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 109 records · Page 6Linked to original sources

PubMed1995

Brain maturation estimation using neural classifier.

Quantitative electroencephalographic (EEG) signal analysis has revealed itself as an important diagnostic tool in the last few years. Through the use of signal processing techniques, new quantitative representations of EEG data are obtained. To automate the diagnosis, a problem of supervised classification must be solved on these. Artificial Neural Networks provide an alternative to more traditional classifier systems for this task. The objective of this paper is to perform a comparison between several classifiers in a particular problem, the brain maturation prediction. The data preprocessing/feature extraction process and the methodology for making the comparison are described. Performance of the methods is evaluated in terms of estimated percentage of correctly classified subjects.

Adolescent↗

PubMed1993

Classifying perinatal death: experience from a regional survey.

OBJECTIVE: To examine problems encountered in classifying perinatal death using the systems proposed by Hey et al. (1986) and Cole et al. (1986). SUBJECTS: 451 deaths from a regional perinatal mortality survey of which 293 had a post mortem examination. METHODS: Documents from each death were reviewed by four assessors, one from each discipline, selected randomly from a pool of obstetricians, paediatricians, general practitioners and midwives. Each assessor classified the cause of death blind to the others. The degree of agreement between assessors was calculated for the full and shortened obstetric and fetal-neonatal classifications using the kappa statistic for inter-rater agreement. RESULTS: The kappa statistic, which is a measure of the proportion of agreement above chance, gave a value of 0.55 for the full obstetric classification and 0.58 for the full fetal and neonatal classification when all four assessors made an assignment. An assignment was omitted in 6.2%, but the kappa value of zero for these omissions suggested that this was a nonsystematic result due to random protocol violations. The grouped (shortened) classifications generated a higher kappa value of 0.62 for the nine point obstetric system and 0.67 for the six point fetal and neonatal (New Wigglesworth) system. Post mortem had little effect on agreement. The best agreement levels observed were for congenital anomaly. CONCLUSION: This survey highlighted the complexity of the 22 and 24 point classifications, the uneven distribution of deaths within their categories, and the variable levels of agreement between professionals classifying deaths, thus questioning the validity of individual maternity units of health districts generating local data in this degree of detail for comparative purposes in regional and national statistics. Grouping the original categories led to greater agreement particularly for the New Wigglesworth classification. The role of post mortems in clarifying the cause of fetal and neonatal death needs further investigation.

Cause of Death↗

PubMed1998

Using the Unger system to classify 386 long bone fractures in dogs.

A system already described by Unger and others was used to classify long bone fractures in dogs. The present paper reports experiences using the fracture classification system regarding its ease of use and the ability to analyse the data generated. Three hundred and eighty-six canine long bone fractures were classified from radiographs. Results were assessed by reviewing the medical records or by sending questionnaires to referring veterinarians. There were a few inconsistencies, particularly in classifying proximal ulnar fractures, but the system was easy to use and data retrieval was readily accomplished. Data from the system were used to compare the results of repairs of diaphyseal fractures of the radius/ulna, femur and tibia/fibula. A chi square analysis was used to determine significant differences between the outcome scores of the three fracture types. Fractures of the femoral diaphysis had a statistically poorer outcome than did diaphyseal fractures of the radius/ulna or tibia/fibula.

Animals↗

PubMed1996

Total and occupationally active life expectancies in relation to social class and marital status in men classified as healthy at 20 in Finland.

