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 1,693 records · Page 94Linked to original sources
PubMed2003

Clinically potential subclasses of retinoid synergists revealed by gene expression profiling.

Retinoids have chemopreventive and therapeutic potency in oncology and dermatology, although their application is restricted by many undesirable side effects. For the development of more effective and less toxic retinoids, gene expression analyses using DNA microarrays have the potential to supplement conventional screening methods, which are based on the changes in cell morphology and/or function. In this study, we applied the class prediction algorithm, which was used in the molecular phenotyping of tumors, for the classification of synthetic retinoids (Am80 and Tp80) and retinoid synergists (HX630, TZ335, and PA024) as all-trans retinoic acid-like, 9-cis retinoic acid-like, and control-like classes. By analyzing the effects of all-trans retinoic acid and 9-cis retinoic acid on the gene expressions in a human promyelocytic leukemia cell line, HL60, we successfully selected 50 marker genes whose expression pattern could distinguish these classes. Moreover, the classification revealed the existence of two subclasses among the retinoid synergists used with Am80. Close inspection of the DNA microarray analyses indicated that these two subclasses had different effects on the apoptosis of HL60 cells, and this was confirmed by in vivo experiments. These results indicate that the retinoidal activity of Am80, which has already been used in clinical trials, could be modulated differently by the two classes of retinoid synergists. Thus, these two subclasses of retinoid synergists have the potency to widen the usage of Am80. Our analyses demonstrated that the gene expression profiling could provide important information for developing useful retinoid synergists by compensating conventional screening methods.

Alitretinoin↗
PubMed1998

[Chemical pattern recognition of traditional Chinese medicine kudingcha (II)].

In this paper, the HPLC data from 78 samples of Kudingcha were treated with back propagation algorithm of artifical neural network pattern recognition, and the computer-aided classification of Ilex cornuta Lindl., Ilex latifolia Thunb. and Ligustrum lucidum Ait. was accomplished. This paper provides a scientific, advanced and feasible method for identification of traditional Chinese medicine.

Chromatography, High Pressure Liquid↗
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↗
PubMed1996

Volume determination of human metaphase chromosomes by scanning force microscopy.

The scanning force microscopy (SFM) yields the topography of the investigated surface. A procedure was developed which starts from this three-dimensional information to estimate the volume of a biological specimen. The volume of spread human metaphase chromosomes was determined in air and rehydrated in aqueous buffer. A difference of the determined volume of a air-dried metaphase chromosome set was found compared to values from electron microscopic investigations, and could be correlated with differences in the hydration state of the chromosomes. SFM-based relative volumes of air-dried chromosomes resembles literature data regarding volume range and distribution. Possible application of SFM-based relative volume measurements for chromosome classification purposes is discussed.

Algorithms↗
PubMed2002

Email recruitment to use web decision support tools for pneumonia.

Application of guidelines to improve clinical decisions for Community Acquired Pneumonia (CAP) patients depends on accurate information about specific facts of each case and on presenting guideline support at the time decisions are being made. We report here on a system designed to solicit information from physicians about their CAP patients in order to classify CAP and present appropriate guidelines for type of care, length of stay, and use of antibiotics. We used elements of three existing information systems to create a achieve these goals: professionals coding diagnoses captured by the existing clinical information system (CIS), email, and web-based decision support tools including a pneumonia severity evaluation tool (SET). The non-secure IS components (email and web) were able to link to information in the CIS using tokens that do not reveal confidential patient-identifiable information. We examined their response to this strategy and the accuracy of pneumonia classification using this approach compared to chart review as a gold standard. On average physicians responded to email solicitations 50% of the time over the 14 month study. Also using this standard, we examined various information triggers for case finding. Professional coding of the primary reason for admission as pneumonia was fairly sensitive as an indicator of CAP. Physician use of the web SET was insensitive but fairly specific. Pneumonia classification using the SET was very reliable compared to experts' chart review using the same algorithm. We examined the distribution of severity of pneumonia for cases of pneumonia found by the various information triggers and for each severity the average length of stay. The distribution found by both chart review and by SET has demonstrated a shift toward more severe cases being admitted compared to only 3 years ago. The length of stay for level of severity is above expectations published by guidelines even for cases of true CAP by chart review. We suggest that the Fine classification system may not adequately describe patients in this setting. Physicians frequently responded that the guidelines presented did not fit their patients.

