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 613 records · Page 34Linked to original sources
PubMed1987

How to classify Raynaud's phenomenon. Long-term follow-up study of 73 cases.

Raynaud's phenomenon without an underlying cause was diagnosed in 96 consecutive patients in 1978 to 1979. Seventy-three patients were available for long-term follow-up. They were classified on initial evaluation as having primary Raynaud's phenomenon (49 patients) when no clinical, laboratory, or serologic abnormality was detected, and as having suspected secondary Raynaud's phenomenon when at least one finding was abnormal. Re-evaluation was performed in 1984 to 1985 after an average duration of Raynaud's phenomenon of 14.9 +/- 12 years. The average duration of the follow-up from initial to final evaluation was 4.7 +/- 1 years. On final evaluation, none of the 49 patients with an initial diagnosis of primary Raynaud's phenomenon had evidence of secondary Raynaud's phenomenon, whereas 14 of the 24 patients with suspected secondary Raynaud's phenomenon had a definite diagnosis. Among them, there were 13 connective tissue diseases. The study proved that Raynaud's phenomenon without an underlying cause must be followed up for more than two years, contrary to what was recommended previously, before it can be rightly diagnosed as primary Raynaud's phenomenon. Moreover, the results suggested that, in order to distinguish early primary Raynaud's phenomenon from suspected secondary Raynaud's phenomenon, a simple and noninvasive evaluation is sufficient. In this study, the evaluation included history and clinical examination, tests for antinuclear antibodies, radiography of hands, chest roentgenography, and nailfold capillary microscopy.

Adult↗
PubMed1982

On the classification of single evoked potentials using a quadratic classifier.

It has been shown that using a computationally simple technique it is possible to classify single event-related potentials associated with upper and lower visual field stimulation with a high degree of accuracy. A flow chart of the algorithm and the FORTRAN 77 computer program required to perform the classification just described are included in the Appendix. The program as given in the Appendix is for a 2 class problem only. Memory limitations (33000 bytes 16-bit words) per user in the time-shared system utilized limits the amount of data that may be in core at any one time. A 2 class, 5 step problem takes approximately 5 min in a PDP ll/45 System (Digital Equipment Corp.).

Adult↗
PubMed1990

Fuzzy multi-level classifier for medical applications.

In this paper a fuzzy pattern recognition model is described, which is a tool to handle problems with noncrisp and multi-class membership of the objects. It is oriented to medical diagnostics, where the patients suffer from more than one disease in different degrees. Fuzzy pattern recognition is supposed to fit medical diagnostic problems better than conventional pattern recognition. The design of a multi-level fuzzy decision scheme is considered in order to derive high performance, taking into account expert logic and human experience. Two main topics are discussed--the criterion for evaluation of classification accuracy and the training rule. The implementation of fuzzy multi-level classifier is illustrated with real clinical data.

Aerospace Medicine↗
PubMed1994

Discrimination between demented patients and normals based on topographic EEG slow wave activity: comparison between z statistics, discriminant analysis and artificial neural network classifiers.

The topographic distributions of absolute delta and theta powers were used to classify demented patients and normals by means of z statistics, discriminant analysis and artificial neural networks (NN). The data were taken from two psychopharmacological studies in mildly to moderately demented patients (111 and 96 patients for studies I and II, respectively) and from 56 normal healthy controls. All patients were diagnosed according to DSM-III criteria and were free of medication for at least 2 weeks. The NN used was a strictly layered feed-forward network with complete connections. The z-transformed absolute power values in the combined delta and theta frequency range at 17 electrodes, recorded in a 3 min vigilance-controlled EEG with eyes closed, were used as input. After having trained the NN successfully by backpropagating of errors, the generalization test with independent data results in a classification performance of 90% determined by "relative operating characteristic" analysis. The NN out-performed z statistics and discriminant analysis. This high percentage of correct classifications may justify the development of further application of NNs based on topographic EEG data.

Aged↗
PubMed1980

Protein signatures--a novel way to classify proteins.

A method is developed to classify proteins by establishing their familial identity based on the presence and the absence of characteristic signature dipeptides. It is hoped that this method will lead to the establishment of a theoretical basis for the determination of interrelationships among proteins.

Amino Acid Sequence↗
PubMed1996

The core of computer based patient records in family practice: episodes of care classified with ICPC.

