Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “CLASSIFICATION”

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 1,405 records · Page 78Linked to original sources
PubMed2006

Interobserver and intraobserver agreement of Lenke and King classifications for idiopathic scoliosis and the influence of level of professional training.

STUDY DESIGN: This is a blinded study of radiographs by observers with different levels of professional training. OBJECTIVES: To determine whether the level of professional training on nonmeasured and premeasured radiographs would affect reliability of Lenke's and King's classifications for adolescent idiopathic scoliosis. SUMMARY OF BACKGROUND DATA: Both classification systems have been studied for their reliability, mainly by observers with a high level of experience in orthopedics and scoliosis surgery using premeasured radiographs. METHODS: Examination of radiographs of 60 operative cases of adolescent idiopathic scoliosis was performed. On 5 occasions, 3 observers with a completely different degree of professional training measured and classified preoperative radiographs according to Lenke's or King's criteria. The results were determined by calculating the interobserver and intraobserver agreement and were quantified using two-rater and multirater kappa statistics. RESULTS: The Lenke and King classifications demonstrated poor to fair interobserver and good intraobserver agreement on nonmeasured radiographs. Both classifications demonstrated good to excellent interobserver agreement on premeasured radiographs. CONCLUSIONS: The results confirm that both classifications have a good reliability. On nonmeasured radiographs, the degree of professional training and the measurement process seem to influence the outcome. On premeasured radiographs, the interobserver agreement does not seem to be influenced by the level of professional training.

Adolescent↗
PubMed2006

Prognostic variables and prognostic groups for malignant melanoma. The information from Cox and Classification And Regression Trees analysis: an Italian population-based study.

The common way to analyse the prognostic role of selected variables in cutaneous melanoma patients is by means of Cox proportional hazard model. The prognostic effect of the simultaneous presence of more than one independent variable in the same patient is, however, difficult to establish. This hampers the possibility of tailoring a survival expectance for a selected patient as well as to communicate it to the patient himself/herself. The objectives of the study were to compare information on cutaneous melanoma prognosis from multivariate Cox proportional hazard model and from Classification And Regression Trees analysis. Classification And Regression Trees analysis is an automatic method that splits data by means of a binary recursive process creating a 'tree' of groups with different profiles according to the analysed outcome, for example, the risk of death. This approach automatically produces data that is easily interpreted by clinicians. A total of 1403 invasive cutaneous melanoma patients, 1110 from the Tuscan Cancer Registry and 293 from the Reggio Emilia Cancer Registry, Italy, were included. Cases were incident during 1996-2001 and followed up at the end of 2003. Cox proportional hazard model and Classification And Regression Trees analysis were applied to the following variables: age, sex, Breslow thickness, Clark level, registry, subsite and morphologic type. The Classification And Regression Trees analysis identified 10 categories with statistically different survival; this results were summarized into six classes of different risks based on Breslow thickness, age and sex. The best prognostic group (5-year observed survival, 98.1%) included those subjected with Breslow less than 0.94 mm and age 19-44 years. The same thickness but an older age (50-69 years) was associated with a statistically significant different prognosis (5-year observed survival, 92.8%). The Cox proportional hazard model found sex, age, Breslow thickness, Clark and morphologic type to have a significant independent prognostic value. In conclusion, compared with the conventional approach based on Cox hazard model, Classification And Regression Trees analysis produces data closer to the clinical need of defining the prognostic profile of a specific patient. This may help the clinician both in the communication of risk and in the follow-up strategy.

Adult↗
PubMed2005

Current TNM classification of renal cell carcinoma evaluated: revising stage T3a.

