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 379 records · Page 21Linked to original sources
PubMed2000

The learning classifier system: an evolutionary computation approach to knowledge discovery in epidemiologic surveillance.

The learning classifier system (LCS) integrates a rule-based system with reinforcement learning and genetic algorithm-based rule discovery. This investigation reports on the design, implementation, and evaluation of EpiCS, a LCS adapted for knowledge discovery in epidemiologic surveillance. Using data from a large, national child automobile passenger protection program, EpiCS was compared with C4. 5 and logistic regression to evaluate its ability to induce rules from data that could be used to classify cases and to derive estimates of outcome risk, respectively. The rules induced by EpiCS were less parsimonious than those induced by C4.5, but were potentially more useful to investigators in hypothesis generation. Classification performance of C4.5 was superior to that of EpiCS (P<0.05). However, risk estimates derived by EpiCS were significantly more accurate than those derived by logistic regression (P<0.05).

Algorithms↗
PubMed2002

An artificial intelligence approach to classify and analyse EEG traces.

We present a fully automatic system for the classification and analysis of adult electroencephalograms (EEGs). The system is based on an artificial neural network which classifies the single epochs of trace, and on an Expert System (ES) which studies the time and space correlation among the outputs of the neural network; compiling a final report. On the last 2000 EEGs representing different kinds of alterations according to clinical occurrences, the system was able to produce 80% good or very good final comments and 18% sufficient comments, which represent the documents delivered to the patient. In the remaining 2% the automatic comment needed some modifications prior to be presented to the patient. No clinical false-negative classifications did arise, i.e. no altered traces were classified as 'normal' by the neural network. The analysis method we describe is based on the interpretation of objective measures performed on the trace. It can improve the quality and reliability of the EEG exam and appears useful for the EEG medical reports although it cannot totally substitute the medical doctor who should now read the automatic EEG analysis in light of the patient's history and age.

Adult↗
PubMed2002

An automated phylogenetic key for classifying homeoboxes.

When novel gene sequences are discovered, they are usually identified, classified, and annotated based on aggregate measures of sequence similarity. This method is prone to errors, however. Phylogenetic analysis is a more accurate basis for gene classification and ortholog identification, but it is relatively labor-intensive and computationally demanding. Here we report and demonstrate a rapid new method for gene classification based on phylogenetic principles. Given the phylogeny of a minimal sample of gene family members, our method automatically identifies amino acids that are phylogenetically characteristic of each class of sequences in the family; it then classifies a novel sequence based on the presence of these characteristic attributes in its sequence. Using a subset of homeobox protein sequences as a test case, we show that our method approximates classification based on full-scale phylogenetic analysis with very high accuracy in a tiny fraction of the time.

Algorithms↗
PubMed1998

Incorporation of a set enumeration trees-based classifier into a hybrid computer-assisted diagnosis scheme for mass detection.

RATIONALE AND OBJECTIVES: The authors evaluated whether a hybrid classifier of two independent computer-aided diagnosis (CAD) schemes, the set enumeration (SE) trees approach and an artificial neural network (ANN), could improve the detection of masses on digitized mammograms. The potential benefits resulting from the interpretability of the SE trees model was also explored. MATERIALS AND METHODS: Two hundred thirty verified mass regions and 230 negative but suspicious regions were randomly selected from 618 digitized mammograms. Each region was represented by a 24-parameter feature vector. These features were used as input data for the SE trees and ANN-based schemes. After the positive and negative regions were randomly segmented into five exclusive partitions, a fivefold cross-validation method was applied to evaluate and compare the performance of the SE trees, ANN, and hybrid system in the identification of masses. RESULTS: The performance of the SE trees approach was comparable to that of the ANN. The average area under the receiver operating characteristic (ROC) curves for all five partitions was 0.88 (standard deviation, 0.04). Owing to the relatively low correlation between the region-based results of the SE trees and ANN methods, the hybrid classifier yielded a significantly improved performance, with an area under the ROC curve of 0.94 (standard deviation, 0.02; P < .05). CONCLUSION: The hybrid CAD scheme significantly improved performance. The amenability of the SE trees models to interpretation may aid in the assessment of the importance of specific features.