A central element in the definition of primary care is that primary care clinicians address the large majority of personal health care needs of their patients. As a consequence, they should document data on these health care needs reliably and continuously. To establish whether this occurs, the episode of care is the most appropriate unit of assessment: a health problem from its first encounter with a health care provider until the completion of the last encounter for it. An episode of care is distinguished from episodes of disease and of illness. The episode of care as an epidemiological concept for the calculation of rates has evolved into a central element of a computer based record. Episode oriented data classified with the International Classification of Primary Care (ICPC), and specified with ICD-10 as a nomenclature are especially suitable as the core of a generic patient record in family practice. ICPC has been available to the family medicine community for well over a decade as the main ordering principle of its domain. The basic structure of an encounter (within the string of encounters which together form an episode of care) distinguishes reasons for encounter, diagnoses and diagnostic and therapeutic interventions. In this article, a more refined structure of encounters is proposed for a more precise documentation of episodes of care in a computer based patient record. The conversion structure between ICPC and ICD-10 allows both a high level of specificity in the patient's problem list and optimal communication with specialists who contribute to the episodes of care for which the documentation is the primary care provider's responsibility.

Episode of Care↗
PubMed1994

Classifying communicative acts in children's interactions.

Describing speakers' repertoires of communicative intents and rules for expressing those intents is crucial to any complete description of the language capacity. Many different systems for classifying speakers' communicative intents have been developed and used in research analyzing both the acquisition of speech acts and the nature of the communicative deficits shown by various language-impaired populations. We argue, though, that these systems have typically been limited in scope, in applicability across the full developmental range, or in their theoretical foundations. The criteria for an adequate system for analyzing communicative intents are discussed, and a system proposed which meets those criteria.

Child↗
PubMed1985

A method to classify airborne chemicals which alter the normal ventilatory response induced by CO2.

Guinea pigs inhaling 10% CO2, 19% O2, and 71 N2 increase their tidal volume (VT) by a factor of 2 to 3 and their respiratory frequency (f) by a factor of 1.2 to 1.5 above their normal values while breathing room air. While exposing guinea pigs to 10% CO2, a variety of aerosols can be added to determine how they modify the normal ventilatory response to this agent. Aerosols of carbamylcholine, serotonin, or propranolol all decreased VT of guinea pigs when added to 10% CO2. We propose here that chemicals evoking reductions in tidal volume can be classified into two groups based on the set of concurrent respiratory responses. Those chemicals evoking "obstruction," not only reduced VT but also decreased (f), increased resistance to airflow in conducting airways, and interrupted airflow. The prototype of this family would be carbamylcholine. The second group of chemicals evoked what is described as "reflex restriction." These agents reduced VT but increased f and lowered resistance to airflow. Propranolol would be the prototype for this family. Serotonin, however, evoked both types of response patterns which were time dependent. At the beginning of exposure, obstruction was prevalent while at the end of a 30-min exposure, reflex restriction was prevalent.

Aerosols↗
PubMed1993

A binary (Bethesda) system for classifying cervical cancer precursors: criteria, reproducibility, and viral correlates.

This study of cervical squamous precursors addressed the consistency with which pathologists could agree on diagnosis using a Bethesda system and the degree to which the classification system discriminated "high-risk" human papillomavirus (HPV) types. Four pathologists independently assessed biopsies of 75 squamous lesions; all contained HPV DNA amplified from archival fixed tissue with polymerase chain reaction (PCR) and typed by restriction digestion of the PCR product. Lesions were categorized as low or high grade using published criteria. In independently performed histologic evaluations a majority (three or more) of observers agreed on the classification of 63 of the 75 cases (84%) with good to very good interobserver (kappa values, 0.43 to 0.63), and fair to excellent intraobserver (kappa values, 0.32 to 0.83) agreement. A majority of the observers classified as high grade 15 of 17 (88%) HPV 16-positive lesions (P < .002), but only 15 of 21 (71%) lesions associated with other high-risk HPV types 18, 31, 35, and 39 (P = .089). Concurrence among observers also varied with HPV type; majority agreement between three or more observers was present for 100% and 94%, respectively, for lesions associated with HPV 6/11 and HPV 16 versus 82% and 76% for lesions associated with HPV 18/31/35/39 and other HPV types. A binary system for grading cervical precursor lesions was applied with good reproducibility among pathologists, and segregated as high-grade virtually all lesions associated with the prototype high-risk HPV (HPV 16). Conversely, other presumed high-risk HPV types, particularly type HPV 18, were not distinguished by this grading scheme and were segregated frequently with low-grade lesions. This finding suggests that variables other than HPV type alone will influence lesion grade. Resolution of these variables will determine whether lesion grade is a more potent biologic parameter than HPV type.

