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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 163 records · Page 9Linked to original sources

PubMed1994

The development of a decision support system for the pathological diagnosis of human cerebral tumours based on a neural network classifier.

This study describes the use of a topological mapping system in the classification of cerebral tumours and the development of a decision support system based upon that classifier. Fourteen pathological parameters from two hundred primary cerebral tumours are presented as vectors to a topological map. The map, consisting of a grid of neurones, learns the features of each tumour by means of a shortest Euclidean distance algorithm, after which self adaptation of the neurons occurs. An LVQ algorithm performs the final classification. Study of the map reveals that it can correctly classify tumors following their malignancy potential and their cytogenesis. The decision support system uses the network at its core and helps not only in reaching a diagnosis but also in finding the optimal way to reach that diagnosis. The usefulness of such a mapping system lies in the field of education, clinical research and medically acceptable cost reduction.

Algorithms↗

PubMed1991

[Schmuth's group findings--a simple system for classifying dysgnathias].

The advantages and disadvantages of Schmuth's findings, which classify eugnathic as well as dysgnathic dentition are opposed to Angle's classification. Using Schmuth's findings is a way of classifying without ignoring the physiological variability in the area of the first molars, which can lead to false diagnosis. 386 models were examined at the beginning of the patients' treatment. The results are discussed.

Dental Occlusion↗

PubMed1996

Classifying general medicine readmissions. Are they preventable? Veterans Affairs Cooperative Studies in Health Services Group on Primary Care and Hospital Readmissions.

OBJECTIVES: To describe a new quality assessment method used to classify the preventability of hospitalization in terms of patient, clinician, or system factors. DESIGN: The instrument was developed in two phases. Phase 1 was a prospective comparison of admitting residents' and their attending physicians' classifications of the perceived preventability of consecutive admissions to one Veterans Affairs Medical Center (VAMC) excluding admissions to the intensive care unit (ICU). In phase 2, a panel of 10 physicians rated 811 abstracted records of readmissions from nine VAMCs. SETTING: Nine VAMCs across the United States with varying degrees of university hospital affiliation. PATIENTS: Phase 1, 156 patients admitted to the general medicine service at the Durham VAMC. Phase 2, 514 patients accounting for 811 readmissions within 6 months of a general medicine service discharge at nine VAMCs. MEASUREMENTS AND MAIN RESULTS: Physicians used a checklist to record the reason for hospitalization, the preventability of the hospitalization, and, if preventable, a reason defining preventability, which was classified in terms of system, clinician, and patient factors. In phase 2, two physician panelists assessed preventability for each chart. When two panelists disagreed on the preventability of hospitalization, a third panelist, blind to the original assessments, rated the chart. In phase 1, residents and attending physicians rated 33% and 34% of admissions as preventable (kappa = 0.41), respectively. In phase 2, 277 (34%) of 811 readmissions were deemed preventable. Intraobserver accuracy for the assessment of preventability was 96% (kappa = 0.89). interobserver accuracy was 73% (kappa = 0.43). Hospital system factors accounted for 37% of preventable readmissions, clinician factors for 38%, and patient factors for 21%. The nine hospitals differed markedly in their profile of reasons for preventable readmissions (p = .005). CONCLUSIONS: Using a new method of determining the preventability of hospitalizations, we identified several factors that might avert hospitalizations. Focusing efforts to identify preventable hospitalizations may yield better methods for managing patients' total health care needs; however, the content of those efforts will vary by institution.

Adult↗

PubMed1992

An overview of principles for classifying brain tumors.

The purpose of this review is to clarify for the nonneuropathologist some of the confusing issues concerning the classification of brain tumors. Following a short discussion of the commonly used methods to diagnose brain tumors clinically (frozen section, light and electron microscopy, immunohistochemistry), the general principles of classifying neural tumors are presented. Grading of tumors on the basis of histological anaplasia, and the concept that tumor cells can be related to specific cytological stages of normal cellular development (cytogenetic classification) are presented. The World Health Organization system of classifying neural tumors is an attempt to develop a standardized classification scheme with as few interpretative controversies as possible, but it has required revision as new information has been gained. The major clinical and biological features of the commonest tumor groups are then discussed. It is unlikely that improvements in the classification of brain tumors will be based solely on histological information. Definitions of tumor entities that will provide more accurate prognoses and bases for effective therapy will require considerably more information at the molecular level than is currently available.

Astrocytoma↗

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↗

PubMed2025

A functional assay to classify RB1 variants of uncertain significance.

PURPOSE: The RB1 gene encodes the retinoblastoma protein (pRB) playing a major role in cell cycle control, particularly by its interaction with E2F transcription factors. Familial forms of retinoblastoma are caused by germline pathogenic variants in the RB1 gene predisposing to retinoblastoma and other tumors. By analyzing the RB1 gene in patients with retinoblastoma, we found that missense variants often remain variants of uncertain significance (VUS). METHODS: To classify RB1 VUS, we developed a functional assay evaluating their impact on the ability of pRB to inhibit the activity of the E2F1 promoter, with a luciferase reporter gene. A set of 14 pathogenic/likely pathogenic and benign/likely benign RB1 variants was used for validation. RESULTS: We tested 16 VUS detected in patients with retinoblastoma and found that 9 VUS reduced the ability of pRB to inhibit E2F1 promoter. Among them, the (RB1) c.2263T>G p.(Phe755Val) variant showed a reduced level of pRB on Western blot, suggesting a defect in pRB stability. By applying the criterion PS3_moderate of the American College of Medical Genetics and Genomics/Association for Molecular Pathology classification to this functional assay, 5 of the 9 VUS with functional impact could be classified as likely pathogenic. CONCLUSION: This functional assay can improve the molecular diagnosis of retinoblastoma predisposition by a better determination of pathogenic/likely pathogenic RB1 variants.

Humans↗

PubMed1997

A system for classifying mechanical injuries of the eye (globe). The Ocular Trauma Classification Group.

PURPOSE: To develop a classification system for mechanical injuries of the eye. METHODS: The Ocular Trauma Classification Group, a committee of 13 ophthalmologists from seven separate institutions, was organized to discuss the standardization of ocular trauma classification. To develop the classification system, the group reviewed trauma classification systems in ophthalmology and general medicine and, in detail, reports on the characteristics and outcomes of eye trauma, then established a classification system based on standard terminology and features of eye injuries at initial examination that have demonstrated prognostic significance. RESULTS: This system classifies both open-globe and closed-globe injuries according to four separate variables: type of injury, based on the mechanism of injury; grade of injury, defined by visual acuity in the injured eye at initial examination; pupil, defined as the presence or absence of a relative afferent pupillary defect in the injured eye; and zone of injury, based on the anteroposterior extent of the injury. This system is designed to be used by ophthalmologists and nonophthalmologists who care for patients or conduct research on ocular injuries. An ocular injury is classified during the initial examination or at the time of the primary surgical intervention and does not require extraordinary testing. CONCLUSIONS: This classification system will categorize ocular injuries at the time of initial examination. It is designed to promote the use of standard terminology and assessment, with applications to clinical management and research stud ies regarding eye injuries.

Adult↗

PubMed2000

Implications of physical symmetries in adaptive image classifiers.

It is demonstrated that rotational invariance and reflection symmetry of image classifiers lead to a reduction in the number of free parameters in the classifier. When used in adaptive detectors, e.g. neural networks, this may be used to decrease the number of training samples necessary to learn a given classification task, or to improve generalization of the neural network. Notably, the symmetrization of the detector does not compromise the ability to distinguish objects that break the symmetry.

Artificial Intelligence↗

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↗

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↗