. CONCLUSION: The use of a computer-based system, like the one described in this paper, is intended to avoid human subjectivity and to perform specific tasks according to a number of criteria. However the presence of an expert dermatologist is considered necessary for the overall visual assessment of the skin lesion and the final diagnosis.

Algorithms↗
PubMed1992

EDMUS, a European database for multiple sclerosis.

EDMUS is a minimal descriptive record developed for research purposes to document clinical and laboratory data in patients with multiple sclerosis (MS). It has been designed by a committee of the European Concerted Action for MS, organised under the auspices of the Commission of the European Communities. The software is user-friendly and fast, with a minimal set of obligatory data. Priority has been given to analytical data and the system is capable of automatically generating data, such as diagnosis classification, using appropriate algorithms. This procedure saves time, ensures a uniform approach to individual cases and allows automatic updating of the classification whenever additional information becomes available. It is also compatible with future developments and requirements since new algorithms can be entered in the programme when necessary. This system is flexible and may be adapted to the users needs. It is run on Apple and IBM-PC personal microcomputers. Great care has been taken to preserve confidentiality of the data. It is anticipated that this "common" language will enable the collection of appropriate cases for specific purposes, including population-based studies of MS and will be particularly useful in projects where the collaboration of several centres is needed to recruit a critical number of patients.

Database Management Systems↗
PubMed2003

Diagnosis of Ovarian Cancer Using Decision Tree Classification of Mass Spectral Data.

Recent reports from our laboratory and others support the SELDI ProteinChip technology as a potential clinical diagnostic tool when combined with $n$ -dimensional analyses algorithms. The objective of this study was to determine if the commercially available classification algorithm biomarker patterns software (BPS), which is based on a classification and regression tree (CART), would be effective in discriminating ovarian cancer from benign diseases and healthy controls. Serum protein mass spectrum profiles from 139 patients with either ovarian cancer, benign pelvic diseases, or healthy women were analyzed using the BPS software. A decision tree, using five protein peaks resulted in an accuracy of 81.5% in the cross-validation analysis and 80%in a blinded set of samples in differentiating the ovarian cancer from the control groups. The potential, advantages, and drawbacks of the BPS system as a bioinformatic tool for the analysis of the SELDI high-dimensional proteomic data are discussed.

Journal Article↗
PubMed2004

PLS dimension reduction for classification with microarray data.

Partial Least Squares (PLS) dimension reduction is known to give good prediction accuracy in the context of classification with high-dimensional microarray data. In this paper, the classification procedure consisting of PLS dimension reduction and linear discriminant analysis on the new components is compared with some of the best state-of-the-art classification methods. Moreover, a boosting algorithm is applied to this classification method. In addition, a simple procedure to choose the number of PLS components is suggested. The connection between PLS dimension reduction and gene selection is examined and a property of the first PLS component for binary classification is proved. In addition, we show how PLS can be used for data visualization using real data. The whole study is based on 9 real microarray cancer data sets.

Journal Article↗
PubMed2003

New algorithms for multi-class cancer diagnosis using tumor gene expression signatures.

MOTIVATION: The increasing use of DNA microarray-based tumor gene expression profiles for cancer diagnosis requires mathematical methods with high accuracy for solving clustering, feature selection and classification problems of gene expression data. RESULTS: New algorithms are developed for solving clustering, feature selection and classification problems of gene expression data. The clustering algorithm is based on optimization techniques and allows the calculation of clusters step-by-step. This approach allows us to find as many clusters as a data set contains with respect to some tolerance. Feature selection is crucial for a gene expression database. Our feature selection algorithm is based on calculating overlaps of different genes. The database used, contains over 16 000 genes and this number is considerably reduced by feature selection. We propose a classification algorithm where each tissue sample is considered as the center of a cluster which is a ball. The results of numerical experiments confirm that the classification algorithm in combination with the feature selection algorithm perform slightly better than the published results for multi-class classifiers based on support vector machines for this data set. AVAILABILITY: Available on request from the authors.

Algorithms↗
PubMed1984

Clinical classification of regional cerebral blood flow (RCBF) by partitioning.

