SEARCH · PubMed Health

Results for “Classification Algorithms”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 1,657 records · Page 92Linked to original sources

PubMed2006

[Post-stroke-depression. Algorithm for a standardized diagnostic approach in clinical routine].

Depression is a frequent and important complication after stroke. The occurrence of a post-stroke-depression (PSD) has a significant impact on the functional and cognitive deficit, on mortality and on quality of life after stroke. In contrast to the clinical importance, PSD is often ignored in routine management of stroke patients and remains often untreated if diagnosed. The diagnostic uncertainty is aggravated by the lack of appropriate diagnostic criteria for PSD in the International Classification of Diseases (ICD-10) used in Germany. For the first time, we present an algorithm, which allows for a standardized examination of stroke patients on the presence of PSD. All stroke patients should be examined initially by a short and simple screening tool and are subjected to more extensive procedures only if PSD is assumed based on the screening result. Furthermore potentials and limitations to convert the diagnosis of PSD into a diagnostic related group (DRG) that is used to calculate the hospital's reimbursement are highlighted. Finally pharmacological treatment options for PSD are discussed.

Algorithms↗

PubMed1993

Model-based rhythm analysis of the ECG. Evaluation of a prototype implementation.

Current computer algorithms that interpret cardiac rhythms based solely on the surface electrocardiogram are limited, yet offer many benefits to health care. To address the limitations, novel computer algorithms for the automatic diagnosis of complex cardiac rhythms based solely on the surface electrocardiogram are presented. Using the hypothesize-and-test paradigm, a physiologic model of the cardiac conduction system and production rule-based knowledge are combined to reason about the time- and space-varying characteristics of complex heart rhythms. In addition, an evaluation of a prototype implementation of the algorithms is presented. A database of the time of onset, width, and shape classifications of each P wave, QRS complex, and T wave from 59 electrocardiographic strips was developed from an introductory textbook by hand-annotation using calipers. The database was not used in the development of the prototype. The prototype's diagnoses were reviewed by a clinical cardiac electrophysiologist who was not involved in the development process. Pair-wise comparisons among the prototype, textbook, and cardiac electrophysiologist, assuming either the textbook or electrophysiologist as the gold standard, were performed. The specific comparisons performed were prototype versus textbook, electrophysiologist versus textbook, prototype versus electrophysiologist, and textbook versus electrophysiologist. For all diagnostic categories, sensitivities of 88.0%, 97.2%, 78.6%, and 82.1%, respectively, and specificities of 99.2%, 98.5%, 99.7%, and 99.8%, respectively, were attained. When accounting for design and implementation limitations of the prototype, sensitivities of 93.0%, 98.5%, 89.1%, and 92.7%, respectively, and specificities of 99.4%, 99.2%, 99.6%, and 99.8%, respectively, were attained. The results indicate that these algorithms offer clinical advantages over currently available arrhythmia analysis systems.

Algorithms↗

PubMed1993

Use of two data sources to estimate odds ratios in case-control studies.

Information bias is among the most serious and common problems in epidemiology. Approaches have been developed to reduce information bias by correcting for known amounts of misclassification. Unfortunately, in most studies, the extent of exposure misclassification cannot be easily estimated. We discuss the application to case-control studies of an approach originally proposed by Hui and Walter in 1980 to estimate the sensitivity and specificity of two independent classification schemes (Hui SL, Walter SD. Biometrics 1980;36:167-171). In this paper, we propose using the EM algorithm to provide a simple numeric technique for implementing their method that seems to converge for most real-world data. Our approach allows inclusion of a measure of non-independence of the two classification schemes, and we assess the influence of non-independence on the odds ratio. Finally, we provide a simple variance estimate for the odds ratio based on the delta method and maximum likelihood theory. We exemplify our results and method with data from a case-control study of sudden infant death syndrome in which data on some variables were obtained from both maternal interviews and medical records.

Algorithms↗

PubMed1996

Recognition-by-parts: a computational approach to human learning and generalization of shapes.

