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 343 records · Page 19Linked to original sources
PubMed2006

Efficacy of MRI in classifying proximal focal femoral deficiency.

OBJECTIVE: To evaluate the efficacy of MRI in classifying PFFD and to compare MRI to radiographic classification of PFFD. DESIGN: Radiographic and MRI classification of the cases was performed utilizing the Amstutz classification system. PATIENTS: Retrospective evaluation of radiographs and MRI exams in nine hips of eight patients with proximal focal femoral deficiency was performed by two radiologists. RESULTS: The cases were classified by radiographs as Amstutz 1: n=3, Amstutz 3: n=3, Amstutz 4: n=1 and Amstutz 5: n=2. The classifications based on MRI were Amstutz 1: n=6, Amstutz 2: n=1, Amstutz 3: n=0, Amstutz 4: n=2 and Amstutz 5: n=0. Three hips demonstrated complete agreement. There were six discordant hips. In two of the discordant cases, follow-up radiographs of 6 months or greater intervals were available and helped to confirm MRI findings. Errors in radiographic evaluation consisted of overestimating the degree of deficiency. CONCLUSION: MRI is more accurate than radiographic evaluation for the classification of PFFD, particularly early on, prior to the ossification of cartilaginous components in the femurs. Since radiographic evaluation tends to overestimate the degree of deficiency, MRI is a more definitive modality for evaluation of PFFD.

Bone Diseases, Developmental↗
PubMed2006

Synergistic techniques for better understanding and classifying the environmental structure of landscapes.

The desire to capture natural regions in the landscape has been a goal of geographic and environmental classification and ecological land classification (ELC) for decades. Since the increased adoption of data-centric, multivariate, computational methods, the search for natural regions has become the search for the best classification that optimally trades off classification complexity for class homogeneity. In this study, three techniques are investigated for their ability to find the best classification of the physical environments of the Mt. Lofty Ranges in South Australia: AutoClass-C (a Bayesian classifier), a Kohonen Self-Organising Map neural network, and a k-means classifier with homogeneity analysis. AutoClass-C is specifically designed to find the classification that optimally trades off classification complexity for class homogeneity. However, AutoClass analysis was not found to be assumption-free because it was very sensitive to the user-specified level of relative error of input data. The AutoClass results suggest that there may be no way of finding the best classification without making critical assumptions as to the level of class heterogeneity acceptable in the classification when using continuous environmental data. Therefore, rather than relying on adjusting abstract parameters to arrive at a classification of suitable complexity, it is better to quantify and visualize the data structure and the relationship between classification complexity and class homogeneity. Individually and when integrated, the Self-Organizing Map and k-means classification with homogeneity analysis techniques also used in this study facilitate this and provide information upon which the decision of the scale of classification can be made. It is argued that instead of searching for the elusive classification of natural regions in the landscape, it is much better to understand and visualize the environmental structure of the landscape and to use this knowledge to select the best ELC at the required scale of analysis.

Bayes Theorem↗
PubMedDate not supplied

Comparison of contrast-enhanced ultrasound and computed tomography in classifying endoleaks after endovascular treatment of abdominal aorta aneurysms: preliminary experience.

The purpose of the study was to assess the effectiveness of contrast-enhanced ultrasonography (CEUS) in endoleak classification after endovascular treatment of an abdominal aortic aneurysm compared to computed tomography angiography (CTA). From May 2001 to April 2003, 10 patients with endoleaks already detected by CTA underwent CEUS with Sonovue to confirm the CTA classification or to reclassify the endoleak. In three conflicting cases, the patients were also studied with conventional angiography. CEUS confirmed the CTA classification in seven cases (type II endoleaks). Two CTA type III endoleaks were classified as type II using CEUS and one CTA type II endoleak was classified as type I by CEUS. Regarding the cases with discordant classification, conventional angiography confirmed the ultrasound classification. Additionally, CEUS documented the origin of type II endoleaks in all cases. After CEUS reclassification of endoleaks, a significant change in patient management occurred in three cases. CEUS allows a better attribution of the origin of the endoleak, as it shows the flow in real time. CEUS is more specific than CTA in endoleak classification and gives more accurate information in therapeutic planning.

Aged↗
PubMed2002

The clinical relevance of non-classified dysganglionoses and implications for a new grading system.

