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 631 records · Page 35Linked to original sources
PubMed1992

Chemicals classified by IARC: an investigation of some of their toxicological characteristics.

Chemicals classified by the IARC to its Groups 1, 2A, 2B and 3 were examined in an attempt to identify characteristics of their behaviour in experimental studies of carcinogenicity, genotoxicity and acute, mammalian toxicity that correlate with those categories. Only those agents for which carcinogenic potency information was available were studied. For both mice and rats, greater proportions of chemicals were potent carcinogens if they had been categorized in Group 1 (human carcinogens) than if they had been put into one of the other categories. Not surprisingly, there was a weak association between carcinogenic potency and acute toxicity. Mice were especially sensitive to tumour induction by halides, while the lower sensitivity of rats to any carcinogenic effect of halides could be due in part to the higher systemic toxicity of halides in this species: a reduced differential of toxic and carcinogenic doses decreases the dose window in which carcinogenic effects may be demonstrated. It was notable that the human carcinogens were active in those genotoxicity tests with higher specificity for identifying rodent carcinogens. Predictive assays for carcinogenicity considered to have high specificity were in vivo cytogenetic, hepatocyte unscheduled DNA synthesis and Salmonella (5 commonly used strains) and mammalian cell hprt locus mutation assays. None of the relationships was strong enough to form the basis of a simple categorization process, but they could serve to alert investigators to chemicals of special toxicological interest and importance.

Animals↗
PubMed1992

Composite and classified color display in MR imaging of the female pelvis.

Because of its superior soft-tissue-imaging capabilities, MRI has proved to be an excellent modality for visualizing the contents of the female pelvis. In an effort to potentially improve gynecological MRI studies, we have applied color composite techniques to sets of spin-echo and gradient-echo gray-tone MR images obtained from various individuals. For composite generation, based on tissue region of interest calculated mean pixel intensity values, various colors were applied to spatially aligned images using a DEC MicroVAX II computer with interactive digital language (IDL) so that tissue contrast patterns could be optimized in the final image. The IDL procedures, which are similar to those used in NASA's LANDSAT image processing system, allowed the generation of single composite images displaying the combined information present in a series of spatially aligned images acquired using different pulse sequences. With our composite generation techniques, it was possible to generate seminatural-appearing color images of the female pelvis that possessed enhanced conspicuity of specific tissues and fluids. For comparison with color composites, classified images were also generated based on computer recognition and statistical separation of distinct tissue intensity patterns in an image set using the maximum likelihood processing algorithm.

Color↗
PubMed1995

Quantitative assessment of myocardial ultrasound tissue characterization through receiver operating characteristic analysis of Bayesian classifiers.

OBJECTIVES: This work proposes a self-consistent assessment methodology for quantitative evaluation of any combination of diagnostic features, with the immediate goal of quantitatively assessing the discriminating power in diabetic patients of features derived from ultrasound backscatter from myocardium. BACKGROUND: Four features from analysis of left ventricular myocardial ultrasound backscatter have previously been shown to be sensitive to potentially cardiomyopathic changes in patients with insulin-dependent diabetes mellitus who have no overt heart disease. The measured features were significantly different between such patients and normal control subjects, as well as among groups of such patients with and without systemic complications of the disease. The quantitative discriminating potential of the features was not assessed. METHODS: Multivariate classifier functions were constructed and analyzed by using the methodology of the receiver operating characteristic curve, which allows quantitative assessment of the discriminating power of these features, alone or in combination. The area under the receiver operating characteristic curve--the true positive rate averaged over all false positive rates--was used as a summary measure of performance. RESULTS: In distinguishing patients with insulin-dependent diabetes mellitus from normal control subjects, the most discriminating combination of ultrasound features for the detection of such changes in these patients yielded receiver operating characteristic curves with area measures of approximately 0.80; for such patients with retinopathy the measure increased to 0.90. This performance is comparable to that of many commonly used diagnostic tests. CONCLUSIONS: A self-consistent set of evaluation methodologies has quantitatively demonstrated the sensitivity of four ultrasound backscatter features to otherwise latent changes in myocardial structure that accompany the evolution of insulin-dependent diabetes mellitus. The results are remarkable in themselves and suggest the potential of the features for the general field of cardiac ultrasound tissue characterization.