In this paper human pattern recognition is modeled in terms of how human observers learn to describe patterns in terms of their perceived parts, their unary (part) and binary (relational) attributes and the way in which such attribute states "evidence' different classes of shapes. This approach, originally developed in the area of computer vision, is concerned with algorithms which enable the learning of shape descriptions from examples and the classification of new data (generalization) efficiently and accurately. An object in such an "evidence-based' system is represented by a set of rules, where each rule provides a certain amount of evidence for each object class in the database. The accumulated class evidence over all activated rules can then be used to determine the classification probability. We have examined how well this model reflects human perception by training observers to classify compound Gabor patterns and then testing them with versions of such patterns which were segmented (gray-level transformed) versions of the original training set. If the observers were to construct rules to define each pattern class in terms of perceived parts and their relations, then it should be expected that classification performance would generalize to these new patterns from the original set. Results confirm this hypothesis and the specific feature extraction, learning and rule generation model used to predict performance.

Attention↗

PubMed2004

A comparative study of fuzzy classification methods on breast cancer data.

In this paper, we examine the performance of four fuzzy rule generation methods on Wisconsin breast cancer data. The first method generates fuzzy if-then rules using the mean and the standard deviation of attribute values with 92.2% correct classification rate. The second approach generates fuzzy if-then rules using the histogram of attributes values with 86.7% correct classification rate. The third procedure generates fuzzy if-then rules with certainty of each attribute into homogeneous fuzzy sets with 99.73% correct classification rate. In the fourth approach, only overlapping areas are partitioned with 62.57% correct classification rate. The first two approaches generate a single fuzzy if-then rule for each class by specifying the membership function of each antecedent fuzzy set using the information about attribute values of training patterns. The other two approaches are based on fuzzy grids with homogeneous fuzzy partitions of each attribute. The performance of each approach is evaluated on breast cancer data sets. Simulation results show that the simple grid approach has a high classification rate of 99.73%.

Algorithms↗

PubMed2006

The application of wavelet and feature vectors to ECG signals.

The Electrocardiogram (ECG) is one of the most commonly known biological signals. Traditionally ECG recordings are analysed in the time-domain by skilled physicians. However, pathological conditions may not always be obvious in the original time-domain signal. Fourier analysis provides frequency information but has the disadvantage that time characteristics will be lost. Wavelet analysis, which provides both time and frequency information, can overcome this limitation. Here a new method, the combination of wavelet analysis and feature vectors, is applied with the intent to investigate its suitability as a diagnostic tool. ECG signals with normal and abnormal beats were examined. There were two stages in analysing ECG signals: feature extraction and feature classification. To extract features from ECG signals, wavelet decomposition was first applied and feature vectors of normalised energy and entropy were constructed. These feature vectors were used to classify signals. The results showed that normal beats and abnormal beats composed different clusters in most cases. In conclusion, the combination of wavelet transform and feature vectors has shown potential in detecting abnormalities in an ECG recording. It was also found that normalised energy and entropy are features, which are suitable for classification of ECG signals.

Algorithms↗

PubMed1997

[Widening mediastinum after blunt thoracic trauma: an unexpected differential diagnosis].

We report our experience concerning a young, white, healthy woman who had a typical blunt chest injury caused by a severe car accident. We had to evaluate and differentiate the initial roentgenographic post-traumatic mediastinal enlargement in order definitely to exclude a suspected covered rupture of the thoracic aorta or the heart caused by this high-velocity deceleration trauma. The difficulties encountered are critically discussed with regard to the unexpected primary thymoma that was diagnosed postoperatively. The diagnostic algorithm in blunt chest injury is also discussed. The controversy about the classification and management options of primary thymic tumors is also presented.

Adult↗

PubMed2006

Unified approach for multiple sclerosis lesion segmentation on brain MRI.

