Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Classification Algorithms”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 631 records · Page 35Linked to original sources
PubMed1987

Criteria for the classification of osteoarthritis of the knee and hip.

The Osteoarthritis (OA) Criteria Subcommittee of the American Rheumatism Association set out to develop (a) a classification of OA that includes recognised subsets; and (b) subsets of OA identified by a combination of clinical and laboratory features. For the purposes of classification, OA should be specified if of unknown origin (idiopathic, primary) or if related to a known medical condition or event (secondary). Clinical criteria for classification of idiopathic OA of the knee were developed through a multicentre study group involving 130 patients with OA and 107 comparison patients. Comparison diagnoses included rheumatoid arthritis (RA) and other painful conditions of the knee exclusive of referred or para-articular pain. Variables from the history, physical examination, laboratory test results and radiographs were used to develop sets of criteria that serve different investigative purposes: clinical examination (sensitivity 89%; specificity 88%); clinical examination and laboratory tests (sensitivity 88%; specificity 93%); clinical examination, laboratory tests and radiographs (sensitivity 94%; specificity 88%). In contrast to prior classification criteria, the proposed criteria utilise decision trees or algorithms. Clinical criteria for classification of idiopathic OA of the hip are under development. Comparison groups are comprised of patients with other rheumatic diseases (e.g. RA), periarticular pain (e.g. trochanteric bursitis) and referred pain (e.g low back pain). From a method of opinion sampling, OA of the hip may be suggested by a combination of clinical criteria including the following: age greater than 40 years, weight-bearing pain, pain relieved by sitting, antalgic gait, decreased painful range of motion, a normal erythrocyte sedimentation rate (ESR) and a negative rheumatoid factor test.

Algorithms↗
PubMed2002

Bacteria classification using Cyranose 320 electronic nose.

BACKGROUND: An electronic nose (e-nose), the Cyrano Sciences' Cyranose 320, comprising an array of thirty-two polymer carbon black composite sensors has been used to identify six species of bacteria responsible for eye infections when present at a range of concentrations in saline solutions. Readings were taken from the headspace of the samples by manually introducing the portable e-nose system into a sterile glass containing a fixed volume of bacteria in suspension. Gathered data were a very complex mixture of different chemical compounds. METHOD: Linear Principal Component Analysis (PCA) method was able to classify four classes of bacteria out of six classes though in reality other two classes were not better evident from PCA analysis and we got 74% classification accuracy from PCA. An innovative data clustering approach was investigated for these bacteria data by combining the 3-dimensional scatter plot, Fuzzy C Means (FCM) and Self Organizing Map (SOM) network. Using these three data clustering algorithms simultaneously better 'classification' of six eye bacteria classes were represented. Then three supervised classifiers, namely Multi Layer Perceptron (MLP), Probabilistic Neural network (PNN) and Radial basis function network (RBF), were used to classify the six bacteria classes. RESULTS: A [6 x 1] SOM network gave 96% accuracy for bacteria classification which was best accuracy. A comparative evaluation of the classifiers was conducted for this application. The best results suggest that we are able to predict six classes of bacteria with up to 98% accuracy with the application of the RBF network. CONCLUSION: This type of bacteria data analysis and feature extraction is very difficult. But we can conclude that this combined use of three nonlinear methods can solve the feature extraction problem with very complex data and enhance the performance of Cyranose 320.

Algorithms↗
PubMed2001

Causality assessment of suspected virus transmission by human plasma products.

BACKGROUND: Causality assessment of reports on suspected virus transmission is crucial for early detection of infectious plasma products. Commonly used algorithms, such as the WHO criteria, do not meet the specific requirements for causality assessment of suspected virus transmission. STUDY DESIGN AND METHODS: A special algorithm, based on nucleic acid amplification and gene sequencing technology, effectiveness of validated virus-inactivation methods, empirical data concerning the safety record of the product, and information on batch-related infection clusters, was developed. The algorithm is focused on laboratory test results or otherwise standardized data, with few clinical data being required. To facilitate practical application, the algorithm has been converted into a graphical decision tree. RESULTS: The feasibility of the algorithm is shown by causality assessment of sample cases. Three cases are presented with the details of each case used in the 12-question checklist. The answers provided by the checklist led to the causality classification. CONCLUSION: The algorithm is a tool for evaluating reports of suspected virus transmission in a standardized manner. It thus has the potential to improve early signal detection in pharmacovigilance of plasma products by confirmation or exclusion of suspected infectivity in most cases.

Adult↗
PubMed2005

Automated design of robust discriminant analysis classifier for foot pressure lesions using kinematic data.