PURPOSE: : Recent studies of rare cases of pT3a renal cell carcinoma extending directly into the adrenal gland showed worse survival than in other pT3a cases and recategorization as stage pT4 was suggested. We assessed the prognostic validity of a stage pT3a diagnosis based on perirenal fat infiltration. MATERIALS AND METHODS: : The records of 1,794 patients with renal cell carcinoma who underwent surgical resection between 1975 and 2000 at our institution were analyzed retrospectively. Focusing on pT3a tumors, as defined by perirenal fat infiltration, numerous clinical and histopathological parameters were investigated by univariate and multivariate statistical methods with cancer specific survival as the primary end point. RESULTS: : We identified 237 of 1,794 patients with perirenal fat infiltration, classified as having pT3a disease. In patients with pT3a tumors tumor size was a significant parameter predicting survival. The most significant cutoff value for tumor size in pT3a disease was 7 cm. Patients with distant metastasis had a worse prognosis independent of T classification. Therefore, to assess the prognostic value of the current T classification in regard to T3a tumors we excluded patients with tumor stage cM+ for further subgroup analysis. Survival comparison of pT1 pNall, cM0 (744 of 1,794 cases) and pT3a pNall, cM0 7 cm or less (100 of 237) as well as pT2 pNall, cM0 (265 of 1,794) and pT3a pNall, cM0 greater than 7 cm (93 of 237) yielded similar results. After splitting pT3a into a modified T1/T2 classification a significant difference in 5-year survival analysis for a modified T1/T2 stage was found (pT1 plus pT3a less than 7 cm 90% vs pT2 plus pT3a greater than 7 cm 73%, p <0.001). Subsequently multivariate analysis in all 1,794 patients showed that modified T stage was an independent significant predictor of cancer specific survival. CONCLUSIONS: : We suggest revising the current pT3a classification based on perirenal fat infiltration but rendering a modified pT1/pT2 classification, which resolves pT3a cases without the loss of prognostic validity. Perirenal fat infiltration should not be used to assign T category. Tumors directly infiltrating the adrenal gland should be reclassified as T4.

Carcinoma, Renal Cell↗
PubMed2005

Intra- and interobserver variation in the use of the Vienna classification of Crohn's disease.

BACKGROUND: Crohn's disease is a heterogeneous disease, and several classification systems have been developed to classify the patients in more homogeneous groups. Our aim was to assess the intra- and interobserver variation when classifying patients according to the widely used Vifenna classification. METHODS: Ten randomly selected Crohn's disease cases were presented to 11 Danish gastroenterologists with a special interest in inflammatory bowel diseases. Clinical details, together with endoscopic, radiologic, and pathologic reports, were presented to the participants as a PowerPoint slide show, sent by e-mail with a data collection form. The experts were asked to classify the cases according to the Vienna classification and to evaluate intraobserver variation; the participants classified the patients 3 times. The strength of agreement was calculated using kappa statistics. RESULTS: Classification of the patients according to age gave a kappa value of 1.00. The intraobserver kappa value was good, with an average kappa value of 0.75 (range, 0.42-0.86) for location and 0.77 (range, 0.53-1.00) for behavior. The mean overall interobserver kappa value was 0.64 (range, 0.12-1.00), which improved slightly between the first and third rounds. When classifying according to location and behavior, most patients were classified in 2 or 3 different ways, and in no patients was there full agreement among the observers for both location and behavior. CONCLUSIONS: In this study, we found an overall good interobserver agreement when using the Vienna classification, although when looking at individual cases, there was some disagreement.

Crohn Disease↗
PubMed2005

A basic classification and a comprehensive examination of pediatric myeloproliferative syndromes.