The presence of large number of false lesion classification on segmented brain MR images is a major problem in the accurate determination of lesion volumes in multiple sclerosis (MS) brains. In order to minimize the false lesion classifications, a strategy that combines parametric and nonparametric techniques is developed and implemented. This approach uses the information from the proton density (PD)- and T2-weighted and fluid attenuation inversion recovery (FLAIR) images. This strategy involves CSF and lesion classification using the Parzen window classifier. Image processing, morphological operations, and ratio maps of PD- and T2-weighted images are used for minimizing false positives. Contextual information is exploited for minimizing the false negative lesion classifications using hidden Markov random field-expectation maximization (HMRF-EM) algorithm. Lesions are delineated using fuzzy connectivity. The performance of this algorithm is quantitatively evaluated on 23 MS patients. Similarity index, percentages of over, under, and correct estimations of lesions are computed by spatially comparing the results of present procedure with expert manual segmentation. The automated processing scheme detected 80% of the manually segmented lesions in the case of low lesion load and 93% of the lesions in those cases with high lesion load.

Adult↗

PubMed1990

Automatic classification and analysis of microneurographic spike data using a PC/AT.

Using a standard PC-AT with a commercial analog data interface a system was designed which supports microneurographic experiments and which may also be used for other types of extracellular spike recordings. The signal is sampled on-line at 25 kHz and a spike is detected if the signal passes a certain threshold. The spikes are displayed on the screen and stored on disk. A second on-line mode records the responses of the examined unit to electrical stimulations, which are used to identify the type of fibre and to test the subsequent spike classification. The spikes are classified off-line using a template matching algorithm, which has unsupervised learning and discrimination phases. The results are displayed in a time-frequency plot and may be checked with the responses to electrical stimulations. Artifacts from EMG and other electrical fields are reliably sorted out. In recordings, which include more than one unit, their spikes are discriminated with a low error rate.

Action Potentials↗

PubMed1990

Development of a computer program classifying rat sleep stages.

We developed a simple and precise program for the on-line judgement of the sleep stages of four rats simultaneously for an unlimited period, using a commercially available general purpose signal processor (NEC-Sanei 7T17; 32-bit, 5 MHz, 4 Mbyte, 1 Mbyte 1 floppy disc drive). EEG and EMG were recorded with an 8-channel polygraph (NEC-Sanei, System 380) through electrodes chronically implanted into the brain. The signals were A/D converted every ms and integrated for 2760 ms after full-wave rectification, and the subsequent 2240 ms was used for calculation and further analysis. All data were handled with this 5000 ms as the minimum unit. Then 3 sleep stages, i.e., waking, slow-wave sleep, and REM sleep, were determined by a template matching method from the relative amplitudes and durations of the integrated EEG, EMG and EMG surge data based on algorithms of standard visual amplitude analysis criteria for the sleep-stage classification. An agreement matrix was constructed between the data scored by the visual and by the automatic analysis, and the agreement value was satisfactory, although slight variability was seen in the REM sleep-stage determination. This result indicated that EEG and EMG data analysis is appropriate for researching the circadian rhythmic mechanism of the sleep-wake cycle.

Animals↗

PubMed2006

Minimal emotional dysfunctions (MED) in personality disorders.

The concept of minimal emotional dysfunctions (MED) refers to traditional psychopathology in order to describe, classify, and understand personality disorders. Emotional dysfunctions encompass disorders of affect predominance, production, expression, experience, modulation, and regulation. MED can explain the dimensional nature of personality disorders, their multidimensionality and problems with categorical classifications. It can stimulate research on the etiology of personality disorders in reference to modern developmental brain research and trauma psychology. It can guide new developments in pharmacotherapy and psychotherapy. It is suggested to focus on MED in future developments of the description and classification of personality disorders.

Affective Symptoms↗

PubMed2004

New ICD-10 version of the Charlson comorbidity index predicted in-hospital mortality.

BACKGROUND AND OBJECTIVE: The ICD-9-CM adaptation of the Charlson comorbidity score has been a valuable resource for health services researchers. With the transition into ICD-10 coding worldwide, an ICD-10 version of the Deyo adaptation was developed and validated using population-based hospital data from Victoria, Australia. METHODS: The algorithm was translated from ICD-9-CM into ICD-10-AM (Australian modification) in a multistep process. After a mapping algorithm was used to develop an initial translation, these codes were manually examined by the coding experts and a general physician for face validity. Because the ICD-10 system is country specific, our goal was to keep many of the translated code at the three-digit level for generalizability of the new index. RESULTS: There appears to be little difference in the distribution of the Charlson Index score between the two versions. A strong association between increasing index scores and mortality exists: the area under the ROC curve is 0.865 for the last year using the ICD-9-CM version and remains high, at 0.855, for the ICD-10 version. CONCLUSION: This work represents the first rigorous adaptation of the Charlson comorbidity index for use with ICD-10 data. In comparison with a well-established ICD-9-CM coding algorithm, it yields closely similar prevalence and prognosis information by comorbidity category.