Female↗
PubMed1988

In vitro fertilization and cleavage capability of bovine follicular oocytes classified by cumulus cells and matured in vitro.

Bovine oocytes were collected from ovaries obtained from an abattoir. They were classified according to the character of the cumulus cells using a stereomicroscope, and cultured in 25 mM Hepes buffered Tissue Culture Medium 199 supplemented with 10% fetal calf serum at 39 degrees C and inseminated by capacitated sperm. Maturation rates of Class A oocytes, with compact, dense cumulus cells; Class B, partially naked oocytes with thin cumulus layers or small remnants of cumulus cells and Class C, naked oocytes were 97.4% (38/39), 89.8% (106/118) and 52.9% (45/85), respectively. The fertilization rates for the three classes were 86.8%, 85.8% and 53.3%, respectively. The naked oocytes had a significantly lower fertilization rate than oocytes of the other two classes. Significantly more Class A oocytes cleaved (63.7%, 232/364) than those of Class B (29.5%, 36/122) and Class C (17.7%, 28/158).

Journal Article↗
PubMed1990

Phenotypic and genotypic analysis of large-cell lymphomas, formerly classified as true histiocytic lymphoma: identification of an unusual group of tumors.

A group of 12 large-cell lymphomas, seen in the period January 1983 to January 1985 and then tentatively classified as histiocytic sarcomas/true histiocytic lymphomas (i.e. non B-, non T-cell lymphomas, with expression of some histiocytic markers) were restudied phenotypically with a much more extensive range of monoclonal and polyclonal antibodies. They were also genotypically analyzed with respect to rearrangements of genes coding for the immunoglobulin (Ig) heavy and light chains and the gamma and beta chains of the T-cell receptor (TCR). The combined results suggest that these "histiocytic sarcomas" represent a heterogeneous group of large cell lymphomas often with unexpected rearrangements (or lack of rearrangements) of either Ig and TCR genes and phenotypically with coexpression of "histiocytic" and B- or T-cell markers. Such coexpression may be regarded as a warning signal to expect unusual genotype. True histiocytic tumours apparently do exist, but are rare (one case in this study), and their diagnosis is very difficult.

Antigens, Differentiation↗
PubMed1994

Regrowth resistance in leukemia and lymphoma: the need for a new system to classify treatment failure and for new approaches to treatment.

Treatment failure in drug sensitive malignancies is a complex phenomenon resulting from both drug resistance and from the rapid regrowth of malignant cells ('regrowth resistance'). Attempts to overcome regrowth resistance during the treatment of the aggressive lymphomas by increasing the frequency of cytotoxic therapy appears to have failed. An alternative approach of significant potential would be to administer biologically active agents to directly slow the regrowth of neoplastic cells between courses of full dose cytotoxic therapy. To facilitate this approach a new system for classifying treatment failure in the leukemias and lymphomas is needed so that the extent of regrowth resistance and the effects of treatment on regrowth resistance can be directly assessed. Accordingly, a new classification system is proposed.

Antineoplastic Combined Chemotherapy Protocols↗
PubMed1979

Further validation of a questionnaire method for classifying depressive illness.

A total of 367 patients admitted to a psychiatric facility completed the LPD questionnaire. By application a decision rule to their responses, they were classified as 'non-endogenous depression', 'endogenous depression' and 'non-depressive syndrome'. This classification was found to be associated significantly with their categorization on the basis of clinical diagnosis. The findings suggest that this method of classification on the basis of responses to the LPD may have a useful research and clinical role.

Adult↗
PubMed1983

Classifying cancer of the lip: an epidemiological perspective.

A review of papers related to oral cancer reveals some non-uniformity in the classification of cancer of the lip. This paper examines the incidence of lip cancer in England and Wales using age-standardized and age- and sex-specific rates, and relates the results to those for other sites of oral cancer. There is a falling trend in age-adjusted incidence rates for lip cancer but not for intra-oral cancers, and the age-specific incidence shows a plateau effect for lip cancer after about 75 yr of age, whereas the incidence rate continues to rise throughout life for intra-oral cancers. These differences underline the importance of classifying cancer of the lip separately from other oral cancers.