STUDY OBJECTIVE: To study differences in total life expectancy and in occupationally active life expectancy in relation to social class and marital status in men classified as healthy as young adults. DESIGN: Historical cohort study. SETTING: Finland. PARTICIPANTS: Altogether 1662 men classified as completely healthy at the time of induction to military service (mean birth year 1923), who had been selected as referents for a study of former athletes. Mean follow up time was 46 years. MEASUREMENTS: Vital status was determined by follow up through local parish data up to 1990. Mortality data were obtained from the Cause of Death bureau of the Central Statistical Office of Finland. Occurrence of work disability was assessed from nationwide disability pension register data. Mean total life expectancy and mean occupationally active life expectancy (end points disability pension or death before age 65 years) were estimated. Social class was based on the major lifetime occupation, while marital status was classified as "never married" or "ever married" at the end of follow up. MAIN RESULTS: Mean total life expectancy was highest among executives and managers (73.2 (95% confidence interval (CI): 70.3, 76.1) years), next highest in clerical (white collar) workers (72.0 (70.0, 74.1) years), and lowest in unskilled blue collar workers (63.65 (61.1, 66.2) years). Skilled workers and farmers were intermediate. For the occupationally active life expectancy estimates, a similar gradient was observed: highest for executives (61.9 (60.7, 63.1) years) and lowest for the unskilled (52.2 (50.2, 54.2) years). The ratio of occupationally active life expectancy to total life expectancy was highest for executives (85%) and lowest for farmers (81%) and unskilled workers (82%). CONCLUSIONS: The social class gradient known to exist for mortality is also present for occupational disability. Social class and marital status differences in mortality are already evident in early adulthood and continue into old age. Those with the highest life expectancy also have the largest proportion of their life span free of occupationally incapacitating disability.

Adult↗

PubMed1995

Comparison of multilayer neural network and Nearest Neighbor Classifiers for handwritten digit recognition.

The basic Nearest Neighbor Classifier (NNC) is often inefficient for classification in terms of memory space and computing time needed if all training samples are used as prototypes. These problems can be solved by reducing the number of prototypes using clustering algorithms and optimizing the prototypes using a special neural network model. In this paper, we compare the performance of the multilayer neural network and an Optimized Nearest Neighbor Classifier (ONNC) for handwritten digit recognition applications. We show that an ONNC can have the same recognition performance as an equivalent neural network classifier. The ONNC can be efficiently implemented using prototype and variable ranking, partial summation and distance triangular inequality based strategies. It requires the same memory space as, but less, training time and classification time than the neural network.

Computers↗

PubMed1996

Empirical error-confidence curves for neural network and Gaussian classifiers.

"Error-Confidence" measures the probability that the proportion of errors made by a classifier will be within epsilon of EB, the optimal (Bayes) error. Probably Almost Bayes (PAB) theory attempts to quantify how this confidence increases with the number of training samples. We investigate the relationship empirically by comparing average error versus number of training patterns (m) for linear and neural network classifiers. On Gaussian problems, the resulting EC curves demonstrate that the PAB bounds are extremely conservative. Asymptotic statistics predicts a linear relationship between the logarithms of the average error and the number of training patterns. For low Bayes error rates we found excellent agreement between the prediction and the linear discriminant performance. At higher Bayes error rates we still found a linear relationship, but with a shallower slope than the predicted-1. When the underlying true model is a three-layer network, the EC curves show a greater dependence on classifier capacity, and the linear predictions no longer seem to hold.

Bayes Theorem↗

PubMed1991

Attempts to physiologically classify human thenar motor units.

1. This study was designed to determine whether human thenar motor units can be classified into types by the same physiological criteria used for other mammalian limb motor units and to consider whether such classification is functionally relevant. 2. Contractile responses of 25 human thenar single motor units were examined when their motor axons were stimulated intraneurally at rates from 1 to 100 Hz and intermittently at 40 Hz in a conventional 2-min fatigue test. Twitch and tetanic forces were measured together with various indexes of contractile rate. 3. Twitch contraction times and subtetanic to maximum tetanic force ratios were both distributed continuously. "Sag" in tension was not evident in unfused force profiles. Thus these units could not be divided into fast and slow types by the use of traditional contractile rate criteria. 4. Most units were fatigue resistant, with force fatigue indexes (FI) ranging from 0.33 to 1.14. None could be classified as fatiguable (FI less than 0.25). Seven units (28%) fell into the fatigue-intermediate (FI = 0.25-0.75) category, whereas 18 units (72%) had FI greater than 0.75, i.e., they were fatigue-resistant units. However, these units could not be classified by conventional FI and contractile rate criteria, because fatigue-resistant and fatigue-intermediate units had similar contractile rates. 5. Additional FI were calculated to describe changes in contractile rate. During the fatigue test, units behaved in one of three ways, showing 1) little change in either force or rate; 2) contractile slowing during the contraction and relaxation phases, with little or no force loss; or 3) both force and rate reduction.(ABSTRACT TRUNCATED AT 250 WORDS)

Animals↗

PubMed1996

Exploration of the precision of classifying sudden cardiac death. Implications for the interpretation of clinical trials.