In addition to the classified types of dysganglionosis, certain non-classified dysganglionoses (NCD) (types 1-4) were introduced by Meier-Ruge in 1992. Clinical data on these conditions are limited. Among 134 children with intestinal dysganglionoses (ID) treated from 1979 to 1999, 12 were identified to have a NCD. Their clinical course is presented. The existence of mild ID (type 1) is difficult to demonstrate. Current definitions and data on clinical relevance are not convincing. An indication for surgical treatment is not present. Isolated hypogenesis of the submucous plexus (SMP) (type 2, n = 8) is clinically a more severe kind of intestinal neuronal dysplasia type B and often requires early surgical intervention, but not resection. When associated with aganglionosis, its recognition is important for surgical strategy, to avoid complicated clinical courses, which are frequent if total or nearly-total resection is not performed. Hypogenesis of the myenteric plexus (MP) (type 5, n = 1) has received little attention so far. The sporadic appearance of heterotopic nerve cells of the SMP in the mucosa (type 3, n = 1) is physiologic; clusters of such cells, however, are probably of pathologic value, especially in combination with other types of ID in the same patient. Heterotopic nerve cells of the MP (type 4, n = 3) in the circular and longitudinal muscle layers are highly pathologic. This clearly-defined type is of major clinical relevance and requires complete resection. A severe disturbance of the migration process is the underlying cause. To simplify the terminology of IDs, a grading system based on the anatomic structures and clinical findings is proposed: innervation disturbances of the mucosa (grade I) are of limited clinical significance. Isolated malformations of the SMP (grade II) may require an enterostomy, but do not require resection except in certain cases associated with distal aganglionosis. Dysganglionosis of the MP (grade III) usually exhibits more severe symptoms and resection is indicated, especially with associated hypo- or aganglionosis. In aganglionic bowel (grade IV) resection is mandatory.

Child↗
PubMed2006

Clinicopathologic characteristics of sporadic Japanese Creutzfeldt-Jakob disease classified according to prion protein gene polymorphism and prion protein type.

We analyzed neuropathologic features of 23 Japanese patients with sporadic Creutzfeldt-Jakob disease (sCJD) by means of prion protein (PrP) immunolabeling associated with codon 129 polymorphism of the PrP gene and western blot analysis of protease-resistant PrP (PrP type). Clinical features, particularly age at onset, disease duration, periodic synchronous discharge and presence of myoclonus, were also analyzed. This study included 11 cases of subacute spongiform encephalopathy (SSE), 10 cases of panencephalopathic (PE)-type sCJD and two cases of thalamic-type sCJD, classified according to cerebral pathology findings. According to PrP gene polymorphism and PrP type, 18 cases were classified as MM1-type, two as MV1-type, two as MM2-type and one as MM1 + 2-type sCJD. SSE and PE-type sCJD showed similar clinical features, with the exception of disease duration, codon 129 polymorphism and PrP type. Thalamic-type sCJD showed different clinical features and PrP type. We suggest that SSE and PE-type sCJD comprise the sCJD subtype and that PE-type sCJD is a prolonged pathologic phenotype of SSE. When we compare our results with those from a series of Caucasian sCJD patients, the percentages of codon 129 polymorphisms differed, as did classification based on PrP gene polymorphism and PrP type; our series included many PE-type sCJD cases and disease duration was relatively long and MM2-type cases showed clinicopathologic variability.

Adult↗
PubMed2005

A support vector machine approach to classify human cytochrome P450 3A4 inhibitors.

The cytochrome P450 (CYP) enzyme superfamily plays a major role in the metabolism of commercially available drugs. Inhibition of these enzymes by a drug may result in a plasma level increase of another drug, thus leading to unwanted drug-drug interactions when two or more drugs are coadministered. Therefore, fast and reliable in silico methods predicting CYP inhibition from calculated molecular properties are an important tool which can be applied to assess both already synthesized as well as virtual compounds. We have studied the performance of support vector machines (SVMs) to classify compounds according to their potency to inhibit CYP3A4. The data set for model generation consists of more than 1300 structural diverse drug-like research molecules which were divided into training and test sets. The predictive power of SVMs crucially depends on a careful selection of parameters specifying the kernel function and the penalty for misclassifications. In this study we have investigated a procedure to identify a valid set of SVM parameters which is based on a sampling of the parameter space on a regular grid. From this set of parameters, either single SVMs or SVM committees were trained to distinguish between strong and weak inhibitors or to achieve a more realistic three-class assignment, with one class representing medium inhibitors. This workflow was studied for several kernel functions and descriptor sets. All SVM models performed significantly better than PLS-DA models which were generated from the corresponding descriptor sets. As a very promising result, simple two-dimensional (2D) descriptors yield a three-class model which correctly classifies more than 70% of the test set. Our work illustrates that SVMs used in combination with simple 2D descriptors provide a very effective and reliable tool which allows a fast assessment of CYP3A4 inhibition potency in an early in silico filtering process.

