Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “classifier”

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 253 records · Page 14Linked to original sources
PubMed1999

Development of a system to classify 3D structural character of RNA.

We are developing a computational system to extract structural character of RNA. We made a program that classifies conformers by recognizing the hydrogen bonding patterns. The program was applied to a set of 279 conformers and they were classified into about 40 groups. The system is expected to be useful for searching structural motifs of RNA and classifying large number of generated conformers in structural modeling process.

Base Pairing↗
PubMed1999

Comparison of methods for classifying Hispanic ethnicity in a population-based cancer registry.

The accuracy of ethnic classification can substantially affect ethnic-specific cancer statistics. In the Greater Bay Area Cancer Registry, which is part of the Surveillance, Epidemiology, and End Results (SEER) Program and of the statewide California Cancer Registry, Hispanic ethnicity is determined by medical record review and by matching to surname lists. This study compared these classification methods with self-report. Ethnic self-identification was obtained by surveying 1,154 area residents aged 20-89 years who were diagnosed with cancer in 1990 and were reported to the registry as being Hispanic or White non-Hispanic. Predictive value positive, sensitivity, and relative bias were used to assess the accuracy of Hispanic classification by medical record and surname. Among those persons classified as Hispanic by either or both of these sources, only two-thirds agreed (predictive value positive = 66%), and many self-identified Hispanics were classified incorrectly (sensitivity = 68%). Classification based on either medical record or surname alone had a lower sensitivity (59% and 61%, respectively) but a higher predictive value positive (77% and 70%, respectively). Ethnic classification by medical record alone resulted in an underestimate of Hispanic cancer cases and incidence rates. Bias was reduced when medical records and surnames were used together to classify cancer cases as Hispanic.

California↗
PubMed2000

A simple method for classifying genes and a bootstrap test for classifications.

A new simple method for classifying genes is proposed based on Klastorin's method. This method classifies genes into monophyletic groups which are made distinct from each other by evolutionary changes. The method is applicable as long as the phylogenetic tree of genes is obtained. There is a fast algorithm for obtaining the classification. A bootstrap test of a classification is also presented. As an example, we classified opsin genes. The classification obtained by this method is the same as the previous classification based on the function of opsins.

Algorithms↗
PubMed2006

Enhanced Glaucoma Staging System (GSS 2) for classifying functional damage in glaucoma.

PURPOSE: To introduce a new method, derived from the Glaucoma Staging System (GSS), for classifying glaucomatous visual field defects. PATIENTS AND METHODS: Four sample groups composed respectively of 471 (sample #1), 128 (sample #2), 185 (sample #3), and 131 (sample #4) patients with either ocular hypertension or chronic glaucoma were considered. The GSS 2 uses both the MD and CPSD/CLV or PSD/LV perimetric indices to classify visual field defect in 6 stages and in 3 types (generalized, localized, and mixed). The formulas were determined using sample #1. A new borderline stage was created, on the basis of sample #2. The relationship between the PSD/LV and CPSD/CLV values was studied on sample #3 to verify the possibility of using the uncorrected indices instead of the CPSD/CLV. The relationship with other classification methods was studied on sample #4. RESULTS: The GSS 2 showed a strong level of association with the AGIS and the Hodapp-Parrish-Anderson methods in staging defect severity. A good correlation was also found with a classification based on the Bebie curve. CONCLUSIONS: The GSS 2 was able to correctly classify both damage severity and perimetric defect type in the sample studied, using either the corrected or uncorrected visual field indices. It is a quick and easy method, and its formulas can be introduced in any software.

Adult↗
PubMed2005

A nomogram to classify men with lower urinary tract symptoms using urine flow and noninvasive measurement of bladder pressure.

