PubMed Health⌕ Search

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 181 records · Page 10Linked to original sources
PubMed1992

Inductive learning of thyroid functional states using the ID3 algorithm. The effect of poor examples on the learning result.

The ID3 algorithm for inductive learning was tested using preclassified material for patients suspected to have a thyroid illness. Classification followed a rule-based expert system for the diagnosis of thyroid function. Thus, the knowledge to be learned was limited to the rules existing in the knowledge base of that expert system. The learning capability of the ID3 algorithm was tested with an unselected learning material (with some inherent missing data) and with a selected learning material (no missing data). The selected learning material was a subgroup which formed a part of the unselected learning material. When the number of learning cases was increased, the accuracy of the program improved. When the learning material was large enough, an increase in the learning material did not improve the results further. A better learning result was achieved with the selected learning material not including missing data as compared to unselected learning material. With this material we demonstrate a weakness in the ID3 algorithm: it can not find available information from good example cases if we add poor examples to the data.

Algorithms↗
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↗
PubMed1992

EEG classification by learning vector quantization.

EEG classification using Learning Vector Quantization (LVQ) is introduced on the basis of a Brain-Computer Interface (BCI) built in Graz, where a subject controlled a cursor in one dimension on a monitor using potentials recorded from the intact scalp. The method of classification with LVQ is described in detail along with first results on a subject who participated in four on-line cursor control sessions. Using this data, extensive off-line experiments were performed to show the influence of the various parameters of the classifier and the extracted features of the EEG on the classification results.

Algorithms↗
PubMed1992

Automated detection and quantification of venous beading using Fourier analysis.

Venous beading associated with diabetic retinopathy is currently assessed by means of subjective comparison to standard photographs from the modified Airlie House classification scheme. We describe a computerized grading scheme for venous beading. The algorithm, based on Fourier analysis of vessel width measurements, generates a venous beading index (VBI) for digitized colour fundus photographs. Colour photographs of local vessel segments about 1200 microns in length were evaluated by experienced graders. A comparison between the VBI and subjective grading showed good agreement. The mean VBI values across the four levels of clinical grading were significantly different (p = 0.000). Multiple comparison testing indicated that the VBI was able to significantly differentiate between all four categories except the "questionable" (grade 1) category (p < 0.05). We also found that progression of venous beading can be followed with the VBI. The results indicate that further development of automated grading of venous beading is warranted.

Algorithms↗
PubMed1990

Comparative accuracy of the vectorcardiogram and electrocardiogram in the localization of the accessory pathway in patients with Wolff-Parkinson-White syndrome: validation of a new vectorcardiographic algorithm by intraoperative epicardial mapping and electrophysiologic studies.

The scalar electrocardiograms (ECGs) and vectorcardiograms (VCGs) of 41 patients with Wolff-Parkinson-White (WPW) syndrome were used to compare the accuracy of these techniques in the identification of the site of preexcitation. The location of the accessory pathway (AP) was determined by endocavitary electrophysiologic studies in all patients and the location was confirmed during intraoperative epicardial mapping in 28 of them. The ECGs were classified according to Gallagher's criteria and with Milstein's algorithm, whereas the VCGs were classified according to a new two-step algorithm. The presence of multiple accessory pathways and coexisting myocardial infarctions were major limitations in both the VCG and ECG classification procedures. In patients with a single accessory pathway, three AP localizations (right free ventricular wall, posterior, or left free ventricular wall) were identified with the first step of the VCG algorithm, with an overall sensitivity (96.5%), specificity (90.7%), and positive predictive values (80%) that were greater than those obtained with the ECG Milstein algorithm (77.1%, 91.5%, and 75%, respectively). The second step of the VCG algorithm made it possible to identify an AP location in one of the following sites: anterior right, lateral right, posterior right, posterior left, lateral left, or anterior left ventricle. The overall sensitivity, specificity, and positive predictive values were greater for the second step of the VCG algorithm than for the ECG criteria proposed by Gallagher (43.6% versus 39.3%, 92.1% versus 87.4%, and 51.5% versus 33.3%, respectively). It was concluded that the VCG seems to be more specific and sensitive than the ECG in the identification of the preexcitation site and should be given preference in the initial evaluation of the WPW syndrome.

Adult↗
PubMed1991

New approaches in genome analysis by pulsed-field gel electrophoresis: application to the analysis of Pseudomonas species.