Computer-Aided Design↗
PubMed2002

Analysis of the entire genomes of thirteen TT virus variants classifiable into the fourth and fifth genetic groups, isolated from viremic infants.

TT virus (TTV) DNA in serum samples obtained from 24 TTV-infected infants was amplified by polymerase chain reaction (PCR) with inverse primers derived from the untranslated region. The amplified PCR products were molecularly cloned; six clones each were analyzed. Seventy-six (53%) of the 144 TTV clones were classified into group 4 (YONBAN isolates), and 22 (15%) into a novel genetic group (group 5). The TTV clones in group 4 were classified into 9 types, and those in group 5 into 4 types. The entire nucleotide sequence of one representative clone each from the 13 types were determined; they comprised 3570-3770 nucleotides, and had poor homology to TTVs of groups 1-3 (TA278, PMV and SANBAN isolates). A phylogenetic tree based on the entire nucleotide sequence of open reading frame 1 confirmed the presence of five distinct clusters separated by a bootstrap value of 100%. Analysis of 13 TTV variants demonstrated preservation of the genomic organization and transcription profile in all TTV groups. TTV group 4 was detected in 54% or 72% of 7-to-12-month-old infants in Japan and China, respectively, which is comparable with that among adults in the respective country, indicating early and frequent acquisition of this TTV group in infancy.

Adult↗
PubMed1995

Proposal of a tiered approach to assessing and classifying the health risk of exposure to fibres.

The basis of a preventative health policy for humans against potential risks from chemical products is based on risk assessment leading to the classification and labeling of substances. However, the different existing classifications do not give an homogeneous framework that can be used in every country. Therefore, a tiered approach to assessing and classifying the health risk of exposure to fibres is proposed based on the EU Directive on carcinogens. The aim of this paper is to propose an algorithm for the risk assessment of existing and future fibres. Clearly chemically defined respirable fibres should be classified according to an algorithm based on a step-by-step procedure: a priori criteria, screening tests, long-term inhalation tests and epidemiological data (for commercial fibres). Then fibre-containing products should be labelled according to the classification of each type of fibre it contains, on one hand, and the ability of the product to release fibre in the air, on the other. The different tests listed in this algorithm, extensively discussed during the Workshop, are presented in detail in the following paper.

Carcinogenicity Tests↗
PubMed1987

Diagnosis of acute abdominal pain using a three-stage classifier.

The present paper deals with an application of a three-stage classifier based on a decision tree logic to the diagnosis of acute abdominal pain. On the basis of clinical information collected from a series of 476 patients suffering from abdominal pain of acute onset, the method of multistage classifier synthesis is presented. The results of classification accuracy using a modified version of k-nearest neighbours strategy for different features used at interior nodes of a tree are given.

Abdomen, Acute↗
PubMed1991

Fuzzy K-nearest neighbor classifiers for ventricular arrhythmia detection.

We report a study of the efficiency of 4 classifiers (the K-nearest-neighbor and single-nearest-prototype algorithms, each as parametrized by both Fuzzy C-Means and Fuzzy Covariance clustering) in the detection of ventricular arrhythmias in ECG traces characterized by 4 features derived from 7 spectral parameters. Principal components analysis was used in conjunction with a cardiologist's deterministic classification of 90 ECG traces to fix the number of trace classes to 5 (ventricular fibrillation/flutter, sinus rhythm, ventricular rhythms with aberrant complexes and 2 classes of artefact). Forty of the 90 traces were then defined as a test set; 5 different learning sets (numbering 25, 30, 35, 40 and 45 traces) were randomly selected from the remaining 50 traces; each learning set was used to parametrize both the classification algorithms using both fuzzy clustering algorithms and the parametrized classification algorithms were then applied to the test set. Optimal K for K-nearest-neighbor algorithms and optimal cluster volumes for Fuzzy Covariance algorithms were sought by trial and error to minimize classification differences with respect to the cardiologist's classification. Fuzzy Covariance clustering afforded significantly better perception of cluster structure than the Fuzzy C-Means algorithm, and the classifiers performed correspondingly with an overall empirical error ratio of just 0.10 for the K-nearest-neighbor algorithm parametrized by Fuzzy Covariance.

Algorithms↗
PubMed1987

A new method of classifying prognostic comorbidity in longitudinal studies: development and validation.