Artificial Intelligence↗
PubMed2001

Recognition of imagined hand movements with low resolution surface Laplacian and linear classifiers.

EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous EEG signals. In this framework, it was suggested that EEG patterns can be better detected with EEG data transformed with Surface Laplacian computation (SL) than with the unprocessed raw potentials. However, accurate SL estimates require the use of many EEG electrodes, when local estimation methods are used. Since BCI devices have to use a limited number of electrodes for practical reasons, we investigated the performances of spline methods for SL estimates using a limited number of electrodes (low resolution SL). Recognition of mental activity was attempted on both raw and SL-transformed EEG data from five healthy people performing two mental tasks, namely imagined right and left hand movements. Linear classifiers were used including Signal Space Projection (SSP) and Fisher's linear discriminant. Results showed an acceptable average correlation between the waveforms obtained with the low resolution SL and these obtained with the SL computed from 26 electrodes (full resolution SL). More importantly, satisfactorily recognition scores for mental EEG-patterns were obtained with the low-resolution surface Laplacian transformation of the recorded potentials when compared with those obtained by using full resolution SL (82%). These results demonstrated also the utility of linear classifiers for the detection of mental patterns in the BCI field.

Biomedical Engineering↗
PubMed1997

Purification of aminopeptidase from Australian classified barley flour.

Barley is one of the major crops cultivated in the world. A new milling system, which removes successive layers of the grain has been developed, the preparation being called a classified flour. We have detected aminopeptidase activity in the flour obtained from the near surface zone. Barley was the Weeah species cultivated in Australia. Our aim in this paper is to describe the complete purification of aminopeptidase from barley classified flour. Aminopeptidase activity was determined using L-leucine-p-nitroanilide in 10 mM sodium phosphate buffer, pH 7.0. Aminopeptidase was extracted in 20 mM sodium acetate buffer, pH 5.5. Fractions (HP-1 and HP-2) were obtained upon chromatography using an HI-propyl hydrophobic interaction column in 20 mM acetate buffer, pH 5.5, with a linear gradient of ammonium sulfate from 15 to 0% saturation after the ammonium sulfate fractionation (from 40 to 60% saturation) of the extract. The final purified preparation A-1-I-G was obtained from HP-1 by gel filtration, hydroxylapatite chromatography, diethylaminomethyl-ion exchange chromatography, and re-chromatography on a Sephacryl S-100HR gel column. It was pure as assessed by native and sodium dodecylsulfate-polyacrylamide gel electrophoreses. The specific activity of A-1-I-G was 64.8 fold that of the crude extract. A K(m) value of 0.138 mM when using L-leucine-p-nitroanilide was calculated. A-1-I-G is active over a wide pH range and has a strong affinity for its substrate. The classification process is effective as a step of enzyme purification. Also, the results with metal ions suggest that the enzyme is a metalloenzyme. It was concluded that complete purification of an aminopeptidase from barley was achieved.

Aminopeptidases↗
PubMed2005

Classifying genomic sequences by sequence feature analysis.

Traditional sequence analysis depends on sequence alignment. In this study, we analyzed various functional regions of the human genome based on sequence features, including word frequency, dinucleotide relative abundance, and base-base correlation. We analyzed the human chromosome 22 and classified the upstream, exon, intron, downstream, and intergenic regions by principal component analysis and discriminant analysis of these features. The results show that we could classify the functional regions of genome based on sequence feature and discriminant analysis.

Algorithms↗
PubMed1973

Mortality from cancer and cardiovascular diseases in the county boroughs of England and Wales classified according to the sources and hardness of their water supplies, 1958-1967.

Relative rates of proportionate mortality from cancer of six sites based on total cancer deaths and the proportions expected in all towns, and from four types of cardiovascular disease based on total deaths from all causes, have been related in the 80 county boroughs of England and Wales to the sources of water supply and to the average hardness of water in the towns. The sources of water, from upland surfaces, artesian wells and rivers, were classified in eight groups, and significant associations were found for cancers of the stomach, oesophagus, prostate, male bladder and female breast, and for hypertensive and chronic rheumatic heart disease. No associations were apparent with intestinal cancer, vascular disease of the nervous system or arteriosclerotic heart disease. Hardness or softness of the water was classified in seven groups and significant associations were found for the same diseases as for source of water, none being evident for coronary disease.