In the recent years, the use of motion tracking systems for acquisition of functional biomechanical gait data, has received increasing interest due to the richness and accuracy of the measured kinematic information. However, costs frequently restrict the number of subjects employed, and this makes the dimensionality of the collected data far higher than the available samples. This paper applies discriminant analysis algorithms to the classification of patients with different types of foot lesions, in order to establish an association between foot motion and lesion formation. With primary attention to small sample size situations, we compare different types of Bayesian classifiers and evaluate their performance with various dimensionality reduction techniques for feature extraction, as well as search methods for selection of raw kinematic variables. Finally, we propose a novel integrated method which fine-tunes the classifier parameters and selects the most relevant kinematic variables simultaneously. Performance comparisons are using robust resampling techniques such as Bootstrap 632+ and k-fold cross-validation. Results from experimentations with lesion subjects suffering from pathological plantar hyperkeratosis, show that the proposed method can lead to approximately 96% correct classification rates with less than 10% of the original features.

Adult↗
PubMed1998

Design and construction of a realistic digital brain phantom.

After conception and implementation of any new medical image processing algorithm, validation is an important step to ensure that the procedure fulfills all requirements set forth at the initial design stage. Although the algorithm must be evaluated on real data, a comprehensive validation requires the additional use of simulated data since it is impossible to establish ground truth with in vivo data. Experiments with simulated data permit controlled evaluation over a wide range of conditions (e.g., different levels of noise, contrast, intensity artefacts, or geometric distortion). Such considerations have become increasingly important with the rapid growth of neuroimaging, i.e., computational analysis of brain structure and function using brain scanning methods such as positron emission tomography and magnetic resonance imaging. Since simple objects such as ellipsoids or parallelepipedes do not reflect the complexity of natural brain anatomy, we present the design and creation of a realistic, high-resolution, digital, volumetric phantom of the human brain. This three-dimensional digital brain phantom is made up of ten volumetric data sets that define the spatial distribution for different tissues (e.g., grey matter, white matter, muscle, skin, etc.), where voxel intensity is proportional to the fraction of tissue within the voxel. The digital brain phantom can be used to simulate tomographic images of the head. Since the contribution of each tissue type to each voxel in the brain phantom is known, it can be used as the gold standard to test analysis algorithms such as classification procedures which seek to identify the tissue "type" of each image voxel. Furthermore, since the same anatomical phantom may be used to drive simulators for different modalities, it is the ideal tool to test intermodality registration algorithms. The brain phantom and simulated MR images have been made publicly available on the Internet (http://www.bic.mni.mcgill.ca/brainweb).

Brain↗
PubMed2002

Correlation between near-infrared Raman spectroscopy and the histopathological analysis of atherosclerosis in human coronary arteries.

BACKGROUND AND OBJECTIVES: Modern diagnostic methods such as near-infrared Raman spectroscopy (NIRS) allow quantification and evaluation of human atherosclerotic lesions, which can be useful in diagnosing coronary artery disease. The objective of the present study is to obtain feasible diagnostic information to detect atheromatous plaque using NIRS combined with discriminant analysis. STUDY DESIGN/MATERIAL AND METHODS: An 830 nm Ti: sapphire laser pumped by an argon laser provides near-infrared excitation. A spectrograph disperses light scattered from arterial tissue and a liquid-nitrogen cooled CCD detects the Raman spectra. A total of 111 arterial fragments were scanned and Raman results were compared with histopathology. Principal components analysis (PCA) and Mahalanobis distance (m-distance) were used to model an algorithm for tissue classification into three categories: non-atherosclerotic (NA), non-calcified (NC), and calcified (C) using Raman spectra. Spectra were randomly separated into training and prospective groups. RESULTS: It has been found that, for the NA tissue, the algorithm has sensitivity of 84 and 78% and specificity of 91 and 93% for training and prospective groups, respectively. For the NC tissue the algorithm has sensitivity of 88 and 90% and specificity of 88 and 83%. For the C tissue both sensitivity and specificity were maximum, 100%. CONCLUSIONS: An algorithm using PCA and discriminant analysis based on m-distance has been developed and successfully applied to diagnose coronary artery disease by NIRS obtaining good sensitivity and specificity for each tissue category.

Algorithms↗
PubMed2003

Development of explicit criteria for total knee replacement.