Algorithms↗
PubMed2004

ACLAME: a CLAssification of Mobile genetic Elements.

The ACLAME database (http://aclame.ulb.ac.be) is a collection and classification of prokaryotic mobile genetic elements (MGEs) from various sources, comprising all known phage genomes, plasmids and transposons. In addition to providing information on the full genomes and genetic entities, it aims to build a comprehensive classification of the functional modules of MGEs at the protein, gene and higher levels. This first version contains a comprehensive classification of 5069 proteins from 119 DNA bacteriophages into over 400 functional families. This classification was produced automatically using TRIBE-MCL, a graph-theory-based Markov clustering algorithm that uses sequence measures as input, and then manually curated. Manual curation was aided by consulting annotations available in public databases retrieved through additional sequence similarity searches using Psi-Blast and Hidden Markov Models. The database is publicly accessible and open to expert volunteers willing to participate in its curation. Its web interface allows browsing as well as querying the classification. The main objectives are to collect and organize in a rational way the complexity inherent to MGEs, to extend and improve the inadequate annotation currently associated with MGEs and to screen known genomes for the validation and discovery of new MGEs.

Bacteriophages↗
PubMed2000

An integrated approach to the analysis and modeling of protein sequences and structures. I. Protein structural alignment and a quantitative measure for protein structural distance.

We have devised and implemented in PrISM (protein informatics system for modeling) a new measure of protein structural relationships, the protein structural distance (PSD). The PSD is designed to describe relationships between protein structures in quantitative rather than descriptive terms and is applicable both when two structures are very similar, and when they are very different. It is calculated with a structural alignment procedure that uses double dynamic programming to align secondary structure elements and an iterative rigid body superposition that minimizes the root-mean-square deviation of C(alpha) atoms. The alignment algorithm, as implemented on a modest workstation, is computationally efficient, allowing for large-scale structural comparisons. PSD scores for more than one and a half million pairs of proteins were calculated and compared to the discrete classification of proteins in the SCOP database. The PSD scores, which were obtained automatically, are in large part consistent with the manually derived classifications in SCOP. Discrepancies do arise, however, due, in part, to the fact that SCOP uses criteria other than structural similarity to derive classifications while the PrISM procedure is exclusively structure based. Analysis of PSD scores suggests that there is a continuous aspect of protein conformation space, even though various classification schemes are extremely useful. The use of a continuous measure for structural distance between all pairs of proteins allows us, as described in the two accompanying papers to derive sequence/structure relationships in a more quantitative way than has previously been possible. An important strength of the approach implemented in PrISM is its ability to address many different kinds of queries interactively, making its structural comparison procedure a convenient computational tool that complements structural classification databases such as SCOP and CATH.

Algorithms↗
PubMed2006

A new hybrid method based on fuzzy-artificial immune system and k-nn algorithm for breast cancer diagnosis.

The use of machine learning tools in medical diagnosis is increasing gradually. This is mainly because the effectiveness of classification and recognition systems has improved in a great deal to help medical experts in diagnosing diseases. Such a disease is breast cancer, which is a very common type of cancer among woman. As the incidence of this disease has increased significantly in the recent years, machine learning applications to this problem have also took a great attention as well as medical consideration. This study aims at diagnosing breast cancer with a new hybrid machine learning method. By hybridizing a fuzzy-artificial immune system with k-nearest neighbour algorithm, a method was obtained to solve this diagnosis problem via classifying Wisconsin Breast Cancer Dataset (WBCD). This data set is a very commonly used data set in the literature relating the use of classification systems for breast cancer diagnosis and it was used in this study to compare the classification performance of our proposed method with regard to other studies. We obtained a classification accuracy of 99.14%, which is the highest one reached so far. The classification accuracy was obtained via 10-fold cross validation. This result is for WBCD but it states that this method can be used confidently for other breast cancer diagnosis problems, too.

Algorithms↗
PubMed2005

Prediction of siRNA knockdown efficiency using artificial neural network models.