Bayes Theorem↗
PubMedDate not supplied

A rational system for classifying and denominating adenovirus genome types.

We propose to classify "genome types" of human adenoviruses in the same way as the "genomic clusters" defined by Li and Wadell, i.e. groups of closely related DNA variants of a given serotype named by the use of indices, P (standing for prototype) a, b etc. Variants within the genome type are named by letter-number indices (p1, p2; a1, a2 etc.). The percentage of comigrating restriction fragments and common restriction sites is significantly higher in variants than between genome types. The new naming system is applicable to adenoviruses from 5 subgenera, but requires additional work for subgenus C strains. Renaming is required mainly for adenovirus 7.

Adenoviruses, Human↗
PubMedDate not supplied

The inhibitory effect of differently classified calcium antagonists on the calcium- and epinephrine-induced responses of isolated guinea-pig atria.

The effects of calcium antagonists diltiazem, flunarizine and N-(6-aminohexyl)-5-chloro-1-naphthalenesulfonamide (W7) were investigated on the calcium- and epinephrine-induced responses of guinea-pig spontaneously beating atria. All these calcium antagonists showed negative chronotropic and inotropic effects. Diltiazem (3 x 10(-8) M to 1.8 x 10(-7) M) antagonized both the action of epinephrine and calcium in a different manner but at the same concentrations. Flunarizine (1 x 10(-6) M to 1 x 10(-5) M) also antagonized both the action of epinephrine and calcium; but flunarizine weakly inhibits the calcium response at concentrations which have considerable antiadrenergic action. Only at the highest concentrations did both calcium antagonists show a decrease of the epinephrine maximum effect. W7 (1 x 10(-5) M to 1 x 10(-4) M) showed a mainly non-competitive antagonism against epinephrine but was practically ineffective against calcium. The results obtained suggest that a pharmacological prerequisite exists for classifying a calcium antagonist as a calcium entry blocker in the atrial muscle. Such a drug does not produce selective inhibition to calcium- and epinephrine-induced responses. The ability or inability to inhibit the response to calcium represents the discriminant parameter for the action site of the calcium antagonist which are transmembranal fluxes or intracellular mechanisms respectively.

Animals↗
PubMed2004

Neonatal mortality rates among growth-discordant twins, classified according to the birth weight of the smaller twin.

OBJECTIVE: The purpose of this study was to evaluate neonatal mortality rates among discordant twins, classified according to the birth weight of the smaller twin. STUDY DESIGN: We compared neonatal mortality rates among three groups of discordant twins (>25%), distinguished by the birth weight of the smaller twin being <10th, 10th to 50th, or >50th percentile. RESULTS: Among the 10,683 pairs of twins who were studied, the respective proportions of the three groups were 62.4%, 32.9%, and 4.7%. The neonatal mortality rate was significantly higher among pairs in which the smaller twin weighed <10th birth weight percentile (29. vs 11.1 and 11 per 1000; odds ratio, 2.7; 95% CI, 1.3, 5.7). This difference results from the higher mortality rates among the smaller but not among the larger twins. CONCLUSION: Severely discordant twin pairs in whom the smaller twin is also small for gestational age are at an increased risk of neonatal death. Identification of this group is an imperative step in the management of birth weight discordance in twin gestations.

Birth Weight↗
PubMed2005

Gemfibrozil reduces small low-density lipoprotein more in normolipemic subjects classified as low-density lipoprotein pattern B compared with pattern A.