PURPOSE: Bladder pressure during voiding can be estimated by a noninvasive technique using controlled inflation of a penile cuff. This test provides a valid and reliable estimate of isovolumetric bladder pressure but to our knowledge the role of the test for the routine clinical treatment of patients with lower urinary tract symptoms (LUTS) has yet to be demonstrated. As a first step, we evaluated a proposed nomogram for the diagnosis of bladder outlet obstruction in men with LUTS using noninvasive measurements of pressure and flow. MATERIALS AND METHODS: Using a combination of theoretical calculation and experimental data the existing International Continence Society pressure flow nomogram was modified to allow noninvasive measurement of isovolumetric bladder pressure in place of detrusor pressure at maximum urine flow. Accuracy of the nomogram for classifying obstruction was then tested in a group of 144 men with LUTS who underwent an invasive and a noninvasive pressure flow study. RESULTS: The modified nomogram identified men with obstruction with 68% positive predictive value and 78% negative predictive value. Predictive accuracy could be improved by adding an additional criterion of obstruction, that is maximum urine flow less than 10 ml second, whereby an identifiable 69% of all cases could be classified as obstructed (88% positive predictive value) or not obstructed (86% negative predictive value). In the remaining 31% of patients invasive pressure flow studies would provide additional information, although some results would remain equivocal. CONCLUSIONS: The proposed nomogram combined with the additional flow rate criterion can classify more than two-thirds of cases without recourse to invasive pressure flow studies. We must now evaluate the usefulness of this classification for the treatment of men with LUTS.

Aged↗
PubMed2003

The prognostic significance of a system for classifying mechanical injuries of the eye (globe) in open-globe injuries.

PURPOSE: The aim of this study was to determine the prognostic significance of a previously published system for classifying mechanical injuries of the eye (globe) in open-globe injuries. METHODS: The medical records of 150 patients with open-globe injuries identified from an established institutional database were retrospectively reviewed to classify all injuries at presentation by the four specific variables of the classification system: type of injury, defined by the mechanism of injury; grade of injury, defined by visual acuity in the injured eye at initial examination; pupil, defined as the presence or absence of a relative afferent pupillary defect in the injured eye; and zone of injury, defined by the location of the eye-wall opening. Final visual outcomes for these injuries were also recorded. Logistic regression models were used to analyze the data and to determine whether relationships existed between the specific classification variables and final visual acuity in the injured eyes. RESULTS: All four classification variables were significant predictors of visual outcome. When adjusted for the other variables, grade and pupil were the most significant predictors of final visual acuity. CONCLUSION: This system for classifying mechanical injuries of the eye appears to be prognostic for visual outcomes in open-globe injuries. In particular, the measurement of visual acuity and testing for a relative afferent pupillary defect at the initial examination should be performed in all injured eyes because of their relative prognostic significance.

Adult↗
PubMed1995

Hepatitis C virus variants from Thailand classifiable into five novel genotypes in the sixth (6b), seventh (7c, 7d) and ninth (9b, 9c) major genetic groups.

Nine (10%) out of 90 hepatitis C virus (HCV) isolates from hepatitis patients and commercial blood donors in Thailand were not classifiable into any of genotypes I/1a, II/1b, III/2a, IV/2b, V/3a or VI/3b by RT-PCR with type-specific primers deduced from the HCV core gene. These isolates were sequenced over a 1.6 kb stretch of the 5'-terminal sequence and 1.1 kb of the 3'-terminal sequence covering 30% of the entire genome. Based on two-by-two comparison and phylogenetic analyses of the nine Thailand isolates among themselves and with known full or partial sequences of previously reported HCV isolates, the Thailand isolates were classified into five genotypes not reported previously, viz. 6b, 7c, 7d, 9b and 9c. Along with HCV isolates reported already, they make at least nine major genetic groups of HCV which further break down into at least 28 genotypes with sequence similarity in the E1 gene (576 bp) of < or = 80%. As many more HCV isolates of distinct genotypes are expected to be found throughout the world, it will become increasingly difficult to classify them by comparison of any partial sequences of the genome. Complete sequence data will be required for the full characterization and classification of HCV genotypes.

Amino Acid Sequence↗
PubMed2001

Capturing whole-genome characteristics in short sequences using a naïve Bayesian classifier.