An algorithm is proposed to classify the regional cerebral blood flow (RCBF) of two groups of subjects. A 32-tuple training vector is defined corresponding to 32 detectors used to measure 133Xe washout following inhalation. For any index of 133Xe washout, each detector is associated with two cumulative distributions (cds) each corresponding to a population. The 32 index values at which the differences between cds are maximum are defined as partition values. All index values are then compared to their partitions and are designated binary values of 1 or 0 for being above or below the partitions. A representative sum of the binary numbers (0 to 16) indicates the number of detectors in each hemisphere which exceed their respective threshold. In the example, a normal group of subjects (n = 40) is compared to an abnormal group (n = 82). The abnormal group was identified independently of RCBF by clinical testing as having Alzheimer's disease, a subcategory of dementing diseases. The classification algorithm defined a training vector to which the two populations were compared. The normal subjects had higher representative scores than the abnormals with a tight clustering of these scores. Although some abnormals scored well, the great majority had representative scores well below 12 for each cerebral hemisphere. The training vector can be used to classify new studies or can be updated by new studies until no significant changes result. At this point, the new tracing vector is used as a reference set of partition values.

Alzheimer Disease↗
PubMed2005

Unsupervised clustering in mRNA expression profiles.

The development of microarray technologies gives scientists the ability to examine, discover and monitor the mRNA transcript levels of thousands of genes in a single experiment. Nonetheless, the tremendous amount of data that can be obtained from microarray studies presents a challenge for data analysis. The most commonly used computational approach for analyzing microarray data is cluster analysis, since the number of genes is usually very high compared to the number of samples. In this paper, we investigate the application of the recently proposed k-windows clustering algorithm on gene expression microarray data. This algorithm apart from identifying the clusters present in a data set also calculates their number and thus requires no special knowledge about the data. To improve the quality of the clustering, we employ various dimension reduction techniques and propose a hybrid one. The results obtained by the application of the algorithm exhibit high classification success.

Algorithms↗
PubMed2003

Comparison of multiexcitation fluorescence and diffuse reflectance spectroscopy for the diagnosis of breast cancer (March 2003).

Nonmalignant (n = 36) and malignant (n = 20) tissue samples were obtained from breast cancer and breast reduction surgeries. These tissues were characterized using multiple excitation wavelength fluorescence spectroscopy and diffuse reflectance spectroscopy in the ultraviolet-visible wavelength range, immediately after excision. Spectra were then analyzed using principal component analysis (PCA) as a data reduction technique. PCA was performed on each fluorescence spectrum, as well as on the diffuse reflectance spectrum individually, to establish a set of principal components for each spectrum. A Wilcoxon rank-sum test was used to determine which principal components show statistically significant differences between malignant and nonmalignant tissues. Finally, a support vector machine (SVM) algorithm was utilized to classify the samples based on the diagnostically useful principal components. Cross-validation of this nonparametric algorithm was carried out to determine its classification accuracy in an unbiased manner. Multiexcitation fluorescence spectroscopy was successful in discriminating malignant and nonmalignant tissues, with a sensitivity and specificity of 70% and 92%, respectively. The sensitivity (30%) and specificity (78%) of diffuse reflectance spectroscopy alone was significantly lower. Combining fluorescence and diffuse reflectance spectra did not improve the classification accuracy of an algorithm based on fluorescence spectra alone. The fluorescence excitation-emission wavelengths identified as being diagnostic from the PCA-SVM algorithm suggest that the important fluorophores for breast cancer diagnosis are most likely tryptophan, NAD(P)H and flavoproteins.

Algorithms↗
PubMed1997

Calculation of LDL-cholesterol by using apolipoprotein B for classification of nonchylomicronemic dyslipemia.

In this paper we propose a calculation of LDL-cholesterol (LDL-C) not affected by hypertriglyceridemia by using lipid quantities directly measured in total serum. We also propose an algorithm for the classification of nonchylomicronemic dyslipemias. Plasma apolipoproteins (apo) A-I, B, total cholesterol (TC), triglycerides (TG), and cholesterol of lipoproteins were measured in a group of 38 normolipemic and 120 dyslipemic patients (42 phenotype IIa, 38 IIb, and 40 IV) classified according to TG and LDL-C values. Discriminant analysis was applied to obtain the best classification with the lowest number of quantities directly measured from total serum (TC, TG, and apo B), and multiple regression analysis was performed to find an equation to calculate LDL-C from these quantities. Apo B seems to be a useful discriminator between normolipemic and phenotype IIa patients, by using a cutoff value of 1.35 g/L obtained by ROC curve analysis. The proposed algorithm, based on lipid quantities measured by easily automated methods, is shown to be a good alternative for the classification of nonhyperchylomicronemic dyslipemia. LDL-C calculated from TC, TG, and apo B proved a better estimate of true LDL-C than the estimate obtained with Friedewald's formula.