We tested the hypothesis that gemfibrozil has a differential effect on low-density lipoprotein (LDL) and high-density lipoprotein (HDL) subclass distributions and postprandial lipemia that is different in subjects classified as having LDL subclass pattern A or LDL pattern B who do not have a classic lipid disorder. Forty-three normolipemic subjects were randomized to gemfibrozil (1,200 mg/day) or placebo for 12 weeks. Lipids and lipoproteins were determined by enzymatic methods. The mass concentrations of lipoproteins in plasma were determined by analytic ultracentrifugation and included the S(f) intervals: 20 to 400 (very LDL), 12 to 20 (intermediate-density lipoprotein), 0 to 12 (LDL), and HDL(2) mass (F(1.20) 3.5 to 9.0) and HDL(3) mass (F(1.20) 0 to 3.5). Postprandial measurements of triglycerides and lipoprotein(a) were taken after the patients consumed a 500 kcal/M(2) test meal. Treatment with gemfibrozil, compared with placebo, significantly reduced fasting plasma triglycerides (difference from placebo +/- SE; -50.2 +/- 20.6 mg/dl, p = 0.02), total cholesterol (-16.4 +/- 7.5 mg/dl, p = 0.04), apolipoprotein B (-16.1 +/- 5.5 mg/dl, p = 0.006), very LDL mass of S(f) 20 to 400 (-50.8 +/- 24.1 mg/dl, p = 0.02), S(f) 20 to 60 (-17.5 +/- 8.5 mg/dl, p = 0.05), S(f) 60 to 100 (-16.2 +/- 8.1 mg/dl, p = 0.05), and increased peak S(F) (0.48 +/- 0.27 Svedberg, p = 0.08). Gemfibrozil reduced the postprandial triglyceride level significantly at 3 (p = 0.04) and 4 (p = 0.05) hours after the test meal. A significantly different subclass response to gemfibrozil was observed in those with LDL pattern A versus B. Those with LDL pattern B had a significantly greater reduction in the small LDL mass S(f) 0 to 7 (p = 0.04), specifically regions S(f) 0 to 3 (p = 0.009) and S(f) 3 to 5 (p = 0.009). In conclusion, normolipemic subjects with either predominantly dense or buoyant LDL respond differently to gemfibrozil as determined by the changes in LDL subclass distribution. Thus, treatment with gemfibrozil may have additional antiatherogenic effects in those with LDL pattern B by decreasing small dense LDL that is not apparent in those with pattern A.

Adult↗
PubMed2006

Classifying microRNAs in cancer: the good, the bad and the ugly.

MicroRNAs (miRNAs) have quite recently emerged as a novel class of gene regulators. Many miRNAs exhibit altered expression levels in cancer, and we are only starting to understand the functional consequences of the loss or gain of particular miRNAs to the cancerous phenotype. miRNAs can be classified with regard to their role in cancer as the Good, the Bad and the Ugly. The "Good", those miRNAs that are innocent bystanders in the oncogenic transformation process, whose expression profile might even be used for cancer diagnosis or prognosis. The "Bad", those miRNAs that are causally linked to tumorigenesis and directly modify tumor suppressor- or oncogenic- pathways. And the "Ugly", those miRNAs whose inappropriate loss or gain destabilizes the cellular identity of a tumor, which indirectly results in enhanced phenotypic variability and progression of the tumor. Hereunder we will discuss the possible ways in which miRNAs can be relevant to cancer biology, and possible experimental strategies for elucidating the mechanisms involved.

Algorithms↗
PubMed2006

Feature-similarity protein classifier as a ligand engineering tool.

Kinases have been often targeted in drug therapy aimed at blocking signaling pathways. However, the conservation of protein structure across homologs often leads to uncontrolled cross-reactivity. On the other hand, sticky packing defects in proteins are typically not conserved across homologs, making them ligand-anchoring sites potentially important to enhance selectivity. Thus, we introduce a hierarchical clustering of PDB-reported kinases according to packing differences. This kinome partitioning is highly correlated with proximity relations arising from the pharmacological profiling of kinases. A variable packing sensitivity is observed for individual drugs, with highly promiscuous ligands being the most insensitive to packing differences. Our classifier enables a strategy to design selective inhibitors.

Computer Simulation↗
PubMed2026

Disagreement-informed arbitration for gene regulatory network inference: A score-level meta-classifier and a diagnostic typology of inter-method conflict.

