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 19 recordsLinked to original sources

PubMed2006

Comparison of SWAN and WISE menopausal status classification algorithms.

BACKGROUND: Classification of menopausal status is important for epidemiological and clinical studies as well as for clinicians treating midlife women. Most epidemiological studies, including the Study of Women's Health Across the Nation (SWAN), classify women based on self-reported bleeding history. METHODS: The Women's Ischemia Syndrome Evaluation (WISE) study developed an algorithm using menstrual and reproductive history and serum hormone levels to reproduce the menopausal status classifications assigned by the WISE hormone committee. We applied that algorithm to women participating in SWAN and examined characteristics of women with concordant and discordant SWAN and WISE classifications. RESULTS: Of the 3215 SWAN women with complete information at baseline (1995-1997), 2466 (76.7%) received concordant classifications (kappa = 0.52); at the fifth annual follow-up visit, of the 1623 women with complete information, 1154 (72.7%) received concordant classifications (kappa = 0.57). At each time point, we identified subgroups of women with discordant SWAN and WISE classifications. These subgroups, ordered by chronological age, showed increasing trends for menopausal symptoms and follicle-stimulating hormone (FSH) and a decreasing trend for estrogen (p < 0.001). CONCLUSIONS: The WISE algorithm is a useful tool for studies that have access to blood samples for hormone data unrelated to menstrual cycle phase, with or without an intact uterus, and no resources for adjudication. Future studies may want to combine aspects of the SWAN and WISE algorithms by adding hormonal measures to the series of bleeding questions in order to determine more precisely where women are in the perimenopausal continuum.

Adult↗

PubMed2004

FocalPoint slide classification algorithms show robust performance in classification of high-grade lesions on SurePath liquid-based cervical cytology slides.

The FocalPoint Primary Screening System (FPPS) operates by assigning scores to each slide relative to the probability that an abnormality is present. This information ranks each slide within five "quintiles" (1 = highest risk, 5 = lowest risk) of the "review" population, allowing examining cytologists to understand the risk inherent in each slide. Such information helps to make the primary and quality control rescreening processes most efficient. This study examines the efficiency of AutoPap scoring and, thus, stratification of high-grade cases within a clinical trial setting. A total of 1,275 SurePath (TriPath, Burlington, NC) slides were screened on the FPPS. There were 124 high-grade cases in the set (32 HSIL, 5 AIS, and 87 cancers) as determined by cytologic truth adjudication. The efficiency of FPPS ranking was determined by analysis of the numbers of high-grade cases ranked into quintiles 1 (top 20%) and 1+2 (top 40%). FPPS places cases scored as "unsatisfactory" (HSIL, 3; Cancer, 18) into quintile 5 to ensure a manual review. These cases were excluded from the analysis. Overall, 58% of high-grade slides were classified as Q1 and 83% were classified as Q1+Q2. For HSIL, 66% were classified as Q1 and 90% as Q1+Q2. For Cancer, 59% were classified as Q1 and 84% as Q1+Q2. No high-grade slides were ranked in the lower "no review" population (slides that would receive no manual examination). The results confirm the robust performance of the FPPS classification algorithm. Far more high-grade slides are classified into the top two quintiles than would be expected by random chance alone (20% and 40%, respectively). These results validate the safety and effectiveness of this device on SurePath liquid-based slides.

Algorithms↗

PubMed2005

Non-linear cancer classification using a modified radial basis function classification algorithm.

This paper proposes a modified radial basis function classification algorithm for non-linear cancer classification. In the algorithm, a modified simulated annealing method is developed and combined with the linear least square and gradient paradigms to optimize the structure of the radial basis function (RBF) classifier. The proposed algorithm can be adopted to perform non-linear cancer classification based on gene expression profiles and applied to two microarray data sets involving various human tumor classes: (1) Normal versus colon tumor; (2) acute myeloid leukemia (AML) versus acute lymphoblastic leukemia (ALL). Finally, accuracy and stability for the proposed algorithm are further demonstrated by comparing with the other cancer classification algorithms.