Bacterial genomes have diverged during evolution, resulting in clearcut differences in their nucleotide composition, such as their GC content. The analysis of complete sequences of bacterial genomes also reveals the presence of nonrandom sequence variation, manifest in the frequency profile of specific short oligonucleotides. These frequency profiles constitute highly specific genomic signatures. Based on these differences in oligonucleotide frequency between bacterial genomes, we investigated the possibility of predicting the genome of origin for a specific genomic sequence. To this end, we developed a naïve Bayesian classifier and systematically analyzed 28 eubacterial and archaeal genomes. We found that sequences as short as 400 bases could be correctly classified with an accuracy of 85%. We then applied the classifier to the identification of horizontal gene transfer events in whole-genome sequences and demonstrated the validity of our approach by correctly predicting the transfer of both the superoxide dismutase (sodC) and the bioC gene from Haemophilus influenzae to Neisseria meningitis, correctly identifying both the donor and recipient species. We believe that this classification methodology could be a valuable tool in biodiversity studies.

Archaea↗
PubMed1995

Brain maturation estimation using neural classifier.

Quantitative electroencephalographic (EEG) signal analysis has revealed itself as an important diagnostic tool in the last few years. Through the use of signal processing techniques, new quantitative representations of EEG data are obtained. To automate the diagnosis, a problem of supervised classification must be solved on these. Artificial Neural Networks provide an alternative to more traditional classifier systems for this task. The objective of this paper is to perform a comparison between several classifiers in a particular problem, the brain maturation prediction. The data preprocessing/feature extraction process and the methodology for making the comparison are described. Performance of the methods is evaluated in terms of estimated percentage of correctly classified subjects.

Adolescent↗
PubMed2003

A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier.

In this paper, a computer-aided diagnostic (CAD) system for the classification of hepatic lesions from computed tomography (CT) images is presented. Regions of interest (ROIs) taken from nonenhanced CT images of normal liver, hepatic cysts, hemangiomas, and hepatocellular carcinomas have been used as input to the system. The proposed system consists of two modules: the feature extraction and the classification modules. The feature extraction module calculates the average gray level and 48 texture characteristics, which are derived from the spatial gray-level co-occurrence matrices, obtained from the ROIs. The classifier module consists of three sequentially placed feed-forward neural networks (NNs). The first NN classifies into normal or pathological liver regions. The pathological liver regions are characterized by the second NN as cyst or "other disease." The third NN classifies "other disease" into hemangioma or hepatocellular carcinoma. Three feature selection techniques have been applied to each individual NN: the sequential forward selection, the sequential floating forward selection, and a genetic algorithm for feature selection. The comparative study of the above dimensionality reduction methods shows that genetic algorithms result in lower dimension feature vectors and improved classification performance.

Algorithms↗
PubMed2006

A support vector machines classifier to assess the severity of idiopathic scoliosis from surface topography.

A support vector machines (SVM) classifier was used to assess the severity of idiopathic scoliosis (IS) based on surface topographic images of human backs. Scoliosis is a condition that involves abnormal lateral curvature and rotation of the spine that usually causes noticeable trunk deformities. Based on the hypothesis that combining surface topography and clinical data using a SVM would produce better assessment results, we conducted a study using a dataset of 111 IS patients. Twelve surface and clinical indicators were obtained for each patient. The result of testing on the dataset showed that the system achieved 69-85% accuracy in testing. It outperformed a linear discriminant function classifier and a decision tree classifier on the dataset.

Adolescent↗
PubMed2004

A Bayesian approach to joint feature selection and classifier design.

This paper adopts a Bayesian approach to simultaneously learn both an optimal nonlinear classifier and a subset of predictor variables (or features) that are most relevant to the classification task. The approach uses heavy-tailed priors to promote sparsity in the utilization of both basis functions and features; these priors act as regularizers for the likelihood function that rewards good classification on the training data. We derive an expectation-maximization (EM) algorithm to efficiently compute a maximum a posteriori (MAP) point estimate of the various parameters. The algorithm is an extension of recent state-of-the-art sparse Bayesian classifiers, which in turn can be seen as Bayesian counterparts of support vector machines. Experimental comparisons using kernel classifiers demonstrate both parsimonious feature selection and excellent classification accuracy on a range of synthetic and benchmark data sets.