BACKGROUND: As cardiovascular clinical trials improve in sophistication and therapies target specific cardiac mechanisms of death, a more objective and precise system to identify specific cause of death is needed. Ideally, sudden cardiac death would describe patients dying of ventricular tachycardia and ventricular fibrillation. In this context, we explored the precision of current sudden death classification and implications for clinical trials. METHODS AND RESULTS: Deaths were analyzed in 834 patients who received an automatic implantable cardioverter-defibrillator (ICD). Three arrhythmia experts used a standard prospective classification system to classify deaths into accepted categories: sudden cardiac, nonsudden cardiac, and noncardiac. New aspects to this study included analysis of autopsy results and ICD interrogation for arrhythmias at the time of death. All of the patients receiving the ICD previously had documented sustained ventricular tachycardia/fibrillation or cardiac arrest. Of the 109 subsequent deaths in the 834-patient database, 17 (16%) were classified as sudden cardiac. Compared with the nonsudden cardiac and noncardiac categories, sudden cardiac death was more often identified in outpatients (59% versus 10%) and witnessed less often (41% versus 86%; both P < .001). The autopsy information contradicted and changed the clinical perception of a "sudden cardiac death" in 7 cases (myocardial infarction [n = 1], pulmonary embolism [n = 2], cerebral infarction [n = 1], ruptured thoracic [n = 1], and abdominal aortic aneurysms [n = 2]). Interpretable ICD interrogation was available in 53% of the deaths (47% unavailable: buried, programmed off, or other technical reasons). When evaluated, only 7 of 17 "sudden deaths" were associated with ICD discharges near the time of death. CONCLUSIONS: Even in a group of patients with an ICD, deaths classified as sudden cardiac frequently were not associated with ventricular tachycardia or ventricular fibrillation and were often noncardiac. It is possible to create a wide range of sudden cardiac death rates (more than fourfold) using the identical clinical database despite objective, prespecified criteria. Autopsy results frequently reveal noncardiac causes of clinical events simulating sudden cardiac death. ICD interrogation revealed that ICD discharges were often related to terminal arrhythmias incidental to the primary pathophysiological process leading to death.

Cause of Death↗

PubMed1998

The diabolo classifier

We present a new classification architecture based on autoassociative neural networks that are used to learn discriminant models of each class. The proposed architecture has several interesting properties with respect to other model-based classifiers like nearest-neighbors or radial basis functions: it has a low computational complexity and uses a compact distributed representation of the models. The classifier is also well suited for the incorporation of a priori knowledge by means of a problem-specific distance measure. In particular, we will show that tangent distance (Simard, Le Cun, & Denker, 1993) can be used to achieve transformation invariance during learning and recognition. We demonstrate the application of this classifier to optical character recognition, where it has achieved state-of-the-art results on several reference databases. Relations to other models, in particular those based on principal component analysis, are also discussed.

Journal Article↗

PubMed1989

The use of sputum cultures in the evaluation of immigrants classified as tuberculosis suspects.

Because of possible deficiencies in the evaluation, based on symptoms and chest roentgenogram review, of new immigrants classified during the visa application process as tuberculosis suspects, a prospective (cohort) and a retrospective (case control) study were done to test the usefulness of routinely obtaining sputum specimens for culture in that setting. In the prospective study, 249 consecutive classified immigrants who were considered on the basis of clinical and roentgenographic findings to have nonprogressive tuberculosis submitted at least two sputums for culture: 13 (5.2%) had at least one culture positive for M. tuberculosis. Immigrants younger than 50 yr of age and refugees from Kampuchea and Laos had a fivefold to tenfold elevated risk of having a positive sputum culture. The cost per case detected of obtaining and processing sputum cultures was estimated to be +1,996 to +2,994. In the case-control study, 37 classified immigrants evaluated from 1981 through 1986 who had sputum cultures positive for M. tuberculosis even though they fulfilled clinical and roentgenographic criteria for nonprogressive tuberculosis served as control subjects. Several demographic, clinical, and roentgenographic factors were associated with an increased risk of being culture-positive: age younger than 50 yr, a positive tuberculin test, report of a cough, and a cavitary lesion on chest roentgenogram. The history of prior receipt of antituberculosis drugs was associated with having a negative culture, including a marked dose-response effect.