Selective knockdown of gene expression by short interference RNAs (siRNAs) has allowed rapid validation of gene functions and made possible a high throughput, genome scale approach to interrogate gene function. However, randomly designed siRNAs display different knockdown efficiencies of target genes. Hence, various prediction algorithms based on siRNA functionality have recently been constructed to increase the likelihood of selecting effective siRNAs, thereby reducing the experimental cost. Toward this end, we have trained three Back-propagation and Bayesian neural network models, previously not used in this context, to predict the knockdown efficiencies of 180 experimentally verified siRNAs on their corresponding target genes. Using our input coding based primarily on RNA structure thermodynamic parameters and cross-validation method, we showed that our neural network models outperformed most other methods and are comparable to the best predicting algorithm thus far published. Furthermore, our neural network models correctly classified 74% of all siRNAs into different efficiency categories; with a correlation coefficient of 0.43 and receiver operating characteristic curve score of 0.78, thus highlighting the potential utility of this method to complement other existing siRNA classification and prediction schemes.

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↗
PubMed2005

A joint compression-discrimination neural transformation applied to target detection.

Many image recognition algorithms based on data-learning perform dimensionality reduction before the actual learning and classification because the high dimensionality of raw imagery would require enormous training sets to achieve satisfactory performance. A potential problem with this approach is that most dimensionality reduction techniques, such as principal component analysis (PCA), seek to maximize the representation of data variation into a small number of PCA components, without considering interclass discriminability. This paper presents a neural-network-based transformation that simultaneously seeks to provide dimensionality reduction and a high degree of discriminability by combining together the learning mechanism of a neural-network-based PCA and a backpropagation learning algorithm. The joint discrimination-compression algorithm is applied to infrared imagery to detect military vehicles.

Algorithms↗
PubMed2004

Family-based clusters of cognitive test performance in familial schizophrenia.

BACKGROUND: Cognitive traits derived from neuropsychological test data are considered to be potential endophenotypes of schizophrenia. Previously, these traits have been found to form a valid basis for clustering samples of schizophrenia patients into homogeneous subgroups. We set out to identify such clusters, but apart from previous studies, we included both schizophrenia patients and family members into the cluster analysis. The aim of the study was to detect family clusters with similar cognitive test performance. METHODS: Test scores from 54 randomly selected families comprising at least two siblings with schizophrenia spectrum disorders, and at least two unaffected family members were included in a complete-linkage cluster analysis with interactive data visualization. RESULTS: A well-performing, an impaired, and an intermediate family cluster emerged from the analysis. While the neuropsychological test scores differed significantly between the clusters, only minor differences were observed in the clinical variables. CONCLUSIONS: The visually aided clustering algorithm was successful in identifying family clusters comprising both schizophrenia patients and their relatives. The present classification method may serve as a basis for selecting phenotypically more homogeneous groups of families in subsequent genetic analyses.

Adult↗
PubMed2001

SOM integrated with CCA for the feature map and classification of complex chemical patterns.

Considering that the two-dimensional (2D) feature map of the high-dimensional chemical patterns can more concisely and efficiently represent the pattern characteristic, a new procedure integrating self-organizing map (SOM) networks with correlative component analysis (CCA) is proposed. Firstly, CCA was used to identify the most important classification characteristics (CCs) from the original high-dimensional chemical pattern information. Then, the SOM maps the first several CCs, which include the most useful information for pattern classification, onto a 2D plane, on which the pattern classification feature is concisely represented. To improve the learning efficiency of SOM networks, two new algorithms for dynamically adjusting the learning rate and the range of neighborhood around the winning unit were further worked out. Besides, a convenient method for detecting the topologic nature of SOM results was proposed. Finally, a typical example of mapping two classes natural spearmint essence was employed to verify the effectiveness of the new approach. The feature-topology-preserving (FTP) map obtained can well represent the classification of original patterns and is much better than what obtained by SOM alone.

Journal Article↗
PubMed1993

Evaluation of laboratory data by conventional statistics and by three types of neural networks.

Sixty-three patients with lung (34 small-cell, 18 squamous, 11 adeno-) carcinomas and 43 patients with benign lung diseases were characterized with seven tumor markers: neuron-specific enolase (NSE); cancer antigens CA 19-9, CA 125, CA 15-3, and CA 50; carcinoembryonic antigen (CEA); and tissue polypeptide antigen. Diagnosis had been established by histological examination after surgery and used for classification. After vector transformation, the tumor marker data were fed into neural networks (NNs) based on three different types of learning algorithms: backpropagation (BP), competitive learning (CL), and Hopfield (H). For comparison, the data were evaluated with multivariate stepwise discriminant analysis (MVSDA). BP-NNs are equal to (NSE, CA 19-9, CEA) or better than (100% correct classification when using all seven markers) MVSDA in assigning the correct diagnosis to the patients. Cross-validation data yielded shrinkage effects ranging from 0% to 12.5%. Quality-control (QC) data were evaluated by traditional QC algorithms and compared with the results obtained by a BP-NN. The results show that the BP-NNs could only partly fulfill the tasks of three QC algorithms regarding the violation of static borders but gave good results with respect to dynamic changes.