OBJECTIVES: To develop and test an appropriateness of indications tool for total knee replacement (TKR) in patients with osteoarthritis. METHODS: Criteria were developed using a modified Delphi panel judgment. Another panel rated the same indications, and the results were compared with the main panel. Test-retest of the main panel was performed. Regression models were used to assess the contribution of each algorithm variable. A classification tree was developed. RESULTS: The procedure was considered appropriate in 167 (26.8%) scenarios, and there was agreement on 112 (67.1%) of them. When the rates of the main panel were compared with those of a second panel, the result was a kappa statistic of 0.75. The test-retest kappa for the main panel was 0.78. Neither in the first case nor in the second was there an instance in which a scenario classified as appropriate shifted to inappropriate or vice versa. The regression models showed that symptomatology and radiology were the variables that explained most of the variability of appropriateness as determined by panelists. In the classification tree performed, the probability of misclassification was 3.8% with 150 scenarios, of the 156 analyzed and classified correctly. CONCLUSIONS: The previous parameters tested showed acceptable results for an evaluation tool. These results support the use of this algorithm as an aid in formulating clinical practice guidelines and to promote the appropriateness of TKR.

Algorithms↗
PubMed2000

Sequence search algorithm assessment and testing toolkit (SAT).

MOTIVATION: The Sequence Search Algorithm Assessment and Testing Toolkit (SAT) aims to be a complete package for the comparison of different protein homology search algorithms. The structural classification of proteins can provide us with a clear criterion for judgment in homology detection. There have been several assessments based on structural sequences with classifications but a good deal of similar work is now being repeated with locally developed procedures and programs. The SAT will provide developers with a complete package which will save time and produce more comparable performance assessments for search algorithms. The package is complete in the sense that it provides a non-redundant large sequence resource database, a well-characterized query database of proteins domains, all the parsers and some previous results from PSI-BLAST and a hidden markov model algorithm. RESULTS: An analysis on two different data sets was carried out using the SAT package. It compared the performance of a full protein sequence database (RSDB100) with a non-redundant representative sequence database derived from it (RSDB50). The performance measurement indicated that the full database is sub-optimal for a homology search. This result justifies the use of much smaller and faster RSDB50 than RSDB100 for the SAT. AVAILABILITY: A web site is up. The whole packa ge is accessible via www and ftp. ftp://ftp.ebi.ac.uk/pub/contrib/jong/SAT http://cyrah.ebi.ac.uk:1111/Proj/Bio/SAT http://www.mrc-lmb.cam.ac.uk/genomes/SAT In the package, some previous assessment results produced by the package can also be found for reference. CONTACT: jong@ebi.ac.uk

Algorithms↗
PubMed2006

Intrarater and interrater reliability and validity in the assessment of the mechanism of injury and integrity of the posterior ligamentous complex: a novel injury severity scoring system for thoracolumbar injuries. Invited submission from the Joint Section Meeting On Disorders of the Spine and Peripheral Nerves, March 2005.

OBJECT: A new classification and treatment algorithm for thoracolumbar injuries was recently introduced by Vaccaro and colleagues in 2005. A thoracolumbar injury severity scale (TLISS) was proposed for grading and guiding treatment for these injuries. The scale is based on the following: 1) the mechanism of injury; 2) the integrity of the posterior ligamentous complex (PLC); and 3) the patient's neurological status. The reliability and validity of assessing injury mechanism and the integrity of the PLC was assessed. METHODS: Forty-eight spine surgeons, consisting of neurosurgeons and orthopedic surgeons, reviewed 56 clinical thoracolumbar injury case histories. Each was classified and scored to determine treatment recommendations according to a novel classification system. After 3 months the case histories were reordered and the physicians repeated the exercise. Validity of this classification was good among reviewers; the vast majority (> 90%) agreed with the system's treatment recommendations. Surgeons were unclear as to a cogent description of PLC disruption and fracture mechanism. CONCLUSIONS: The TLISS demonstrated acceptable reliability in terms of intra- and interobserver agreement on the algorithm's treatment recommendations. Replacing injury mechanism with a description of injury morphology and better definition of PLC injury will improve inter- and intraobserver reliability of this injury classification system.

Algorithms↗
PubMed2005

Gene selection for classification of cancers using probabilistic model building genetic algorithm.

Recently, DNA microarray-based gene expression profiles have been used to correlate the clinical behavior of cancers with the differential gene expression levels in cancerous and normal tissues. To this end, after selection of some predictive genes based on signal-to-noise (S2N) ratio, unsupervised learning like clustering and supervised learning like k-nearest neighbor (k NN) classifier are widely used. Instead of S2N ratio, adaptive searches like Probabilistic Model Building Genetic Algorithm (PMBGA) can be applied for selection of a smaller size gene subset that would classify patient samples more accurately. In this paper, we propose a new PMBGA-based method for identification of informative genes from microarray data. By applying our proposed method to classification of three microarray data sets of binary and multi-type tumors, we demonstrate that the gene subsets selected with our technique yield better classification accuracy.