Adult↗
PubMed2004

A European longitudinal study in Salmonella seronegative- and seropositive-classified finishing pig herds.

Surveillance and control are important aspects of food safety assurance strategies at the pre-harvest level of pork production. Prior to implementation of a Salmonella surveillance and control programme, it is important to have knowledge on the dynamics and epidemiology of Salmonella infections in pig herds. For this purpose, 17 finishing pig herds initially classified as seropositive and 15 as seronegative, were followed for a 2-year period through serological and bacteriological sampling. The study included 10 herds from Denmark, 13 from The Netherlands, 4 from Germany and 5 from Sweden and was performed between October 1996 and May 1999. The Salmonella status of finishing pig herds was determined by an initial blood sampling of approximately 50 finishing pigs close to market weight per herd. The development of the Salmonella status of the selected herds was assessed at seven subsequent sampling rounds of 25 blood samples from finishing pigs, 25 blood samples from grower pigs and 10 pen faecal samples each, approximately 3 months apart. The odds for testing finishers seropositive, given that growers were found seropositive previously were 10 times higher than if growers were seronegative (OR 10.0, 95% CI 3.2-32.8). When Salmonella was isolated from pen faecal samples, the herd was more likely to be classified seropositive in the same sampling round, compared to no Salmonella being detected (OR 4.0, 95% CI 1.1-14.6). The stability of an initially allocated Salmonella status was found to vary noticeably with time, apparently irrespective of a seropositive or seronegative classification at onset of the study. Given the measured dynamics in the occurrence of Salmonella in pig herds, regular testing is necessary to enable producers, advisors and authorities to react to sudden increases in the Salmonella prevalence in single herds or at a national level.

Animals↗
PubMed2001

Array-to-array transfer of an artificial nose classifier.

This paper describes the use of a microsphere sensor technology that allows simple fabrication of vapor sensor arrays with reproducible response patterns. Microsphere sensor fabrication protocols are uncomplicated and yield billions of highly reproducible sensors. Microsphere sensor arrays combined with a generalized Whitney-Mann-Wilcoxen (GWMW) classifier were used to discriminate between the presence and absence of nitroaromatic compounds in high background vapor mixtures. The classifier was trained on one sensor array and then used to obtain 98.2 and 93.7% correct classification rates with data collected using two subsequent arrays made up to six months after the initial training was performed. These results represent an advance in the ability to transfer training data between multiple sensor arrays with a fluorescence-based artificial nose.

Artificial Organs↗
PubMed2003

Robust classifier for the automated detection of ammonia in heated plumes by passive fourier transform infrared spectrometry.

An automated classification algorithm is implemented for the detection of ammonia vapor in heated plumes by passive Fourier transform infrared (FT-IR) spectrometry. This classification methodology allows the real-time detection of chemical signatures in gaseous effluents such as those generated from industrial processes. The characteristics of real-time implementation and excellent robustness are achieved by an analysis strategy based on the application of band-pass digital filters to short segments of the interferogram data collected by the FT-IR spectrometer, followed by the use of piecewise linear discriminant analysis to obtain a yes/no classification regarding the presence of the analyte signature in the filtered data. The optimal classifier developed through this work is based on only 110 interferogram points and employs a single band-pass filter centered at 945 cm(-)(1) with a pass-band full width at half-maximum of 93 cm(-)(1). The average stop-band attenuation of the optimal filter is 42.1 dB. The robustness of the algorithm is tested by exposing it to chemical releases of sulfur hexafluoride, ethanol, methanol, sulfur dioxide, and hydrogen chloride that were not included in the development of the classifier. Excellent classification performance is demonstrated, with missed ammonia detections occurring at a rate of approximately 1%. The occurrence of false detections is less than 0.1% for SF(6) and less than 0.02% for the other interferences tested.