Myeloproliferative syndromes (MPSs) are clonal stem cell disorders resulting in excessive proliferation of one or more cell lineages. Since MPSs in children occur much less commonly than adults, one can argue that the biology and the categories of the various pediatric MPSs seem to be different from adults. Furthermore, confusion exists between pediatric MPS and other overlapping conditions, such as myelodysplastic syndrome. The authors' objectives were to develop a classification system with a list of disorders relevant to children and to characterize pediatric cases of MPS that were devised according to this classification. Based on the predominant proliferating cell lineage, the authors established a classification system for childhood MPS. Primary MPS was classified into granulocytic proliferation--chronic myelogenous leukemia (CML); monocytic--juvenile myelomonocytic leukemia (JMML); megakaryocytic--essential thrombocythemia (ET), familial thrombocytosis, transient myeloproliferative disorder of Down syndrome (TMD); erythrocytic--polycythemia vera, familial erythrocytosis; fibroblastic--idiopathic myelofibrosis (IMF); eosinophilic--idiopathic hypereosinophilic syndrome (IHES); and mast cells--mastocytosis. Secondary MPS was classified as non-clonal proliferation (eg, infections, drugs, toxins, autoimmune, non-hematologic neoplasm, and trauma), and these were excluded from the study. Next, the classification system was applied to the patient population at the authors' institution. One hundred two cases with primary MPS were identified between 1970 and 2001. Patients were evaluated for clinical manifestations, blood and bone marrow parameters, cytogenetics, and survival following different treatment modalities. Significant proportions of cases of childhood MPS (60%) were unique to the pediatric population and not seen in adults. The most common disorders were JMML (n = 31), TMD of Down syndrome (n = 30), and CML (n = 30); the other disorders were rare: four cases of ET, two of IMF, two of IHES, two of mastocytosis, and one primary erythrocytosis. In contrast to adults, MPS in children is more frequently treated with hematopoietic stem cell transplantation (HSCT), the only available curative option for most of these diseases. HSCT was particularly successful in the more recent cases due to more advanced techniques for HSCT. The authors found that all the cases could be easily classified. MPS in children is different from adult-type MPS in terms of biology, categories, classification, and prognosis.

Adolescent↗
PubMed2006

Recent advances in the pathology and classification of ovarian sex cord-stromal tumors.

In recent years, our knowledge of ovarian sex cord-stromal tumors has increased, and their classification has evolved. In this review, recent advances in the classification and pathology of ovarian sex cord-stromal tumors are discussed, and the controversy regarding the classification of sex cord tumor with annular tubules is addressed. The current classification is built on those of the past, and future classifications should improve on what is now in place incorporating new knowledge from more sophisticated clinicopathologic studies and advanced molecular techniques. This review emphasizes articles written in the 21st century as well as those that have significantly advanced our knowledge of sex cord-stromal tumors in past decades. The tumors in this group occur over a wide age range and are often unilateral. In difficult cases, immunocytochemistry provides improved diagnostic accuracy. The most useful immunohistochemical marker for their identification is alpha-inhibin, which is positive in most neoplasms in the sex cord-stromal group. The article concludes with a section discussing the pathogenesis of sex cord-stromal tumors.

Biomarkers, Tumor↗
PubMed2004

Classification of surgical complications: a new proposal with evaluation in a cohort of 6336 patients and results of a survey.

OBJECTIVE: Although quality assessment is gaining increasing attention, there is still no consensus on how to define and grade postoperative complications. This shortcoming hampers comparison of outcome data among different centers and therapies and over time. PATIENTS AND METHODS: A classification of complications published by one of the authors in 1992 was critically re-evaluated and modified to increase its accuracy and its acceptability in the surgical community. Modifications mainly focused on the manner of reporting life-threatening and permanently disabling complications. The new grading system still mostly relies on the therapy used to treat the complication. The classification was tested in a cohort of 6336 patients who underwent elective general surgery at our institution. The reproducibility and personal judgment of the classification were evaluated through an international survey with 2 questionnaires sent to 10 surgical centers worldwide. RESULTS: The new ranking system significantly correlated with complexity of surgery (P < 0.0001) as well as with the length of the hospital stay (P < 0.0001). A total of 144 surgeons from 10 different centers around the world and at different levels of training returned the survey. Ninety percent of the case presentations were correctly graded. The classification was considered to be simple (92% of the respondents), reproducible (91%), logical (92%), useful (90%), and comprehensive (89%). The answers of both questionnaires were not dependent on the origin of the reply and the level of training of the surgeons. CONCLUSIONS: The new complication classification appears reliable and may represent a compelling tool for quality assessment in surgery in all parts of the world.

Analysis of Variance↗
PubMedDate not supplied

The lateral pillar classification of Legg-Calvé-Perthes disease.