Algorithms↗
PubMed2005

Automated decision tree classification of corneal shape.

PURPOSE: The volume and complexity of data produced during videokeratography examinations present a challenge of interpretation. As a consequence, results are often analyzed qualitatively by subjective pattern recognition or reduced to comparisons of summary indices. We describe the application of decision tree induction, an automated machine learning classification method, to discriminate between normal and keratoconic corneal shapes in an objective and quantitative way. We then compared this method with other known classification methods. METHODS: The corneal surface was modeled with a seventh-order Zernike polynomial for 132 normal eyes of 92 subjects and 112 eyes of 71 subjects diagnosed with keratoconus. A decision tree classifier was induced using the C4.5 algorithm, and its classification performance was compared with the modified Rabinowitz-McDonnell index, Schwiegerling's Z3 index (Z3), Keratoconus Prediction Index (KPI), KISA%, and Cone Location and Magnitude Index using recommended classification thresholds for each method. We also evaluated the area under the receiver operator characteristic (ROC) curve for each classification method. RESULTS: Our decision tree classifier performed equal to or better than the other classifiers tested: accuracy was 92% and the area under the ROC curve was 0.97. Our decision tree classifier reduced the information needed to distinguish between normal and keratoconus eyes using four of 36 Zernike polynomial coefficients. The four surface features selected as classification attributes by the decision tree method were inferior elevation, greater sagittal depth, oblique toricity, and trefoil. CONCLUSION: Automated decision tree classification of corneal shape through Zernike polynomials is an accurate quantitative method of classification that is interpretable and can be generated from any instrument platform capable of raw elevation data output. This method of pattern classification is extendable to other classification problems.

Cornea↗
PubMed2001

Nutritional status classification in the Department of Veterans Affairs.

The Department of Veterans Affairs (VA) Nutrition Status Classification scheme uses clinical data that are routinely collected on admission or shortly thereafter for quick inpatient nutrition screening. In this scheme, patients are assigned to 1 of 4 classification levels according to 7 individual indicators. The indicators include nutrition history, unintentional weight loss as a percent of usual body weight, percent of ideal body weight, diet, diagnosis, albumin, and total lymphocyte count. After ratings (1 to 4) are assigned to each of the 7 indicators, overall nutritional status for each patient is determined by an algorithm. The VA classification system includes many of the same criteria used in other nutritional status classifications. Where it differs is in the greater emphasis on the use of objective criteria and in the rigorous evaluation of reliability and validity that went into its development. Because of these extra measures, the VA classification can be used for prioritizing workload, as well as for determining staff requirements and for comparing workload and productivity across health care facilities. So that others might benefit from using this system, this article provides information on how the classification scheme was developed and explains how it is used.

Algorithms↗
PubMed2003

[Automatic classification of liver segments according to Couinaud: development of a new algorithm and evaluation spiral CT data].

PURPOSE: To develop a software tool that analyzes the anatomy of the portal vein branches and assigns segmental and subsegmental branches according to Couinaud's classification system and to evaluate its accuracy. MATERIALS AND METHODS: The algorithm was developed in C++ on a PC. The algorithm recognizes the three major branching patterns of the portal vein. Segmental and subsegmental branches are assigned to 8 segments following Couinaud and encoded by 8 colors. The software was evaluated using CT data sets of 39 patients. After the individual segmental anatomy of each patient was determined by an experienced radiologist, automatic classification was performed and the results were compared on a branch by branch basis. RESULTS: The numbering was accurate according to Couinaud's system in 358 of 409 segmental and subsegmental branches (88 %). The assignment failed in 51 of 409 branches due to unexpected anatomy or software problems. CONCLUSION: Automatic classification of portal vein branches and their appendant parenchyma is possible. The automatic designation of liver segments enables the three-dimensional visualization of the segmental anatomy. In the future, automatic analysis might facilitate the reporting and communication of CT findings.

Algorithms↗
PubMed1985

Automatic segmentation and quantification of electron micrographs: extracellular components.

Extracellular glycosaminoglycans when precipitated by tannic acid, appear in electron micrographs as amorphous reticulate masses or fragments sometimes finely beaded and often associated with collagen fibrils. An algorithm for automatic classification, segmentation, and quantification of the amount of tannic acid-precipitable material (TAPM) and collagen in electron microscopic images is presented. Small patches of a region are initially located and the patch boundaries are traced using a binary contour tracing algorithm. The patches are then grown out and merged together to form one large area. This area is classified using a two-dimensional feature vector into one of two classes: a region with TAPM and collagen, or one with cell bodies and/or processes. Once these areas are classified and segmented, the distribution of TAPM is measured. The algorithm was tested on several TAPM images displaying varying amounts and configurations of TAPM with good results. It may also be adapted to process other electron microscopic images containing elements of interest which have complex or amorphous form.