A general method for the evaluation of macrorestriction fragment patterns is presented and its applicability to the taxonomy of bacteria is demonstrated for 32 Pseudomonas species. Strains were differentiated at the species and subspecies level by genome size and macrorestriction fragment fingerprints of the chromosome that had been separated on pulsed-field gels. The relatedness of bacteria was ascertained from the similarity of AsnI, DraI, SpeI, SspI or XbaI fragment patterns. In general, the dendrograms calculated from the genome fingerprints corresponded with the phylogenetic classification obtained from phenotypic marker or nucleic acid hybridization analysis, but several exceptions were noted. The techniques and algorithms presented herein are generally applicable to the genome analysis of bacteria, lower eukaryotes, and DNA fragments cloned in yeast artificial chromosomes.

Bacteria↗
PubMed1990

Computer evaluation of Doppler spectral envelope area in patients having a valvular aortic stenosis.

The reliability of three algorithms to estimate the maximal and minimal frequency contours of Doppler spectrograms was evaluated in a group of 48 patients. Two algorithms had previously been used in the literature. These are the Modified Threshold Crossing Method and the Hybrid method. The third algorithm is new and is the Maximal Background Noise Threshold Crossing Method. A new approach was also proposed in the present study to estimate the background noise level of Doppler spectrograms. This level was used as a threshold in the computation of the spectral envelopes. Two diagnostic spectral parameters (the spectral envelope area and the systolic velocity integral) extracted from Doppler spectrograms recorded in the left ventricular outflow tract were also evaluated and tested to discriminate between 23 patients having no aortic pressure gradient and 25 patients with a stenotic aortic valve. Results describe the influence of the threshold level used in the Modified Threshold Crossing Method and the Hybrid method on the variability of the spectral contours. It is clearly demonstrated that the variability of minimal frequency contours is higher than that of maximal frequency contours. All three algorithms provided similar diagnostic performances with the spectral envelope area (71% to 73% of correct classifications) while the Maximal Background Noise Threshold Crossing Method and the Hybrid method provided the best results for the systolic velocity integral (69% of correct classifications). Because the systolic velocity integral combined with the continuity equation is used in the literature to evaluate noninvasively the aortic valve area, these results suggest the use of the spectral envelope area instead of the systolic velocity integral.

Aged↗
PubMed2026

engGNN: a dual-graph neural network for omics-based disease classification and feature selection.

Omics data, such as transcriptomics, proteomics, and metabolomics, provide critical insights into disease mechanisms and clinical outcomes. However, their high dimensionality, small sample sizes, and intricate biological networks pose major challenges for reliable prediction and meaningful interpretation. Graph neural networks offer a promising way to integrate prior knowledge by encoding feature relationships as graphs. Yet, existing methods typically rely solely on either an externally curated feature graph or a data-driven generated graph, which limits their ability to capture complementary information. To address this, we propose the external and generated Graph Neural Network (engGNN), a dual-graph framework that jointly leverages both external biological networks and data-driven generated graphs. Specifically, engGNN constructs a biologically informed undirected feature graph from established network databases and complements it with a directed feature graph derived from tree-ensemble models. This dual-graph design produces more comprehensive representations, thereby improving predictive performance and interpretability. Through extensive simulation studies and real-world applications to three independent gene expression datasets, engGNN consistently demonstrates strong classification performance compared with competitive baselines. Beyond classification, engGNN provides feature- and source-level interpretability, enabling biologically meaningful analyses such as pathway enrichment analysis. Taken together, these results highlight engGNN as a robust, flexible, and interpretable framework for disease classification and biomarker discovery in high-dimensional omics contexts.

Graph Neural Networks↗
PubMed1991

Computer-assisted statistical analyses of enzyme and ribosomal DNA electrophoretic polymorphism in Yersinia.

The intra- and inter-species differentiation of 90 strains of Yersinia belonging to six species were studied independently by computer-assisted statistical analysis of data from enzyme electrophoretic polymorphism and ribosomal DNA (rDNA) restriction fragment length polymorphism. Two correspondence analyses (CA) demonstrated the concordance between the bacterial classification obtained from enzymatic and genomic data. This concordance was reinforced by an algorithm of the correspondence established between the two dendrograms drawn from previous computations. Comparison of CA with similarity analysis (also called "numerical taxonomy") indicated that the intra- and inter-species differentiation obtained by the two methods are similar. The advantage of CA is that it gives a synthetic geometrical representation of the results (factorial planes), displaying both the main features of the clusters of strains (location and dispersion) and their essential character (i.e.: enzyme electrophoretic variant, rDNA fragment size).

Algorithms↗
PubMed1985

Computerized EEG pattern classification by adaptive segmentation and probability density function classification. Clinical evaluation.