To determine the predictive value of a new classification system for Legg-Perthes, 93 hips in 86 patients with radiographic follow-up to maturity were reviewed. All patients were treated by bracing at the Texas Scottish Rite Hospital from 1970 to 1980. Hips were classified during the fragmentation stage of disease into three groups based on radiolucency in the lateral pillar of the femoral head. Final radiographs were reviewed at skeletal maturity, and the outcome was determined according to the Stulberg classification. Group A had a uniformly good outcome (100% Stulberg I and II results); Group B had a good outcome in patients who were less than 9 years at onset (92% Stulberg I and II, 8% Stulberg III results), but a less favorable outcome in patients who were greater than 9 years at onset (30% Stulberg II, 50% Stulberg III, and 20% Stulberg IV results). In Group C, the majority of femoral heads became aspherical in both age groups (29% Stulberg II, 52% Stulberg III, and 19% Stulberg IV results). The group C hips also had a longer duration of fragmentation and reossification stages. Members of the Legg-Perthes study group agreed 78% of the time when applying the classification to unknown radiographs. The classification group was a stronger determinant than age of onset in predicting final outcome. This classification system is easy to apply during the active stage of the disease and has a high correlation in predicting the amount of flattening of the femoral head at skeletal maturity.(ABSTRACT TRUNCATED AT 250 WORDS)

Age Factors↗
PubMed1990

New headache classification: implications for neuroscience nurses.

In June of 1988, the Headache Classification Committee of the International Headache Society published new Classification and Diagnostic Criteria for Headache, Cranial Neuralgias, and Facial Pain. A new standard classification for migraine and tension-type headache was established. An assessment form facilitating headache classification by the neuroscience nurse according to the IHS criteria has been developed. The ability to quantify variables included in the new classification offers the opportunity for productive research on headache by neuroscience nurses.

Headache↗
PubMed2001

Implications of alternative classifications and horizontal gene transfer for bacterial taxonomy.

Following the publication of the Approved Lists, there has been a tendency to regard all subsequent revisions of classification as providing improved nomenclature, to be accepted without question. This takes no account of the fact that such revisions may be based on one of three alternative concepts, phenetic, phylogenetic or polyphasic classification, sometimes leading to different, valid, but incompatible nomenclature, or that some investigations are based only on subsets of relevant taxa and on limited data, leading to incomplete and sometimes confusing revisions of nomenclature. The polyphasic approach to classification has widespread support, although there appears to be a tendency to allow comparative sequence analyses of 16S rDNA to determine classification contrary to the indications of other data. In some cases, classification is based solely on 16S rDNA data. Examples are considered. Consideration is given to the criteria by which taxa are circumscribed, particularly at the level of genus and species. It is suggested that there is a need for reconciliation of the criteria by which taxa at these levels are circumscribed. Recent studies demonstrating the widespread occurrence of horizontal gene transfer suggest that there is a need for caution in monophyletic interpretations, especially when these are based on the analysis of single sequences.

Bacteria↗
PubMed1975

A maximal predictive classification of Klebsielleae and of the yeasts.

The concepts of the numerical method of maximal predictive classification are illustrated with classifications of 13 species of enterobacteria and of 434 species of yeast. The method seeks to classify into a specified number of classes (k) such that more correct statements can be made about the constituent members than with any other classification. The best choice of k relates to the separation of the classes as measured by the average number of correct statements made for an individual assigned to a class to which it does not belong. The maximal predictive classifications are compared with previous classifications of the two groups, which seem to be poor predictively (in terms of the characters considered in this study). The results suggest that taxonomists may be more concerned with maximizing class separation rather than with prediction, but many more groups of organisms would need similar study before this view could be held with confidence.

Aerobiosis↗
PubMed2000

CART classification of human 5' UTR sequences.

A nonredundant database of 2312 full-length human 5'-untranslated regions (UTRs) was carefully prepared using state-of-the-art experimental and computational technologies. A comprehensive computational analysis of this data was conducted for characterizing the 5' UTR features. Classification and regression tree (CART) analysis was used to classify the data into three distinct classes. Class I consists of mRNAs that are believed to be poorly translated with long 5' UTRs filled with potential inhibitory features. Class II consists of terminal oligopyrimidine tract (TOP) mRNAs that are regulated in a growth-dependent manner, and class III consists of mRNAs with favorable 5' UTR features that may help efficient translation. The most accurate tree we found has 92.5% classification accuracy as estimated by cross validation. The classification model included the presence of TOP, a secondary structure, 5' UTR length, and the presence of upstream AUGs (uAUGs) as the most relevant variables. The present classification and characterization of the 5' UTRs provide precious information for better understanding the translational regulation of human mRNAs. Furthermore, this database and classification can help people build better computational models for predicting the 5'-terminal exon and separating the 5' UTR from the coding region.