Animals↗
PubMed2007

Hepatic hemangiomas: subtype classification and development of a clinical practice algorithm and registry.

PURPOSE: Hepatic hemangiomas, though histologically benign, may be associated with significant morbidity and mortality in afflicted infants. The literature presents much confusion regarding the natural history and treatment options for hepatic hemangiomas. Clinical manifestations range from asymptomatic self-limiting lesions to congestive heart failure associated with high-volume vascular shunting to fulminant hepatic failure with hypothyroidism, abdominal compartment syndrome, and death. There has been little rationale to choose among observation, corticosteroid, other pharmacologic agents, arterial embolization, hepatic artery ligation, resection, or liver transplantation for any given patient. METHODS: We analyzed several recent retrospective radiologic analyses and pathologic studies to determine whether hepatic hemangiomas could be categorized, allowing prediction of their natural history and rational choice of therapies based upon their clinical presentation and radiographic appearance. RESULTS: We propose that hepatic hemangiomas do not represent a single entity but, rather, 3 principle categories of lesions: focal, multifocal, and diffuse. Because these 2 categories represent different anatomical and physiologic variants, so, too, may they respond differently to previously anecdotally applied treatment regimens. With input from international multidisciplinary authorities on hemangiomas, we developed and proposed a clinical practice algorithm for the evaluation and management of hepatic hemangiomas. Toward that end, we propose a plan to institute a web-based international hepatic hemangioma registry. Participants in the registry could obtain no-cost centralized review of imaging studies (and histology if available) and guidance regarding the management algorithm from an established multidisciplinary team. In exchange, the registry will facilitate the acquisition of systematic clinical and imaging information. CONCLUSION: Longitudinal observation of response to more directed treatment protocols may contribute greatly to the understanding of these potentially fatal tumors.

Algorithms↗
PubMed2006

A Protein Classification Benchmark collection for machine learning.

Protein classification by machine learning algorithms is now widely used in structural and functional annotation of proteins. The Protein Classification Benchmark collection (http://hydra.icgeb.trieste.it/benchmark) was created in order to provide standard datasets on which the performance of machine learning methods can be compared. It is primarily meant for method developers and users interested in comparing methods under standardized conditions. The collection contains datasets of sequences and structures, and each set is subdivided into positive/negative, training/test sets in several ways. There is a total of 6405 classification tasks, 3297 on protein sequences, 3095 on protein structures and 10 on protein coding regions in DNA. Typical tasks include the classification of structural domains in the SCOP and CATH databases based on their sequences or structures, as well as various functional and taxonomic classification problems. In the case of hierarchical classification schemes, the classification tasks can be defined at various levels of the hierarchy (such as classes, folds, superfamilies, etc.). For each dataset there are distance matrices available that contain all vs. all comparison of the data, based on various sequence or structure comparison methods, as well as a set of classification performance measures computed with various classifier algorithms.

Algorithms↗
PubMed2004

Form analysis using digital signal processing reliably discriminates far-field R waves from P waves.

The correct detection of atrial arrhythmias by pacemakers is often limited by the presence of far-field R waves (FFRWs) in the atrial electrogram. Digital signal processing (DSP) of intracardiac signals is assumed to provide improved discrimination between P waves and FFRWs when compared to current methods. For this purpose, 100 bipolar and unipolar intracardiac atrial recordings from 31 patients were collected during pacemaker replacement and used for the off-line application of a novel DSP algorithm. Digital processing of the atrial intracardiac electrogram (IEGM) signals (8 bit, 800 samples/s) included filtering and calculation of the maximum amplitude and slope of the detected events. The form parameter was calculated, being the sum of the most negative value of the amplitude and that of the slope of the detected event. The algorithm collects form parameter data of P waves and FFRWs and composes histograms of these data. A sufficiently large gap between the FFRW and P wave histograms allows discrimination of these two signals based on form parameters. Three independent observers reviewed the reliability of classification with this algorithm. Sensitivity and specificity of FFRW detection were 99.63% and 100%, respectively, and no P waves were falsely classified. It can be concluded that this novel DSP algorithm shows excellent discrimination of FFRWs under off-line conditions and justify the implementation of this algorithm in future pacemakers for real-time discrimination between P waves and FFRWs. This method prevents false mode switching and allows correct and immediate intervention pacing for atrial tachyarrhythmias.

Algorithms↗