Gene regulatory network inference methods routinely disagree about individual edges, and practitioners resolve those conflicts by choosing one method or averaging them all. We ask whether the conflict can instead be arbitrated per edge. A gradient-boosted classifier is trained on the raw scores that ten inference methods-correlation-based, information-theoretic, sparse-regression and tree-ensemble, including GENIE3, GRNBoost2, CLR and ARACNe-assign to each candidate regulator-target pair, so that the weight given to each method varies from edge to edge. Across six single-cell perturbation screens spanning four cell types, arbitration improves on mean ensembling by +0.056 AUROC on Adamson and +0.083 on Shifrut under target-grouped cross-validation. The evaluation protocol turns out to matter more than the model. Edge-level cross-validation, standard in this literature, inflates apparent gains by 0.060 AUROC through target-gene leakage-comparable to the entire honest improvement. The effect is far larger for methods that represent genes implicitly: a supervised graph-attention link predictor trained on identical folds scores AUROC 0.930 under edge-level cross-validation, better than anything else we evaluate, and 0.533 once target genes are held out. Any method that parameterises genes is exposed, which covers most graph- and embedding-based approaches. A five-category typology of inter-method conflict localises where arbitration pays off, with the largest gains on edges where the methods disagree and the smallest where they already agree, while adding nothing as model input; we therefore report it as a diagnostic instrument rather than a modelling contribution. We also characterise what the ground truth measures: most perturbed genes in widely used screens are not transcription factors, and a mediation screen bounds how much of the perturbation response can be direct.

Ensemble methods↗
PubMed2005

Unified Markov thermodynamics based on stochastic forms to classify drugs considering molecular structure, partition system, and biological species: distribution of the antimicrobial G1 on rat tissues.

To date, molecular descriptors do not commonly account for important information beyond chemical structure. The present work, attempts to extend, in this sense, the stochastic molecular descriptors, incorporating information about the specific biphasic partition system, the biological species, and chemical structure inside the molecular descriptors. Consequently, MARCH-INSIDE molecular descriptors may be identified with time-dependent thermodynamic parameters (entropy and mean free energy) of partition process. A classification function was developed to classify data of 423 drugs and up to 14 different partition systems at the same time. The model has shown a high overall accuracy of 92.1% (293 out of 318 cases) in training series and 90% (36 out of 40 cases) in predicting ones. Finally, we illustrate the use of the model by predicting a high probability (%) for G1 (a novel antibacterial drug) to undergo partition on different biotic systems (rat organs): liver (97.7), spleen (97.5), lung (97.4), and adipose tissue (97.6). These theoretical results coincide with herein reported steady state plasma concentrations (c) and partition coefficients (P) in liver (c=42.25+/-7.86/P=4.75), spleen (11.47+/-4.43/P=1.29), lung (17.04+/-3.58/P=1.91), and adipose tissue (28.19+/-11.82/P=3.17). All values were relative to (14)C-labeled-radioactive-G1 in plasma (c=8.9+/-3.05) after 3h of oral administration. In closing, the present stochastic forms derive average thermodynamic parameters fitting on a more clearly physicochemical framework with respect to classic vector-matrix-vector forms, which include, as particular cases, quadratic forms such as Wiener index, Randic invariants, Zagreb descriptors, Harary index, Balaban index, and Marrero-Ponce quadratic molecular indices.

Animals↗
PubMed2004

Structure of the O-polysaccharide of Proteus mirabilis CCUG 10701 (OB) classified into a new Proteus serogroup, O74.

An acidic O-polysaccharide was isolated by mild acid degradation of the lipopolysaccharide of Proteus mirabilis CCUG 10701 (OB) and studied by chemical analyses and (1)H and (13)C NMR spectroscopy. The following structure of the tetrasaccharide repeating unit of the polysaccharide was established: --> 3)-beta-D-GlcpNAc6Ac-(1 --> 2)-beta-D-GalpA4Ac-(1--> 3)-alpha-D-GalpNAc-(1 --> 4)-alpha-D-GalpA-(1 -->, where the degree of O-acetylation at position 6 of GlcNAc is approximately 50% and at position 4 of beta-GalA approximately 60%. Based on the unique structure of the O-polysaccharide and serological data, it is proposed to classify P. mirabilis CCUG 10701 (OB) into a new Proteus serogroup, O74.

Acetylation↗
PubMed2005

What's in a name? A comparison of methods for classifying predominant type of maltreatment.