5' Untranslated Regions↗
PubMed1992

Probabilistic inference-based classification applied to myoelectric signal decomposition.

A new probabilistic inference based technique (IBC) for the classification of motor unit action potentials (MUAP's) is presented. This new technique discovers statistically significant relationships in the data and uses these relationships to generate classification rules. The technique was applied to the classification of MUAP's extracted from simulated myoelectric signals. Its performance was compared to that of classical template matching algorithms (TBC) applied to the same data. Using 32 time samples as features to represent the MUAP's it was found that the IBC based technique performed significantly better (p less than 0.005) than the TBC algorithms (83.0 +/- 2.6% versus 78.1 +/- 2.8% peak correct classification performance). As the size of the training set was reduced or as increasing numbers of random classification errors were introduced into the training data, the performance of the IBC and TBC techniques declined similarly. IBC performance remained superior until very small training sets (less than 30 MUAP's per motor unit) or training sets with large numbers of errors (greater than 50%) were used. Because the probabilistic inference technique can utilize nominal data it has the potential to use declarative problem domain knowledge which conceivably could improve its performance.

Action Potentials↗
PubMed1989

Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty.

Laser angioplasty, or the ablation of atherosclerotic plaque using laser energy, has tremendous potential to expand the scope of nonsurgical treatment of obstructive vascular disease. Clinical laser angioplasty, however, has been hindered by an unacceptable risk of vessel perforation. Laser-induced fluorescence spectroscopy can discriminate atherosclerotic from normal artery and may therefore be capable of guiding selective plaque ablation. To assess the feasibility of utilizing spectral information to discriminate arterial tissue type, several classification algorithms were developed and evaluated. Arterial fluorescence spectra from 350 to 700 nm were obtained from 100 human aortic specimens. Seven spectral classification algorithms were developed with the following techniques: multivariate linear regression, stepwise multivariate linear regression, principal components analysis, decision plane analysis, Bayes decision theory, principal peak ratio, and spectral width. The classification ability of each algorithm was evaluated by its application to the training set and to a validation set containing 82 additional spectra. All seven spectral classification algorithms prospectively classified atherosclerotic and normal aorta with an accuracy greater than 80 percent (range: 82-96 percent). Laser angioplasty systems incorporating spectral classification algorithms may therefore be capable of detection and selective ablation of atherosclerotic plaque.

Algorithms↗
PubMed1997

Wavelet image extension for analysis and classification of infarcted myocardial tissue.

Some computer applications for tissue characterization in medicine and biology, such as analysis of the myocardium or cancer recognition, operate with tissue samples taken from very small areas of interest. In order to perform texture characterization in such an application, only a few texture operators can be employed: the operators should be insensitive to noise and image distortion and yet be reliable in order to estimate texture quality from the small number of image points available. In order to describe the quality of infarcted myocardial tissue, we propose a new wavelet-based approach for analysis and classification of texture samples with small dimensions. The main idea of this method is to decompose the given image with a filter bank derived from an orthonormal wavelet basis and to form an image approximation with higher resolution. Texture energy measures calculated at each output of the filter bank as well as energies of synthesized images are used as texture features in a classification procedure. We propose an unsupervised classification technique based on a modified statistical t-test. The method is tested with clinical data, and the classification results obtained are very promising. The performance of the new method is compared with the performance of several other transform-based methods. The new algorithm has advantages in classification of small and noisy input samples, and it represents a step toward structural analysis of weak textures.

Algorithms↗
PubMed1997

Measures of acutance and shape for classification of breast tumors.