Algorithms↗

PubMed2006

Methodology of the thyroid gland disease decision-making using profiling in steroid hormone pathway.

To find out the genetic factors of outbreak of thyroid gland disease, we developed the thyroid gland decision-making system, which processes the metabolic profile in steroid hormone map using a statistical method. Metabolic profile is a measured data of lots of mixed materials that includes not only known metabolites, but also unknown ones, which is estimated to have an influence on the thyroid gland disease. Therefore, to develop thyroid gland disease decision-making system, analyzing metabolic profile containing multi-materials would be useful for diagnosing thyroid gland disease. Because experimental values used for system construction are area values for the retention time, the observations are preprocessed through variable transition and t-test to use the area values concurrently and the highly correlated materials are estimated by principal component analysis. The thyroid gland decision-making system developed through the logistic regression is an excellent system demonstrating 98.7% accuracy in the classification table.

Algorithms↗

PubMed2002

Evolutionary psychiatry. Adaptationist and nonadaptationist conceptualizations.

Darwin's theory of evolution, and in particular one of its mechanisms, natural selection, is being used as the explanatory cornerstone of many unsolved problems in human biology and human affairs. Psychiatry is an example of that. Darwinian psychiatry's main proponents endorse the adaptationist program to carry out their project to implement an evolutionary psychiatry. The adaptationist program is an attempt to view all evolutionary novelties as adaptations, i.e., classically, features that favour survival and/or reproduction. This position is definitely teleological, and anthropomorphism plays a central role in its construction. This paper takes issue with the adaptationist approach. We argue that organism-environment interactions are bidirectional processes. Hence, as a result of the fact that "a surprisingly large amount of the environment, which affects natural selection on an animal is the more or less direct result of the animals own behavior" [Waddington, C.H., 1976. Evolution of the subhuman world. In: Jantsch, E., Waddington, C.H. (Eds.), Evolution of Consciousness. London, UK, pp. 11-23], a more appropriate term to describe these interactions appears to be construction rather than adaptation alone [Lewontin, R., 2000. The triple helix: gene organism and environment. Harvard Univ. Press]. We present factual anatomical, physiological and clinical data critical of the platonic Kraepelinean classification of mental diseases, and claim that this classification is contrary to modern ideas on the evolution of nervous systems. We argue against the view of mainstream evolutionary psychiatrists that mental diseases are adaptations. We do so on two accounts. One is methodological; authors in this position do not ask whether every disease has evolutionary causes, but assume this in order to explain all diseases in such terms. The other mistake is biological; it is their belief that adaptation is the driving force of evolution while in fact it is just an outcome of evolution. The current status of the controversy between cognitive versus emotional experiences as essentially independent is reviewed, and evidence is presented, that they cannot be considered platonic, categorically independent functions of CNSs. These data, taken together, plus arguments derived from the high degree of plasticity of nervous systems, lead us to suggest a different approach to classification of mental diseases.

Adaptation, Physiological↗

PubMed2002

The EQ-5D and the Health Utilities Index for permanent sequelae after meningitis: a head-to-head comparison.

Framed in a study on the cost-effectiveness of different diagnostic strategies regarding children with meningeal signs, this study evaluated the quality weights for permanent sequelae after childhood bacterial meningitis obtained with two different classification instruments: the EQ-5D, and Health Utilities Index (HUI). A panel of 28 pediatricians classified seven standardized descriptions of patients with permanent sequelae after bacterial meningitis according to the EQ-5D and HUI classification system. Quality weights for each classification were calculated using the EQ-5D and HUI standard scoring algorithms. HUI Mark 3 quality weights were substantially lower than the EQ-5D for all descriptions (mean difference 0.11; 95% CI: 0.08-0.14). Mean Kendall W for agreement of the ranking order between EQ-5D and HUI Mark 3 was 0.90. The EQ-5D and HUI resulted in different absolute quality weights, in particular for states associated with "deafness" and "mental retardation." Due to their performance differences, the HUI may be preferable to EQ-5D in studies focussed on "sensation" (hearing, vision, speech) or "cognition." These differences proved not to be relevant in the present cost-utility study of diagnostic strategies to rule out bacterial meningitis, as such consequences were at the distal end of the decision tree. This may be different in a cost-utility analysis of therapeutic strategies. Hence, sensitivity analysis to quality weights is recommended.