Algorithms↗
PubMedDate not supplied

[Specific features of QRS-complex identification algorithms for real-time ECG systems].

The paper reviews the existing methods for identifying QRS complexes. An attempt is made to make a well-defined classification of available algorithms in an approach to QRS detection. Emphasis is laid on the consideration of specific requirements for such algorithms by computer-aided real-time ECG systems. A task of choice of the most suitable method is formulated. An algorithm based on the well-known principles of frequency-time detection is proposed as an alternative solution of this task. The algorithm makes it possible to single out QRS complexes from real-time ECG and to effectively make a digital signal processing by available optimized libraries. The method initially used in the Matlab package has been integrated within the laboratory computerized ECG system.

Algorithms↗
PubMed2006

An association rule mining-based methodology for automated detection of ischemic ECG beats.

Currently, an automated methodology based on association rules is presented for the detection of ischemic beats in long duration electrocardiographic (ECG) recordings. The proposed approach consists of three stages. 1) Preprocessing: Noise is removed and all the necessary ECG features are extracted. 2) Discretization: The continuous valued features are transformed to categorical. 3) CLASSIFICATION: An association rule extraction algorithm is utilized and a rule-based classification model is created. According to the proposed methodology, electrocardiogram (ECG) features extracted from the ST segment and the T-wave, as well as the patient's age, were used as inputs. The output was the classification of the beat as ischemic or not. Various algorithms were tested both for discretization and for classification using association rules. To evaluate the methodology, a cardiac beat dataset was constructed using several recordings of the European Society of Cardiology ST-T database. The obtained sensitivity (Se) and specificity (Sp) was 87% and 93%, respectively. The proposed methodology combines high accuracy with the ability to provide interpretation for the decisions made, since it is based on a set of association rules.

Arrhythmias, Cardiac↗
PubMed2006

[Classification method of deciduous-conifer mixed forest in jilin province based on GIS-TM remote sensing image].

To improve the accuracy of automatic classification and identification of TM remote sensing images in forest area, an expert system for automatically classifying and identifying deciduous-conifer mixed forest was built up, based on the GIS technique, quantitative analysis on the internal relations between geographic factors such as DEM and slope aspect and environment factors like soil type, and qualitative analysis on the spectrum information and preclassification information of sensing images, aimed to build a classification knowledge system. Taking the TM remote sensing image of Wangqing Forest Bureau in Jilin Province as an example, the study showed that this expert system could obviously reduce the influence of mixed pixel and terrain shadow. The classification precision of this system was increased by 14.22%, compared with that of Iterative Self-Organizing Data Analysis Techniques Algorithm (ISODATA) unsupervised classification, and the Kappa index was 0.7556, which could help to classify needle, deciduous and mixed forests. Introducing GIS data into the expert system could also solve the problem that TM remote sensing image could not do, due to the loss of correct spectrum value in cloudy and shady area.

China↗
PubMed2003

Ultrasonic liver tissues classification by fractal feature vector based on M-band wavelet transform.

This paper describes the feasibility of selecting fractal feature vector based on M-band wavelet transform to classify ultrasonic liver images-normal liver, cirrhosis, and hepatoma. The proposed feature extraction algorithm is based on the spatial-frequency decomposition and fractal geometry. Various classification algorithms based on respective texture measurements and filter banks are presented and tested. Classifications for the three sets of ultrasonic liver images reveal that the fractal feature vector based on M-band wavelet transform is trustworthy. A hierarchical classifier, which is based on the proposed feature extraction algorithm is at least 96.7% accurate in the distinction between normal and abnormal liver images and is at least 93.6% accurate in the distinction between cirrhosis and hepatoma liver images. Additionally, the criterion for feature selection is specified and employed for performance comparisons herein.

Algorithms↗
PubMed1994

Automatic reduction of NMR spectroscopic data for statistical and pattern recognition classification of samples.