Air Pollutants, Occupational↗
PubMedDate not supplied

A criteria to classify biological activity of benzimidazoles from a model of structural similarity.

We have classified a set of 250 benzimidazoles using a criterion of structural similarity. This criterion has led us to several clusters, which keep a close relationship between the molecules belonging to each one of them and their pharmacological activity. To study the structural similarity we have built a mathematical space where chemical structures are pictured as vectors. A set of well-chosen descriptors was used as variables. These descriptors arise from graph theoretical studies and quantum mechanical calculations. Principal components analysis was employed to find the suitable dimension for the space. Finally, cluster analysis was performed to classify the set of molecules by similarity. A Euclidean metric was used as a similarity coefficient.

Benzimidazoles↗
PubMed2001

Comparison of exhaust emissions from Swedish environmental classified diesel fuel (MK1) and European Program on Emissions, Fuels and Engine Technologies (EPEFE) reference fuel: a chemical and biological characterization, with viewpoints on cancer risk.

Diesel fuels, classified as environmentally friendly, have been available on the Swedish market since 1991. The Swedish diesel fuel classification is based upon the specification of selected fuel composition and physical properties to reduce potential environmental and health effects from direct human exposure to exhaust. The objective of the present investigation was to compare the most stringent, environmentally classified Swedish diesel fuel (MK1) to the reference diesel fuel used in the "European Program on Emissions, Fuels and Engine Technologies" (EPEFE) program. The study compares measurements of regulated emissions, unregulated emissions, and biological tests from a Volvo truck using these fuels. The regulated emissions from these two fuels (MK1 vs EPEFE) were CO (-2.2%), HC (12%), NOx (-11%), and particulates (-11%). The emissions of aldehydes, alkenes, and carbon dioxide were basically equivalent. The emissions of particle-associated polycyclic aromatic hydrocarbons (PAHs) and 1-nitropyrene were 88% and 98% lower than those of the EPEFE fuel, respectively. The emissions of semi-volatile PAHs and 1-nitropyrene were 77% and 80% lower than those from the EPEFE fuel, respectively. The reduction in mutagenicity of the particle extract varied from -75 to -90%, depending on the tester strain. The reduction of mutagenicity of the semi-volatile extract varied between -40 and -60%. Furthermore, the dioxin receptor binding activity was a factor of 8 times lower in the particle extracts and a factor of 4 times lower in the semi-volatile extract than that of the EPEFE fuel. In conclusion, the MK1 fuel was found to be more environmentally friendly than the EPEFE fuel.

Animals↗
PubMed2002

An application of linear programming discriminant analysis to classifying and predicting the symptomatic status of HIV/AIDS patients.

This study presents an application of linear programming discriminant analysis (LPDA) to classify and to predict the symptomatic status of HIV/AIDS patients. We applied LPDA as well as several traditional discriminant analysis methods to the AIDS Cost and Services Utilization Survey data set in order to demonstrate the use of LPDA to classify the symptomatic status of HIV/AIDS patients. The potential benefit of LPDA in terms of the classification accuracy was also analyzed.

Diagnosis, Computer-Assisted↗
PubMed2000

Perinatal deaths in a Norwegian county 1986-96 classified by the Nordic-Baltic perinatal classification: geographical contrasts as a basis for quality assessment.