OBJECTIVE: The primary aim of the study was to identify a classification scheme, for determining the predominant type of maltreatment in a child's history that best predicts differences in developmental outcomes. METHOD: Three different predominant type classification schemes were examined in a sample of 519 children with a history of alleged maltreatment. Cases were classified into predominant maltreatment types according to three different schemes: Hierarchical regression analyses examined whether the HT, SFT, and EHT type classifications contributed to prediction of child behavior problems, trauma symptoms and adaptive functioning. RESULTS: After controlling for demographic factors, the HT definitions predicted four outcomes, while the SFT definitions predicted three, and the EHT classifications contributed to the prediction of five child outcomes. The co-occurrence of multiple types of maltreatment was robustly related to outcomes. However, the HT and SFT classifications predicted outcomes even after accounting for the co-occurrence of multiple maltreatment subtypes. CONCLUSION: A classification scheme that differentiates between type combinations and single maltreatment types may have the greatest predictive validity. Over and above knowing about co-occurrence of maltreatment sub-types, it is important to understand what type, or constellation of types, of maltreatment have been alleged in a child's history.

Child↗
PubMed2005

Similarity classifier with generalized mean applied to medical data.

A new approach based on fuzzy similarity was presented for the detection of erythemato-squamous diseases, diabetes, liver disorders, breast cancer and thyroid. The domain contained records of patients with known diagnoses. The results were very promising with all data sets and some conclusions can be drawn that a fuzzy similarity model can be used for the diagnosis of patients taking into consideration the error rate. A fuzzy similarity classifier was used to detect the six erythemato-squamous diseases when 34 features defining six disease indications were used as inputs. The results confirmed that the proposed model has potential in detecting erythemato-squamous diseases. The fuzzy similarity model achieved accuracy rates (over 97%) which were higher than that of the stand-alone neural network model or the ANFIS model suggested in [E.D. Ubeyli, I. Güler, Comput. Biol. Med. 35(5) (2005) 421-433]. With PIMA Indian diabetes, the detection model has an error rate of about 25% which is much better than the overall rate of 33% for diabetes. The model was also tested with other data sets: thyroid and two breast cancer data sets where the average detection accuracy was over 96% for all cases, which is quite good. Also, the liver disorder data set gave promising results.

Algorithms↗
PubMed2004

Development of the cubic least squares mapping linear-kernel support vector machine classifier for improving the characterization of breast lesions on ultrasound.

An efficient classification algorithm is proposed for characterizing breast lesions. The algorithm is based on the cubic least squares mapping and the linear-kernel support vector machine (SVM(LSM)) classifier. Ultrasound images of 154 confirmed lesions (59 benign and 52 malignant solid masses, 7 simple cysts, and 32 complicated cysts) were manually segmented by a physician using a custom developed software. Texture and outline features and the SVM(LSM) algorithm were used to design a hierarchical tree classification system. Classification accuracy was 98.7%, misdiagnosing 1 malignant an 1 benign solid lesions only. This system may be used as a second opinion tool to the radiologists.

Breast Diseases↗
PubMed2005

Endoscopic ultrasound and computer tomography are inaccurate methods of classifying cystic pancreatic lesions.

BACKGROUND: Despite advances in imaging modalities, preoperative diagnosis of pancreatic cystic lesions remains difficult. AIM: To assess the accuracy of endoscopic ultrasound and computer tomography to preoperatively distinguish benign from potentially malignant and malignant pancreatic cystic lesions. METHODS: Photograph series obtained from endoscopic ultrasound examinations of 66 patients with cystic pancreatic lesions were blindly reviewed by three endoscopic ultrasonographers. Forty-one of those 66 patients also underwent a computer tomography scan at our institution, which was blindly reviewed by a single radiologist. Computer tomography and endoscopic ultrasound classification into benign and malignant and potentially malignant pancreatic cystic lesions was correlated with the final diagnosis, which was established by surgical pathology (n = 43), diagnostic fine needle aspiration (n = 13) or follow-up imaging (n = 10). Interobserver agreement was measured using kappa statistics. RESULTS: Endoscopic ultrasound classification by the three examiners into benign versus malignant or potentially malignant cystic lesions was correct in 65-67%. Interobserver agreement was 50%. Kappa values for pairs of endoscopic ultrasound examiners were 0.16, 0.43 and 0.53. Computer tomography classification was correct in 71% and in agreement with the endoscopic ultrasound classification in 56-61% (kappa 0.12 to 0.27). CONCLUSIONS: Endoscopic ultrasound and computer tomography cannot accurately distinguish between benign pancreatic cystic lesions and malignant or potentially malignant ones. There is poor-to-modest interobserver agreement in classifying these lesions.