The objective of this study was to develop a prospectively applicable method for classifying comorbid conditions which might alter the risk of mortality for use in longitudinal studies. A weighted index that takes into account the number and the seriousness of comorbid disease was developed in a cohort of 559 medical patients. The 1-yr mortality rates for the different scores were: "0", 12% (181); "1-2", 26% (225); "3-4", 52% (71); and "greater than or equal to 5", 85% (82). The index was tested for its ability to predict risk of death from comorbid disease in the second cohort of 685 patients during a 10-yr follow-up. The percent of patients who died of comorbid disease for the different scores were: "0", 8% (588); "1", 25% (54); "2", 48% (25); "greater than or equal to 3", 59% (18). With each increased level of the comorbidity index, there were stepwise increases in the cumulative mortality attributable to comorbid disease (log rank chi 2 = 165; p less than 0.0001). In this longer follow-up, age was also a predictor of mortality (p less than 0.001). The new index performed similarly to a previous system devised by Kaplan and Feinstein. The method of classifying comorbidity provides a simple, readily applicable and valid method of estimating risk of death from comorbid disease for use in longitudinal studies. Further work in larger populations is still required to refine the approach because the number of patients with any given condition in this study was relatively small.

Actuarial Analysis↗
PubMed1979

Should 'non-Feighner schizophrenia' be classified with affective disorder?

Narrow definitions of schizophrenia increase homogeneity at the expense of leaving unclassified many patients with shizophrenic symptoms. Family history and follow-up studies indicate that many such patients ought to be classified with those having affective disorders. This study determines morbid risks for affective disorder and schizophrenia in first degree relatives of patients with chart but not research diagnoses of schizophrenia. Comparisons with morbid risk figures for relatives of individuals satisfying research criteria for depression, mania or schizophrenia indicate that the 'non-Feighner schizophrenia' group is probably too heterogenous to be classified entirely as affective disorder or as schizophrenia.

Adolescent↗
PubMedDate not supplied

Evaluation of automated information systems in health care: an approach to classifying evaluative studies.

In this paper we discuss an approach to classifying evaluative studies of automated information systems in health care. Selected literature (76 studies) is classified according to the type of automated information system (based on relationship to the care process), the study design used, the data collection methods used, the effect(s) measured and the type of evaluation (e.g. cost-benefit analysis). First results show that certain types of automated information systems have not been evaluated much, going by the number of studies selected. Furthermore, it is observed that certain study designs (time-series design), data collection methods (modelling and simulation) and effect measures (job satisfaction) are hardly to be found in the literature. Only 10 of 76 selected studies used a type of evaluation for which both consequences and costs are considered. Detailed investigation of the literature may provide information for the development of a general framework for the evaluation of different types of automated information systems.

Classification↗
PubMed1989

The bleeding severity index: validation and comparison to other methods for classifying bleeding complications of medical therapy.

Reports of bleeding complications of medical therapy should be based on valid methods of classification, but the reproducibility of existing methods has not been tested. Therefore, we prospectively studied three methods to classify the severity of bleeding: a purely subjective implicit method, a previously published explicit method using brief criteria, and the bleeding severity index, which is a new explicit method using detailed criteria about the amount, rate, and consequences of bleeding. Three physicians independently reviewed abstracts of 168 patients treated with anticoagulants. The proportion of cases classified as major bleeding varied widely when the implicit method was used (2, 14 and 39%), less when the old explicit method was used (28, 40 and 47%), and not at all when the new bleeding severity index was used (20, 20 and 20%). Intraobserver agreement was excellent for both explicit methods (kappa greater than or equal to 0.95). However, interobserver agreement was better for the bleeding severity index (kappa = 0.87) than for the old explicit method (kappa = 0.69) or the implicit method (kappa = 0.39). We conclude that the classification of bleeding complications of medical therapy depends on the method used. In comparison to older methods, the bleeding severity index is highly reproducible and should be tested more widely to determine whether it can be applied to the burgeoning clinical research in anticoagulation and thrombolysis.

Anticoagulants↗
PubMed2004

Differential effect of two nicotinic acid preparations on low-density lipoprotein subclass distribution in patients classified as low-density lipoprotein pattern A, B, or I.