Algorithms↗
PubMedDate not supplied

Prognosis of breast cancer patients with familial history classified according to their menopausal status.

Breast cancer patients were classified in the family history positive (FHP) group when they had at least one second-degree relative who was a breast cancer patient. The results of a comparative study with patients classified in the family history negative (FHN) group showed the prognosis of the FHP group was significantly better than that of the FHN group. However, when those patients were classified according to their menopausal status at onset, there were no significant differences in survival rates between the FHP and FHN groups with onset before menopause, whereas the survival rate of the FHP group was significantly higher than that of the FHN group with onset after menopause. The same results were found when the FHP group was subgrouped into the FHP group with first-degree relatives and the FHP group with second-degree relatives. Further investigations on background factors revealed that the patients with onset before menopause showed no significant differences between the FHP and FHN groups in age at surgery, diameter of the tumor, histologic grade, the number of metastatic lymph nodes, body weight, estrogen receptor (ER) status, and the values of CEA and CA15-3 before surgery. On the other hand, the FHP patients with onset after menopause showed significantly lower numbers of metastatic lymph nodes and trends showing higher ER values and lower CA15-3-values. Therefore the favorable prognosis in the FHP group seems to be attributable to the higher survival rate of the FHP patients with onset after menopause.

Adult↗
PubMed2005

Applying ICF in nursing practice: classifying elements of nursing diagnoses.

AIM: This study explores the relevance of the International Classification of Functioning, Disability and Health (ICF) to nursing diagnoses. BACKGROUND: As a multidisciplinary classification of human functioning, the ICF (previously known as ICIDH-2) is potentially relevant to nursing care. However, nurses have rarely used the classification during the 23 years of its existence. METHOD: In part 1 of the study, 51 nursing diagnoses from anonymous patients were deliberately selected for diversity from an existing database. The 427 diagnostic elements from these diagnoses (problem statements, aetiological factors, signs and symptoms) were classified, using the ICF, by a panel of six nurses. In part 2 of the study, the panel classified 223 elements from 30 diagnoses of patients they had actually cared for. RESULTS: Nearly all diagnostic elements could be classified, most often in the sub-dimensions of body functions and activities. Agreement on appropriate ICF components was 61% for anonymous patients and 75% for familiar patients. Agreement at the more detailed 3-digit level of the classification was 42% for anonymous and 60% for familiar patients. CONCLUSION: The ICF has relevance to nursing care. As a general classification, it was not designed by nurses or specifically for nursing care. This can explain some difficulties in using the classification that were identified in this study, as well as the rather low levels of agreement. To resolve these issues and to further improve the classification, nurses should further explore the use of the ICF and participate in future revision processes.

Academic Medical Centers↗
PubMed2005

Causes of death classified by risk and condition, New Zealand 1997.

OBJECTIVE: To classify causes of death in New Zealand by risk factor (in addition to condition) as a planning tool for health promotion. METHOD: Deaths occurring in New Zealand in 1997 were classified by 20 prevalent risk factors using a combination of categorical attribution (rule-based) and counterfactual modelling (population-attributable risk-based) approaches. RESULTS: Approximately 30% of deaths were attributed to the joint effect of dietary factors. Tobacco consumption was responsible for 18% of deaths and insufficient physical activity for almost 10%. Less important behavioural risk factors included alcohol consumption (3%), illicit drug use (0.5%) and unsafe sex (0.5%). Among biological risk factors, higher than optimal total blood cholesterol, systolic blood pressure and body mass index accounted for 17%, 15% and 12% of deaths respectively. Deprivation contributed to 17% of deaths, and adverse in-hospital events to 6%. Among environmental exposures, microbes accounted for 6.5% of deaths, air pollution 3.5% and occupational diseases and injuries 0.5%. Among injury hazards, risk factors related to road traffic were responsible for 2% of deaths, while violence accounted for 2.5% of deaths, mostly through suicide. Cross-classifying deaths by both condition and risk factor, 90% of ischaemic heart disease and 80% of stroke, but only 30% of cancer deaths, could be attributed to specific risk factors. CONCLUSIONS: This is the first comprehensive ranking of causes of death at the level of risk factors available for New Zealand and should prove useful as a planning tool, especially for disease prevention and health promotion.