Biomarkers, Tumor↗
PubMed2004

Classification of periodic orbits in the four- and five-body problems.

The research described in this paper was motivated by the new types of periodic solutions that were recently discovered by Moore, Chenciner, Montgomery, and Simo in the three-body and the N-body problem (with large N). We attempt to classify the various types of periodic orbits, in the inertial frame, on the basis of an extensive numerical exploration. We have started an exploration of the four-body problem, where the classification of types of periodic orbits is more involved. We immediately found those orbits with symmetry with respect to the x-axis, the y-axis, or both. Complete quadruple interplay, or a triple system around a single mass is possible. Finally, what seems to be the most frequent, two binary systems in orbit around the general center of mass. However, the last group can be separated into several subgroups. We have, for instance, the case of two masses on one orbit and the two other masses on another orbit. This is again a partial choreography. We then have the case of double binary choreographies: two binary systems in which all four masses travel on one single curve. To realize this situation, a certain commensurability is needed between the overall period and the period of each binary system. The binary system makes an odd integer number, q, of revolutions during a general period. We computed many cases from q = 5 to 97. This indicates that we have a discrete infinity of choreographies. The choreography q = 5 is an especially remarkable star-shaped curve. Actually, we have two such infinite families, one with corotational and the other with contrarotational motions. We show that they can be justified by simple Keplerian approximations. Finally, we mention that our work depends heavily on the existence of symmetries. They simplify the algorithms for finding periodic orbits and they play an important role in the classification. In the four-body problem with equal masses, we have five different types of symmetries. In addition to the well-known collinear symmetry, we also found what we call double isosceles and trapezoidal symmetries. All our four-body choreographies satisfy these two symmetry conditions. In the five-body problem, we limit our work to two symmetry cases. We show that in Gerver's super-eight choreography, we are allowed to place a fifth mass at the center and we may speak about a larger sun with four smaller but equal planets that are in a choreography.

Journal Article↗
PubMed1983

Fuzzy and crisp set-theoretic-based classification of health and disease. A qualitative and quantitative comparison.

Conventional cluster analyses of patient populations are intended to assist in the identification and characterization of groups that may represent etiological or pathological subtypes within a particular disease class. These methods have been criticized as being insensitive to subtle patient differences, which may be masked as a result of the all-or-nothing concept of cluster membership intrinsic to crisp set-theoretic-based grouping algorithms. As an alternative to conventional clustering procedures, several investigators have studied the use of fuzzy classification methods. In general, these measure a patient's clinical status in terms of a real number defined on the closed unit interval, reflecting the extent or degree to which a particular grouping entity characterizes the patient. This paper compares and contrasts the applications of crisp and fuzzy set-theoretic-based clustering procedures to a set of data describing the cognitive and intellectual functioning of a group of subjects participating in a longitudinal study of aging. Emphasis is placed on both qualitative and quantitative aspects corresponding, respectively, to the clinical interpretation of cluster definitions, and the robustness or sensitivity of the classification procedures to changes in patient profiles over time. The fuzzy set-theoretic-based model was found to be more sensitive to changes in subject level of functioning over time, to provide superior quantitative protrayals of patterns of aging, and to reflect properties of the aging process derived from other research.

Aged↗
PubMed1995

Neural network classification of infrared spectra of control and Alzheimer's diseased tissue.

Artificial neural network classification methods were applied to infrared spectra of histopathologically confirmed Alzheimer's diseased and control brain tissue. Principal component analysis was used as a preprocessing technique for some of these artificial neural networks while others were trained using the original spectra. The leave-one-out method was used for cross-validation and linear discriminant analysis was used as a performance benchmark. In the cases where principal components were used, the artificial neural networks consistently outperformed their linear discriminant counterparts; 100% versus 98% correct classifications, respectively, for the two class problem, and 90% versus 81% for a more complex five class problem. Using the original spectra, only one of the three selected artificial neural network architectures (a variation of the back-propagation algorithm using fuzzy encoding) produced results comparable to the best corresponding principal component cases: 98% and 85% correct classifications for the two and five class problems, respectively.

Alzheimer Disease↗