We tested the hypothesis that treatment with nicotinic acid results in a differential blood lipid response in subjects classified as having a low-density lipoprotein (LDL) pattern A or B. One hundred eighty hypercholesterolemic subjects were randomized to placebo (n = 61), immediate-release niacin (3,000 mg/day, n = 59), or extended-release niacin (1,500 mg/day, n = 60) for 14 weeks. Lipids and lipoprotein cholesterol were determined with enzymatic methods. LDL subclass distribution was determined with 2% to 16% polyacrylamide gradient gel electrophoresis. Extended- and immediate-release niacin had significant effects on the decrease of triglycerides, total cholesterol, LDL cholesterol, apoprotein B, lipoprotein(a), and apoprotein A-I and significantly increased high-density lipoprotein cholesterol. The 2 nicotinic acid compounds and doses significantly increased mean LDL peak particle diameter and percent distribution in large LDL I and IIa, with a significant decrease in small LDL IIIa, IIIb, and IVb. In patients with LDL pattern B compared with those with pattern A, extended-release niacin (1,500 mg/day) increased LDL peak particle diameter significantly more and decreased the percent distributions of small LDL IIIa, LDL IIIb, and LDL IVa significantly more. With 3,000 mg/day, immediate-release nicotinic acid in patients with LDL pattern B exhibited a significantly greater increase in LDL peak particle diameter and large LDL IIa and IIb and significantly greater decreases in small LDL IIIa, IIIb, and IVa compared with patients with pattern A. These differences in response between patients with LDL pattern A and those with pattern B were not reflected by changes in the standard lipid profile, including apoproteins A-I and B. Nicotinic acid has a significantly different effect on lipids and lipoprotein subclass distribution in subjects classified as having LDL subclass pattern A or B. Nicotinic acid has a significantly greater effect on the decrease of small LDL subclass distribution and increase in LDL peak particle diameter in pattern B versus pattern A.

Adult↗
PubMed2006

Classifying patients suspected of appendicitis with regard to likelihood.

BACKGROUND: We sought to develop a clinical predictive model for acute appendicitis and contrast it with current clinical practice. METHODS: A prospective observational study of patients presenting with signs or symptoms consistent with acute appendicitis. Random-partition modeling was used to develop an appendicitis likelihood model (ALM). RESULTS: Four hundred thirty-nine patients were enrolled, 101 with appendicitis, and 338 with other diagnoses. The ALM classified patients as "low likelihood" if they had a white blood cell count <9,500 and either no right lower-quadrant tenderness or a neutrophil count <54%. Patients were classified as "high likelihood" if they had a white blood cell count >13,000 with rebound tenderness or both voluntary guarding and neutrophil count >82%. The ALM outperformed actual clinical practice with regard to "missed" appendicitis, negative laparotomies, and total number of imaging studies. CONCLUSION: The ALM may permit more judicious use of advanced radiographic imaging with lower nontherapeutic laparotomy rates.

Adolescent↗
PubMed2005

Classifying threats with a 14-MeV neutron interrogation system.

SeaPODDS (Sea Portable Drug Detection System) is a non-intrusive tool for detecting concealed threats in hidden compartments of maritime vessels. This system consists of an electronic neutron generator, a gamma-ray detector, a data acquisition computer, and a laptop computer user-interface. Although initially developed to detect narcotics, recent algorithm developments have shown that the system is capable of correctly classifying a threat into one of four distinct categories: narcotic, explosive, chemical weapon, or radiological dispersion device (RDD). Detection of narcotics, explosives, and chemical weapons is based on gamma-ray signatures unique to the chemical elements. Elements are identified by their characteristic prompt gamma-rays induced by fast and thermal neutrons. Detection of RDD is accomplished by detecting gamma-rays emitted by common radioisotopes and nuclear reactor fission products. The algorithm phenomenology for classifying threats into the proper categories is presented here.

Algorithms↗
PubMed2005

Using optimized evidence-theoretic K-nearest neighbor classifier and pseudo-amino acid composition to predict membrane protein types.

Knowledge of membrane protein type often provides crucial hints toward determining the function of an uncharacterized membrane protein. With the avalanche of new protein sequences emerging during the post-genomic era, it is highly desirable to develop an automated method that can serve as a high throughput tool in identifying the types of newly found membrane proteins according to their primary sequences, so as to timely make the relevant annotations on them for the reference usage in both basic research and drug discovery. Based on the concept of pseudo-amino acid composition [K.C. Chou, Proteins: Struct. Funct. Genet. 43 (2001) 246-255; Erratum: Proteins: Struct. Funct. Genet. 44 (2001) 60] that has made it possible to incorporate a considerable amount of sequence-order effects by representing a protein sample in terms of a set of discrete numbers, a novel predictor, the so-called "optimized evidence-theoretic K-nearest neighbor" or "OET-KNN" classifier, was proposed. It was demonstrated via the self-consistency test, jackknife test, and independent dataset test that the new predictor, compared with many previous ones, yielded higher success rates in most cases. The new predictor can also be used to improve the prediction quality for, among many other protein attributes, structural class, subcellular localization, enzyme family class, and G-protein coupled receptor type. The OET-KNN classifier will be available as a web-server at http://www.pami.sjtu.edu.cn/kcchou.

Algorithms↗