Age Factors↗
PubMed1994

Biological markers as classifiers for depression: a multivariate study.

1. Delta TSH, REM latency, 4 pm and 11 pm post-dexamethasone cortisol values were determined after a wash-out period in a group of 74 non-selected depressed patients who were diagnosed (according to RDC with the SADS) as follows: 46 definite and 10 probable MD, 4 minor and 14 intermittent depression. 2. These biological variables, as well as gender, age and basal TSH were introduced in a principal component analysis. The four first PC scores explaining up to 77% of the data set were further calculated for each patients and used in a cluster analysis. A three clusters solution was retained. 3. DST escape and increased TSH response to TRH each identified subgroups of depressed patients. Conversely, blunted TSH response or REM latency were inefficient to classify patients. 4. Thus, HPA hyperactivity characterized CL-I patients (n = 29). These were more severely depressed, displayed more endogenous features and were reported as being more anxious. 5. Increased TSH response to TRH identified CL-III, exclusively composed of female patients (n = 10) that displayed more apparent sadness and tended to be older. 6. In CL-II, the usual sex-ratio for depressive illness was reversed and patients (n = 35) exhibited the least HPA axis disturbances and the same rate of blunted TSH response than in CL-I. They were also less severely depressed, displayed less endogenous characteristics and were rated as more mood reactive. 7. These results suggest heterogeneity in biological disturbances in depression and further stress the importance for controlling age, gender and severity of illness in studies investigating biological markers in depression.

Adult↗
PubMed1984

Negative staining characteristics of arrays of mitochondrial pore protein: use of correspondence analysis to classify different staining patterns.

Fourier-filtered images of negatively stained arrays of mitochondrial pore protein have been classified by correspondence analysis of their diffraction patterns. The most significant component of interpattern variation is an isotropic shift in reflection intensities between high- and low-order reflections. This corresponds in the images to the presence or absence of high resolution detail (stain minima). Experimentally the loss of detail in images correlates with the use of highly dissociated heavy metal salts as negative stains. It is proposed that such stains yield poorer negative-contrast images due to electrostatic binding of heavy-metal complex ions to fixed charge groups on the protein. Results with surface-modified protein arrays are consistent with this hypothesis.

Crystallography↗
PubMedDate not supplied

Classifying COAs with three variations of the CAST: classification rates, stability, and gender differences.

The Children of Alcoholics Screening Test (CAST) was administered to a sample of young adolescents as sixth graders and again one year later. Psychometric properties of the full CAST and a shortened version (CAST-6) were examined, and three different rules for classifying COAs were analyzed. The CAST was found to demonstrate adequate internal consistency and test-retest reliability. When examined as an entire group, the vast majority of respondents maintained the same classification (COA or NCOA) from the first to the second administration. For boys, however, CAST scores and the proportion who were self-identified as COAs declined significantly. Classification rates based on the full CAST and on the shortened version were similar. The use of two confirmatory items, "Ever think your father (mother) was an alcoholic?" however, substantially reduced the percentage of self-identified COAs. Finally, girls were dramatically more likely than boys to endorse items suggesting parental alcoholism, and they were also more likely to self-identify as COAs.

Adolescent↗
PubMed1985

Multifactorial pathogenesis: ought we to classify disease or treat the individual's causes of disease?

Added to the uniqueness of most of us imparted by HLA, our individual differences in the expression of other genetic traits, foetal period steroid imprints on brain and other functions, and regulators shared by body and mind indicate that each one of us (except most monozygotic twins) is born as a unique individual whole (I). Mechanisms suspected to be contributing ones in classified synovitides appear to correspond to individually exaggerated or depressed modes of response by physiological mechanisms linked to our unique individual wholes (II). If we upgrade the importance of influences of combinations of 'contributing' mechanisms, the importance of the alleged unknown fundamental causes of these diseases diminishes (III). This broad interpretation of 'multifactorial pathogenesis' can probably be applied to many common types of disease (IV), implying that disease classifications may poorly reflect the individual's causes of disease (V). There is reason to challenge modern concepts about disease (VI).

Arthritis, Rheumatoid↗