Asia, Southeastern↗

PubMed1991

A comparison of taxonomic systems for classifying homeless men.

The present study compared the relative merits of two taxonomic systems for classifying homeless men. One system classified homeless men based on their past history of psychiatric disability. The other system classified individuals on the basis of their current psychiatric impairment. Both classification systems displayed significant discriminating power using a set of predictor variables that included demographic variables, childhood happiness, current life satisfaction, social support, stressful life events, and history of homelessness. Based on the percentage of correct classifications the system based on current impairment was superior to the system based on past history.

Demography↗

PubMed2026

A cfDNA fragmentomics classifier for noninvasive differentiation of benign and malignant renal masses.

Noninvasive differentiation of malignant and benign renal masses remains a major clinical challenge, particularly for radiologically indeterminate lesions. Here, we developed and validated a plasma cell-free DNA (cfDNA) fragmentomics-based machine learning classifier for renal mass characterization. The model was trained on 331 participants (171 cancer, 160 benign) and independently validated on 144 participants (73 cancer, 71 benign). Three cfDNA fragmentation features, including copy number variation (CNV), fragmentation-based methylation (FRAGMA), and nucleosome footprint (NF), derived from low-pass whole-genome sequencing, were integrated into an ensemble framework. The model achieved strong discriminative performance, with area under the curve (AUC) values of 0.956 in the training cohort and 0.946 in the validation cohort, outperforming individual feature-based models. At a predefined operating threshold corresponding to 90% sensitivity, specificity reached 0.90 and 0.87, respectively. Notably, most cancer samples exhibited low tumor fraction (TF < 3%), yet the model maintained robust performance in low-TF samples (AUCs: 0.952 and 0.941, respectively). Performance remained consistent across tumor stage, grade, and histological subtypes. The classifier also demonstrated potential clinical utility in diagnostically challenging settings, including lipid-poor angiomyolipoma and oncocytoma, with 12 of 13 oncocytoma samples correctly classified in an independent cohort. In addition, the model correctly identified 85.3% of benign masses > 4 cm, for which surgical intervention is more commonly considered, and 84.6% of malignant tumors ≤ 4 cm, for which management can be challenging. Collectively, these findings support cfDNA fragmentomics as a promising noninvasive liquid biopsy approach for renal mass evaluation and clinical decision-making.

Humans↗

PubMed1992

A neural network chromosome classifier.

We present a chromosome classifier for automated karyotyping of banded chromosomes which uses a multi-layer perception neural network. Two network configurations have been investigated. The resulting classifiers have been trained and tested on data from three different data sets covering a range of data quality. Classification results compare very favourably with those obtained using a highly optimised parametric classifier.

Chromosomes↗

PubMed2001

Naming, defining, and classifying in mental retardation.

Recent discussions about changing the term mental retardation to a different term may be considered in the broader framework of three distinct but related processes: naming (terminology), defining, and classifying. The three processes are analyzed according to their purposes and functions: In naming, a term is assigned; in defining, the term is explained; and in classifying, the group is divided into subgroups according to stated principles. The current status of each process is described, especially as represented in the 1992 AAMR manual, Mental Retardation: Definition, Classification, and Systems of Supports. We suggest three sets of guiding questions that may help evaluate proposed changes in naming, defining, or classifying.

Humans↗

PubMed2000

Classifying postures of freely moving rodents with the help of Fourier descriptors and a neural network.