Adult↗

PubMed2006

Comprehensive analysis of microRNA expression patterns in hepatocellular carcinoma and non-tumorous tissues.

MicroRNAs (miRNAs) are a non-coding family of genes involved in post-transcriptional gene regulation. These transcripts are associated with cell proliferation, cell differentiation, cell death and carcinogenesis. We analysed the miRNA expression profiles in 25 pairs of hepatocellular carcinoma (HCC) and adjacent non-tumorous tissue (NT) and nine additional chronic hepatitis (CH) specimens using a human miRNA microarray. Targets and references samples were co-hybridized to a microarray containing whole human mature and precursor miRNA sequences. Whereas three miRNAs exhibited higher expression in the HCC samples than that in the NT samples, five miRNAs demonstrated lower expression in the HCC samples than in the NT samples (P<0.0001). Classification of samples as HCC or NT by using support vector machine algorithms based on these data provided an overall prediction accuracy of 97.8% (45/46). In addition, the expression levels of four miRNAs were inversely correlated with the degree of HCC differentiation (P<0.01). A comparison of CH and liver cirrhosis samples revealed significantly different pattern of miRNA expression (P<0.01). There were no differences, however, between hepatitis B-positive and hepatitis C-positive samples. This information may help clarify the molecular mechanisms involved in the progression of liver disease, potentially serving as a diagnostic tool of HCC.

Adult↗

PubMed2001

The utility of serology in diagnosing candidosis in non-neutropenic critically ill patients.

This study was carried out to evaluate the utility of serological tests in the diagnosis of candidal infections in non-neutropenic critically ill patients. A prospective study was carried out in a 10-bed general intensive care unit; all patients with at least one organic sample with Candida spp. were included. A therapeutic-diagnostic algorithm was designed, and patients were treated or not, according to a classification. Blood samples were taken, and serological tests included: antigenaemia detection using two different commercial latex kits (Cand-Tec and Pastorex) and antibody detection by indirect haemagglutination (IHA) and indirect germ tube immunofluorescence (IFA). A total of 56% of antibody tests (IHA 45% and IFA 64%) and 26% of antigen tests (Cand-Tec 36% and Pastorex 17%) were positive. The sensitivity and specificity of these tests with respect to systemic candidosis were 37% and 78%, respectively, for antibodies, and 0% and 90% for antigens. There was statistical significance for mortality and low levels of antibodies; Candida glabrata was detected by IFA and Candida tropicalis by Cand-Tec. Serological tests may help to define the prognosis of these patients and to support the detection of specific Candida species.

Antibodies, Fungal↗

PubMed1995

'Morphing' class filter: an interactive tool for continuous adjustment of tissue type related contrast.

The proposed class filter increases tissue type related contrast in MR images of brain. During the first phase of the filtering process tissue type classes are defined. This is done by operator intervention, or by a semiautomatic process based either on a supervised or unsupervised classifier, respectively. During the second phase a pixel intensity transform makes pixels of the same tissue class appear 'more similar' while the pixel intensities of different classes will become 'more different', in effect increasing the tissue type related contrast. For example, normal mixture cluster analysis is performed on an MR image set obtained by varying pulse sequence (PS) parameters and provides unsupervised definition of classes while taking advantage of much greater information content of the whole image set in comparison to that of a single image. The algorithm permits continuous transition ('morphing') between the original image and the tissue classification image that has been calculated from the input image set by simple sliding cursor-bar on the computer screen under the physician's control. Consequently, the resulting images do not require retraining of the physician who is already familiar with the appearance of standard MR images and they make mental integration of information from a large input image set possible and easier.

Brain↗