Most benign breast tumors possess well-defined, sharp boundaries that delineate them from surrounding tissues, as opposed to malignant tumors. Computer techniques proposed to date for tumor analysis have concentrated on shape factors of tumor regions and texture measures. While shape measures based on contours of tumor regions can indicate differences in shape complexities between circumscribed and spiculated tumors, they are not designed to characterize the density variations across the boundary of a tumor. In this paper we propose a region-based measure of image edge profile acutance which characterizes the transition in density of a region of interest (ROI) along normals to the ROI at every boundary pixel. We investigate the potential of acutance in quantifying the sharpness of the boundaries of tumors, and propose its application to discriminate between benign and malignant mammographic tumors. In addition, we study the complementary use of various shape factors based upon the shape of the ROI, such as compactness, Fourier descriptors, moments, and chord-length statistics to distinguish between circumscribed and spiculated tumors. Thirty-nine images from the Mammographic Image Analysis Society (MIAS) database and an additional set of 15 local cases were selected for this study. The cases included 16 circumscribed benign, seven circumscribed malignant, 12 spiculated benign, and 19 spiculated malignant lesions. All diagnoses were proven by pathologic examinations of resected tissue. The contours of the lesions were first marked by an expert radiologist using X-Paint and X-Windows on a SUN-SPARCstation 2 Workstation. For computation of acutance, the ROI boundaries were iteratively approximated using a split/merge and end-point adjustment technique to obtain the best-fitting polygonal approximation. The jackknife method using the Mahalanobis distance measure in the BMDP (Biomedical Programs) package was used for classification of the lesions using acutance and the shape factors as features in various combinations. Acutance alone resulted in a benign/malignant classification accuracy of 95% the MIAS cases. Compactness alone gave a circumscribed/spiculated classification rate of 92.3% with the MIAS cases. Acutance in combination with a moment-based shape measure and a Fourier descriptor-based measure gave four-group classification rate of 95% with the MIAS cases. The results indicate the importance of including lesion edge definition with shape information for classification of tumors, and that the proposed measure of acutance fills this need.

Breast Neoplasms↗
PubMed2000

Gradient and texture analysis for the classification of mammographic masses.

Computer-aided classification of benign and malignant masses on mammograms is attempted in this study by computing gradient-based and texture-based features. Features computed based on gray-level co-occurrence matrices (GCMs) are used to evaluate the effectiveness of textural information possessed by mass regions in comparison with the textural information present in mass margins. A method involving polygonal modeling of boundaries is proposed for the extraction of a ribbon of pixels across mass margins. Two gradient-based features are developed to estimate the sharpness of mass boundaries in the ribbons of pixels extracted from their margins. A total of 54 images (28 benign and 26 malignant) containing 39 images from the Mammographic Image Analysis Society (MIAS) database and 15 images from a local database are analyzed. The best benign versus malignant classification of 82.1%, with an area (Az) of 0.85 under the receiver operating characteristics (ROC) curve, was obtained with the images from the MIAS database by using GCM-based texture features computed from mass margins. The classification method used is based on posterior probabilities computed from Mahalanobis distances. The corresponding accuracy using jack-knife classification was observed to be 74.4%, with Az = 0.67. Gradient-based features achieved Az = 0.6 on the MIAS database and Az = 0.76 on the combined database. The corresponding values obtained using jack-knife classification were observed to be 0.52 and 0.73 for the MIAS and combined databases, respectively.

Breast Neoplasms↗
PubMed2004

Massively parallel classification of single-trial EEG signals using a min-max modular neural network.

This paper presents a method for classifying single-trial electroencephalogram (EEG) signals using min-max modular neural networks implemented in a massively parallel way. The method has three main steps. First, a large-scale, complex EEG classification problem is simply divided into a reasonable number of two-class subproblems, as small as needed. Second, the two-class subproblems are simply learned by individual smaller network modules in parallel. Finally, all the individual trained network modules are integrated into a hierarchical, parallel, and modular classifier according to two module combination laws. To demonstrate the effectiveness of the method, we perform simulations on fifteen different four-class EEG classification tasks, each of which consists of 1491 training and 636 test data. These EEG classification tasks were created using a set of non-averaged, single-trial hippocampal EEG signals recorded from rats; the features of the EEG signals are extracted using wavelet transform techniques. The experimental results indicate that the proposed method has several attractive features. 1) The method is appreciably faster than the existing approach that is based on conventional multilayer perceptrons. 2) Complete learning of complex EEG classification problems can be easily realized, and better generalization performance can be achieved. 3) The method scales up to large-scale, complex EEG classification problems.

Algorithms↗