A computerized method for classifying the postures of freely moving rodents is presented. The behavior of the rats was recorded on videotape by means of a camera hanging perpendicular to an open field. An automatic tracking system (10 images/sec) was used to transform the video images of postures into a binary image, thereby providing silhouettes in a computer format. The contours of these silhouettes were used for determining their characteristic features with the help of a Fourier transformation. The resulting features were classified with the help of a Kohonen network composed of 32 neurons. The four best winning neurons, rather than the usual one, were used for the classification. The resolution (11,090 distinct classes of postures), reliability (96.9%), and validity of this method were determined. With the use of the same approach, the effectiveness of this method for classifying behaviors was illustrated by analyzing grooming (247 grooming images vs. 4,950 nongrooming images). We found 15.4% false positives and 2.5% false negatives.

Animals↗

PubMed1999

Why race is differentially classified on U.S. birth and infant death certificates: an examination of two hypotheses.

Among U.S. infants who die within a year of birth, classification of race on birth and death certificates may differ. I investigate two hypotheses: (1) The race of infants of different-race parents is more likely to be differentially classified at birth and death than the race of infants of same-race parents. (2) States with a greater proportion of infant deaths of a given race are less likely to differentially classify infants of that race on birth and death certificates than states with a smaller proportion of infant deaths of that race. Using the Linked Birth/Infant Death data tape for 1983-1985, I assessed the first hypothesis by comparing rates of differential classification for infants with different-race parents and same-race parents. To assess the second hypothesis, I examined the correlations between the proportion of infant deaths of each race in each state and the proportion of infants of that race consistently classified. Differential racial classification on birth and death certificates was more than 31 times as likely with different-race than with same-race parents. The second hypothesis was confirmed for white, black, American Indian, and Japanese infants. As the U.S. population becomes more heterogeneous, attention to these methodologic issues becomes increasingly critical for the measurement and redress of differential racial health status.

Birth Certificates↗

PubMed2000

Can we classify medical data dictionaries?

Medical Data Dictionaries enable a clinical information system to maintain a controlled vocabulary, to store descriptive knowledge about terms, to map between those terms and from those terms to external classifications. They support a variety of functions in the information system, ranging from structured documentation to knowledgebased functions. This paper derives a multi-axial classification for medical data dictionaries. Dictionaries are classified along 4 axes, a vocabulary axis defining vocabulary properties, an application axis which characterises the degree of linkage between dictionary and information system, a semantic axis defining the quality of inter-term relationships and finally a language axis which classifies rules for inter-term relationships in semiotic theory. As an example two existing dictionaries are classified in the model and reference is taken to the design of future dictionaries.

Artificial Intelligence↗

PubMed1986

Within- and between-person variation in dietary surveys: number of days needed to classify individuals.

The variation from day to day, between individuals and within individuals, in the consumption of energy and a variety of nutrients is presented for two groups of executive grade civil servants aged 40-49, numbering 83 and 68 and working in London in 1970-1971, and for 98 drivers and 83 conductors aged 30-67 of London's double decker buses in 1958-1967, a total of 332 men. Each man weighed and recorded his food for at least a week. The reliability with which these men could be classified into extreme thirds of the distribution of individual consumption of the various 'nutrients' or foods on the basis of a single day's or of several days' measurement was calculated. The number of days of measurement required to achieve a given reliability of classification into extreme thirds of the distribution was also estimated. The key is the ratio of the 'between-person' to the 'within-person' variance for the particular nutrient. A diagram is presented of how this ratio is related to the number of days of survey required for a given reliability. Nutrients fall into three main groups--those consumed in relatively large amounts each day (eg protein, fat), those found in moderate amounts in many or most foods but in very large quantities in a few foods (eg dietary cholesterol, calcium), and those which may not be consumed at all by some people but are taken in large quantities by others (eg alcohol). The number of days of survey required for 80 per cent reliable classification of individuals varies from 2 or 3 days for some nutrients like sugar or total carbohydrates to 2 or 3 weeks for others like dietary cholesterol or the ratio of polyunsaturated fatty acids to saturated fatty acids. One day's survey classified no nutrients with 80 per cent reliability in our data, whereas one week's survey classified most nutrients with this reliability or better, although for a few the figure is lower. The precision of a week's survey is also shown in absolute quantities such as grams as distinct from thirds of the distribution. The relevance of these observations to the use of the results of 24-hour surveys in population surveys and correlation and regression analysis is discussed.

Adult↗