BACKGROUND: Quality assessment of perinatal care can be carried out by classifying perinatal deaths. In the following we have analyzed the geographical contrasts in perinatal deaths according to the Nordic-Baltic perinatal death classification in a sparsely populated Norwegian county. MATERIAL AND METHODS: All stillbirths (> or =28 weeks of gestation) and neonatal deaths (gestational age > or =22 weeks; death < or =28 days) in 1986-96 from Nordland county (240,000 inhabitants) were classified. For comparison the county was geographically divided into six general local hospital areas and one central hospital area. RESULTS: The classification showed a well acceptable inter and intra observer variation. One hundred and seventy-one stillbirths and 155 neonatal deaths were analyzed. The death rate (pr 1,000 births) for single, non-malformed, antenatal stillbirths was higher in the central hospital area than in the local hospital areas (3.22 vs. 2.02). The death rate for extreme preterm infants (22-27 weeks of gestation) was on the other hand higher in the local hospital areas (2.45 vs. 1.05). One of the general local hospital areas was singled out with an especially high neonatal death rate among extreme preterm infants. This was to some extent explained by the death of extreme preterm twins and triplets. CONCLUSION: The Nordic-Baltic perinatal death classification system is a consistent and reproducible tool also for studying perinatal death in restricted geographical areas. The observed contrasts in perinatal deaths were used as basis for programs aimed at improving perinatal care. The observation of an unexplained increased number of antenatal stillbirths in the central hospital area resulted in a program for prospective recording and better characterization of the placenta and umbilical cord. Proposals for a better antenatal program preventing extreme preterm birth of twins for the whole county has been launched. In utero transfer to a hospital with a neonatal intensive care unit seems crucial in improving the prognosis for these infants.

Age Factors↗
PubMed2002

A comparison of maximum covariance and K-means cluster analysis in classifying cases into known taxon groups.

Maximum covariance (MAXCOV) is a method for determining whether a group of 3 or more indicators marks 1 continuous or 2 discrete latent distributions of individuals. Although the circumstances under which MAXCOV is effective in detecting latent taxa have been specified, its efficiency in classifying cases into groups has not been assessed, and few studies have compared its performance with that of cluster analysis. In the present Monte Carlo study, the classification efficiencies of MAXCOV and the k-means algorithm were compared across ranges of sample size, effect size, indicator number, taxon base rate, and within-groups covariance. When the impact of these parameters was minimized, k-means classified more data points correctly than MAXCOV. However, when the effects of all parameters were increased concurrently, MAXCOV outperformed k-means.

Cluster Analysis↗
PubMed2006

Two-dimensional predictive equation to classify visceral obesity in clinical practice.

OBJECTIVE: Visceral obesity assessment is not easy, and although computed tomography (CT) is an accurate tool, this technique is expensive and sometimes not suitable in clinical practice. We developed a new two-dimensional elliptical anthropometric equation to classify visceral obesity and evaluated the validity and the reliability of the new equation compared with CT. RESEARCH METHODS AND PROCEDURES: We collected anthropometric and CT data from overweight/obese subjects (n = 61, BMI = 32.4 +/- 3.7 kg/m2). A validation group of 32 subjects was also selected. An equation for the assessment of visceral obesity was developed using multiple regression analysis. Once validated, the equation was compared with previous models. Tests for accuracy included mean differences, analysis of diagnostic, R2, Snedecor's F-test, and Bland-Altman plot. RESULTS: Multiple regression analysis revealed that the sagittal and coronal diameters and the triceps skinfold were significant contributors to the model. The final equation was: visceral area (VA)/subcutaneous area (SA)predicted = 0.868 + 0.064 x sagittal diameter - 0.036 x coronal diameter - 0.022 x triceps skinfold. Patients with visceral-subcutaneous area ratio (VA/SA) > 0.42 were classified as having visceral obesity. The predictive equation was valid, showing a significant association with VA/SA assessed by CT (VA/SA(CT); r = 0.68; p < 0.0001). Paired Student's t test showed no significant differences with VA/SACT (p = 0.541). The reliability was high [F(24/60) = 2.12; p = 0.01]. DISCUSSION: The new two-dimensional and elliptical predictive equation is valid to assess visceral obesity and is more precise than previous models.

Adult↗
PubMed2026

An international framework for clinical translation of molecular classifiers in osteosarcoma.

Despite well-recognized biological heterogeneity, osteosarcoma has been treated as a single disease for over four decades with minimal improvement in survival. Clinical features are inadequate for risk stratification, and no molecular classifiers guide therapy. An international working group evaluated candidate prognostic biomarkers for clinical translation. Pre-treatment circulating tumor DNA is positioned for clinical implementation, while additional classifiers warrant prospective validation. This work establishes a path to risk-adapted, biologically informed treatment.

Journal Article↗