A series of 63 clinical EEGs showing a variety of normal and abnormal patterns was analysed by computer with particular reference to the different types of pattern within the same EEG. Boundaries between different patterns were established by means of adaptive segmentation, so that the duration of the resulting segments was determined by the particular EEG itself (thus the term 'adaptive'). Four channels from each EEG were analysed, paired (left and right) channels were simultaneously segmented and analysed interactively. Similar segments were then clustered without supervision by estimating a probability density function in a 2-dimensional 'feature space' having dimensions of mean frequency and mean power. Individual clusters emerged as well-defined peaks of the surface, individual segments or small groups of duration insufficient to constitute a separate cluster, being identified as 'singular events' (e.g., rare sharp waves, artifacts). The autocorrelation function was used to characterize the EEG both for the segmentation and for the subsequent clustering of the resulting segments. In confirmation of our previous work, adaptive segmentation based on the autocorrelation function of the EEG was found to be quite satisfactory. Unsupervised clustering by estimation of the probability density function in feature space was found to give the correct number of clusters (usually less than 5) in a majority of the records (65%), but in the remaining minority of cases (35%), either overclustering or underclustering occurred. Further, the 'singular events' were occasionally partly included in a formal cluster. Comparison of these results of EEG clustering by unsupervised probability density function estimation with earlier results obtained by supervised hierarchical clustering suggests that there may be subtle cues used by the electroencephalographer in the classification of EEG patterns which have not been adequately approximated by the computer algorithms thus far used in this work. Hence at least some minimal degree of supervision in the clustering process may be necessary, at least for the present. On the other hand, the method recommends itself for the representation of illustrative EEG summaries which, in conjunction with a short written report, would provide the clinical neurologist with a sufficient picture of the real EEG without, in most cases, the need to inspect the original record.

Action Potentials↗
PubMedDate not supplied

Automatic identification of significant graphoelements in multichannel EEG recordings by adaptive segmentation and fuzzy clustering.

A new approach to visual evaluation of long-term EEG recordings is proposed. The method is based on multichannel adaptive segmentation, subsequent feature extraction, automatic classification of the acquired segments by fuzzy cluster analysis (fuzzy c-means algorithm), and on the distinguishing of thus identified EEG segments by colour directly in the EEG record. The black and white variant of the described automatic system is presented. The method was evaluated by applying it to simulated artificial data and to real EEG recordings; some of the illustrative results are shown. In addition, the performance of this system is evaluated and the first experience with its application to routine EEG recordings is discussed.

Algorithms↗
PubMed1989

Heuristic potency of the minimum spanning tree (MST) method in toxicology.

A rapid and manual mathematical method for comparing ecotoxicologic data has been investigated. It uses a classification procedure based on the calculation of chi 2 distances between the different elements of a data matrix. The classification is carried out using a simple graph-theoretical procedure (Kruskal's algorithm), allowing the construction of minimum spanning tree (MST). From an ecotoxicologic data base of 18 bacterial tests carried out on eight heavy metals the construction of the MST is explained in detail. Even if the results obtained are directly dependent on the data set chosen, they illustrate the heuristic potency of the minimum spanning tree method in comparing and estimating the dependence between environmental data.

Bacteria↗
PubMed1985

Imaging approach to the suspected renal mass.

The authors present their algorithmic approach to the detection, characterization, and staging of renal masses. Based on classification of urographic findings, the patient may be triaged to the appropriate cross-sectional or invasive imaging modality that will result in the most cost-effective management.

Abscess↗
PubMed1987

[Staging of pulmonary cancer, establishment of M1].

The rapid and widespread development of imaging techniques during the last decade has markedly modified the previous algorithms used in the staging of pulmonary carcinoma, particularly M0/M1 in the TNM classification and the directives of the American Thoracic Society. Sensitivity and specificity of each method are reviewed according to the most frequent metastatic sites of bronchopulmonary carcinoma. Presently, CT is the most efficient technique for detection and display of metastases of the contralateral lung, brain, adrenal glands and retroperitoneal lymph nodes. Ultrasound is equal or even slightly superior to CT for the detection of liver metastases. The superiority of magnetic resonance imaging (MRI) over CT in the detection of brain metastases has already been demonstrated. The results of MRI using fast sequences have recently been demonstrated for imaging of thoracic, abdominal and bone metastases, but confirmation of these first results by prospective studies is needed. Skeletal survey is still obtained by radioisotope scanning.

Bone Neoplasms↗
PubMed1989

The P-A-I-N MMPI classification system: a critical review.

The Costello et al. (Pain, 30 (1987) 199-209) literature-based MMPI clustering algorithm was compared to a standard clustering procedure of chronic pain patients' MMPI profiles. Results indicated that the Costello algorithm was too restrictive, failing to classify 69% of the MMPI profiles of the local sample. It was suggested that it may be premature to adopt a literature based clustering method until the validity of empirically derived clusters has been more thoroughly determined. The utility of a given set of clusters may best be determined by using locally derived clusters to predict treatment response. Once the predictive validity of the local clusters has been demonstrated, the Costello approach may prove more useful.

Adolescent↗