Attitude to Health↗
PubMed1993

Classifying perinatal death: experience from a regional survey.

OBJECTIVE: To examine problems encountered in classifying perinatal death using the systems proposed by Hey et al. (1986) and Cole et al. (1986). SUBJECTS: 451 deaths from a regional perinatal mortality survey of which 293 had a post mortem examination. METHODS: Documents from each death were reviewed by four assessors, one from each discipline, selected randomly from a pool of obstetricians, paediatricians, general practitioners and midwives. Each assessor classified the cause of death blind to the others. The degree of agreement between assessors was calculated for the full and shortened obstetric and fetal-neonatal classifications using the kappa statistic for inter-rater agreement. RESULTS: The kappa statistic, which is a measure of the proportion of agreement above chance, gave a value of 0.55 for the full obstetric classification and 0.58 for the full fetal and neonatal classification when all four assessors made an assignment. An assignment was omitted in 6.2%, but the kappa value of zero for these omissions suggested that this was a nonsystematic result due to random protocol violations. The grouped (shortened) classifications generated a higher kappa value of 0.62 for the nine point obstetric system and 0.67 for the six point fetal and neonatal (New Wigglesworth) system. Post mortem had little effect on agreement. The best agreement levels observed were for congenital anomaly. CONCLUSION: This survey highlighted the complexity of the 22 and 24 point classifications, the uneven distribution of deaths within their categories, and the variable levels of agreement between professionals classifying deaths, thus questioning the validity of individual maternity units of health districts generating local data in this degree of detail for comparative purposes in regional and national statistics. Grouping the original categories led to greater agreement particularly for the New Wigglesworth classification. The role of post mortems in clarifying the cause of fetal and neonatal death needs further investigation.

Cause of Death↗
PubMed1998

Using the Unger system to classify 386 long bone fractures in dogs.

A system already described by Unger and others was used to classify long bone fractures in dogs. The present paper reports experiences using the fracture classification system regarding its ease of use and the ability to analyse the data generated. Three hundred and eighty-six canine long bone fractures were classified from radiographs. Results were assessed by reviewing the medical records or by sending questionnaires to referring veterinarians. There were a few inconsistencies, particularly in classifying proximal ulnar fractures, but the system was easy to use and data retrieval was readily accomplished. Data from the system were used to compare the results of repairs of diaphyseal fractures of the radius/ulna, femur and tibia/fibula. A chi square analysis was used to determine significant differences between the outcome scores of the three fracture types. Fractures of the femoral diaphysis had a statistically poorer outcome than did diaphyseal fractures of the radius/ulna or tibia/fibula.

Animals↗
PubMedDate not supplied

Classifying structural alterations of the cytoskeleton by spectrum enhancement and descriptor fusion.

A classifier capable of ranking structural alterations of the cytoskeleton is developed. Images of cytoskeletal microtubules obtained from the epifluorescence microscopy of primary culture rat hepatocytes are analyzed. Morphological descriptors are extracted by contour and mass fractal analysis, direct methods, and spectrum enhancement. All methods are designed and tuned to make the extracted morphological descriptors insensitive to absolute fluorescence intensities. Spectrum enhancement is a nonlinear filter that involves spatial differentiation of the gray-scale image followed by conversion of power spectral density to the logarithmic scale and averaging over arcs in the reciprocal domain. Enhanced spectra exhibit local maxima that correspond to the structured microtubule bundles of a normal cytoskeleton. Descriptor fusion for classification is achieved by means of multivariate analysis. The classifier is trained by image sets representing normal ("negative control") microtubules and those altered by exposure to a fungicide at the highest dose of the experiment design. Some sensitivity and validation tests, including discriminant functions analysis, are applied to the classifier. The latter is applied to recognize images of microtubules not used in the training stage and comes from treatments at lower concentrations and shorter times. As a result, structural alterations are ranked and structural recovery after treatment is quantified. The method has potential use in quantitative, morphology-based tests on the cytoskeleton treated either by anticancer drugs or by cytotoxic agents.

Algorithms↗