A general method of automatically reducing NMR spectra to provide numerical descriptors of samples has been developed and investigated. These descriptors can be used as input to pattern recognition or multivariate algorithms for sample classification. The methods have been tested using 600 MHz one-dimensional 1H NMR spectra of biofluids which are complex mixtures. The approach is, in principle, applicable to multidimensional and heteronuclear NMR spectra and to other types of liquid samples such as oils and foodstuffs as well as to situations such as 1H or 31P NMR in vivo and solid state NMR in drug formulation analysis. The method relies upon apportioning the information in the spectra to individual contiguous segments and allowing specified regions of the spectra to be omitted. Three approaches, based on the number of peaks, the summed peak heights and the summed peak areas respectively in each segment, have been tested. The effect of segment width and overlap and the effects of manipulation of the NMR spectra have been evaluated in terms of the classification of the samples using principal components analysis. A simple method of generating NMR based spectral descriptors for object classification is thus proposed.

Algorithms↗
PubMedDate not supplied

Clinical study for classification of benign, dysplastic, and malignant oral lesions using autofluorescence spectroscopy.

Autofluorescence spectroscopy shows promising results for detection and staging of oral (pre-)malignancies. To improve staging reliability, we develop and compare algorithms for lesion classification. Furthermore, we examine the potential for detecting invisible tissue alterations. Autofluorescence spectra are recorded at six excitation wavelengths from 172 benign, dysplastic, and cancerous lesions and from 97 healthy volunteers. We apply principal components analysis (PCA), artificial neural networks, and red/green intensity ratio's to separate benign from (pre-)malignant lesions, using four normalization techniques. To assess the potential for detecting invisible tissue alterations, we compare PC scores of healthy mucosa and surroundings/contralateral positions of lesions. The spectra show large variations in shape and intensity within each lesion group. Intensities and PC score distributions demonstrate large overlap between benign and (pre-)malignant lesions. The receiver-operator characteristic areas under the curve (ROC-AUCs) for distinguishing cancerous from healthy tissue are excellent (0.90 to 0.97). However, the ROC-AUCs are too low for classification of benign versus (pre-)malignant mucosa for all methods (0.50 to 0.70). Some statistically significant differences between surrounding/contralateral tissues of benign and healthy tissue and of (pre-)malignant lesions are observed. We can successfully separate healthy mucosa from cancers (ROC-AUC>0.9). However, autofluorescence spectroscopy is not able to distinguish benign from visible (pre-)malignant lesions using our methods (ROC-AUC<0.65). The observed significant differences between healthy tissue and surroundings/contralateral positions of lesions might be useful for invisible tissue alteration detection.

Adolescent↗
PubMed2003

Identifying exposures of in vitro fertilization from drug reimbursement files: a case study from Finland.

OBJECTIVE: This article describes an innovative method to identify infertility interventions from drug reimbursement data, which did not contain diagnoses. METHODS: An algorithm of usual infertility care steps was designed and information on drug prescriptions were retrieved from the Drug Reimbursement Register and linked to a register covering examinations and interventions in private health care. The data were compared to in vitro fertilization (IVF) statistics and the Birth Register. RESULTS: Despite the novelty of the idea, the complexity of the pharmacological details, the use of administrative registers not commonly used for research, and the involvement of two institutions, the identification of the exposed cohorts went well. An estimated 16 work-weeks were used. The numbers of started IVF-cycles with fresh embryos were similar to those in statistics, but our data had more transfers of frozen embryos. The linkage to the Birth Register gave further support that our algorithm worked well. Classification into different IVF-classes was not accurate. CONCLUSION: Even though diagnoses were not recorded in the Finnish drug reimbursement data, the algorithm approach allowed exposure identification.

Algorithms↗
PubMedDate not supplied

Assessing different classification methods for virtual screening.

How well do different classification methods perform in selecting the ligands of a protein target out of large compound collections not used to train the model? Support vector machines, random forest, artificial neural networks, k-nearest-neighbor classification with genetic-algorithm-optimized feature selection, trend vectors, naïve Bayesian classification, and decision tree were used to divide databases into molecules predicted to be active and those predicted to be inactive. Training and predicted activities were treated as binary. The database was generated for the ligands of five different biological targets which have been the object of intense drug discovery efforts: HIV-reverse transcriptase, COX2, dihydrofolate reductase, estrogen receptor, and thrombin. We report significant differences in the performance of the methods independent of the biological target and compound class. Different methods can have different applications; some provide particularly high enrichment, others are strong in retrieving the maximum number of actives. We also show that these methods do surprisingly well in predicting recently published ligands of a target on the basis of initial leads and that a combination of the results of different methods in certain cases can improve results compared to the most consistent method.

Algorithms↗