Adult↗
PubMed2005

Significance analysis of qualitative mammographic features, using linear classifiers, neural networks and support vector machines.

Advances in modern technologies and computers have enabled digital image processing to become a vital tool in conventional clinical practice, including mammography. However, the core problem of the clinical evaluation of mammographic tumors remains a highly demanding cognitive task. In order for these automated diagnostic systems to perform in levels of sensitivity and specificity similar to that of human experts, it is essential that a robust framework on problem-specific design parameters is formulated. This study is focused on identifying a robust set of clinical features that can be used as the base for designing the input of any computer-aided diagnosis system for automatic mammographic tumor evaluation. A thorough list of clinical features was constructed and the diagnostic value of each feature was verified against current clinical practices by an expert physician. These features were directly or indirectly related to the overall morphological properties of the mammographic tumor or the texture of the fine-scale tissue structures as they appear in the digitized image, while others contained external clinical data of outmost importance, like the patient's age. The entire feature set was used as an annotation list for describing the clinical properties of mammographic tumor cases in a quantitative way, such that subsequent objective analyses were possible. For the purposes of this study, a mammographic image database was created, with complete clinical evaluation descriptions and positive histological verification for each case. All tumors contained in the database were characterized according to the identified clinical features' set and the resulting dataset was used as input for discrimination and diagnostic value analysis for each one of these features. Specifically, several standard methodologies of statistical significance analysis were employed to create feature rankings according to their discriminating power. Moreover, three different classification models, namely linear classifiers, neural networks and support vector machines, were employed to investigate the true efficiency of each one of them, as well as the overall complexity of the diagnostic task of mammographic tumor characterization. Both the statistical and the classification results have proven the explicit correlation of all the selected features with the final diagnosis, qualifying them as an adequate input base for any type of similar automated diagnosis system. The underlying complexity of the diagnostic task has justified the high value of sophisticated pattern recognition architectures.

Analysis of Variance↗
PubMed2004

Mucosal immune responses to infections in infants with acute life threatening events classified as 'near-miss' sudden infant death syndrome.

This study examined the hypothesis that dysregulation of mucosal immune responses to respiratory infections is a critical event, which could be causal in respiratory arrest of some previously healthy infants. To examine this hypothesis, a prospective study was undertaken of infants presenting to the emergency department of a major teaching hospital with acute life threatening events (ALTE) of unknown cause and classified as "near-miss" SIDS. Salivary immunoglobulin concentrations were measured on admission and again after 14 days. The salivary immunoglobulins were compared with three control groups: infants with a mild upper respiratory tract infection (URTI); bronchiolitis; and healthy age-matched infants. The salivary IgA and IgM concentrations in the ALTE infants at presentation to hospital indicated a significant mucosal immune response had already occurred, with nearly 60% of the IgA concentrations significantly above the population-based reference ranges. The hyper-immune response was most evident in the ALTE infants with pathology evidence of an infection; 87% of these infants had salivary IgA concentrations on average 10 times higher that the age-related median concentration. The most prevalent pathogen identified in the ALTE infants was respiratory syncytial virus (RSV) (64%). RSV was also identified in all subjects with bronchiolitis. Risk factors for SIDS were assessed in each group. The data indicated that the ALTE infants diagnosed as 'near-miss' SIDS were a relatively homogeneous group, and most likely these ALTE infants and SIDS represent associated clinical outcomes. The study identified exposure to cigarette smoke and elevated salivary IgA concentrations as predictors of an ALTE. The study findings support the hypothesis of mucosal immune dysregulation in response to a respiratory infection in some infants with an ALTE. They provide a plausible explanation for certain SIDS risk factors. The underlying patho-physiological mechanism of proinflammatory responses to infections during a critical developmental period might be a critical factor in infants who have life-threatening apnoea or succumb to SIDS. The study raises the possibility of using salivary IgA to test infants who present with mild respiratory infections to identify a substantial number of infants at risk of developing an ALTE or SIDS, thus enabling intervention management to prevent such outcomes.

Apnea↗