Acute Disease↗

PubMed2006

Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG).

The early detection of subjects with probable Alzheimer's disease (AD) is crucial for effective appliance of treatment strategies. Here we explored the ability of a multitude of linear and non-linear classification algorithms to discriminate between the electroencephalograms (EEGs) of patients with varying degree of AD and their age-matched control subjects. Absolute and relative spectral power, distribution of spectral power, and measures of spatial synchronization were calculated from recordings of resting eyes-closed continuous EEGs of 45 healthy controls, 116 patients with mild AD and 81 patients with moderate AD, recruited in two different centers (Stockholm, New York). The applied classification algorithms were: principal component linear discriminant analysis (PC LDA), partial least squares LDA (PLS LDA), principal component logistic regression (PC LR), partial least squares logistic regression (PLS LR), bagging, random forest, support vector machines (SVM) and feed-forward neural network. Based on 10-fold cross-validation runs it could be demonstrated that even tough modern computer-intensive classification algorithms such as random forests, SVM and neural networks show a slight superiority, more classical classification algorithms performed nearly equally well. Using random forests classification a considerable sensitivity of up to 85% and a specificity of 78%, respectively for the test of even only mild AD patients has been reached, whereas for the comparison of moderate AD vs. controls, using SVM and neural networks, values of 89% and 88% for sensitivity and specificity were achieved. Such a remarkable performance proves the value of these classification algorithms for clinical diagnostics.

Aged↗

PubMed2004

Comparison of different classification algorithms for underwater target discrimination.

Classification of underwater targets from the acoustic backscattered signals is considered here. Several different classification algorithms are tested and benchmarked not only for their performance but also to gain insight to the properties of the feature space. Results on a wideband 80-kHz acoustic backscattered data set collected for six different objects are presented in terms of the receiver operating characteristic (ROC) and robustness of the classifiers wrt reverberation.

Acoustic Stimulation↗

PubMed1991

DTL: a language to assist cardiologists in improving classification algorithms.

Heuristic classifiers, e.g., for diagnostic classification of the electrocardiogram, can be very complex. The development and refinement of such classifiers is cumbersome and time-consuming. Generally, it requires a computer expert to implement the cardiologist's diagnostic reasoning into computer language. The average cardiologist, however, is not able to verify whether his intentions have been properly realized and perform as he hoped for. But also for the initiated, it often remains obscure how a particular result was reached by a complex classification program. An environment is presented which solves these problems. The environment consists of a language, DTL (Decision Tree Language), that allows cardiologists to express their classification algorithms in a way that is familiar to them, and an interpreter and translator for that language. The considerations in the design of DTL are described and the structure and capabilities of the interpreter and translator are discussed.

Algorithms↗

PubMed2002

A software-based pacemaker pulse detection and paced rhythm classification algorithm.

A new pacemaker pulse detection and paced electrocardiogram (ECG) rhythm classification algorithm with high sensitivity and positive predictive value has been implemented as part of the Philips Medical Systems' (Andover, MA) ECG analysis program. The detection algorithm was developed on 1,108 paced ECGs with 16,029 individual pulse locations. It operates on 12-lead, 500 sample per second, 150 Hz low-pass filtered ECG signals. Even after low-pass filtering, this algorithm distinguishes between pacemaker pulses and narrow QRS complexes from newborns. An individual pulse detection sensitivity of 99.7% and positive predictive value of 99.5% was obtained by the multi-lead detector. A 10-second, 12-lead ECG database (n = 13,155) of paced (n = 2,190), non-paced adult (n = 8,070), non-paced pediatric (n = 1,209) and "noisy" ECGs with spike noise and muscle artifact (n = 1,686) was assembled and annotated by two readers. The overall performance in identification of an ECG as paced with any pacing present versus non-paced is 97.2% in sensitivity and 99.9% in specificity. The paced ECGs were classified by the mode in which the beats were paced, such as, atrial, ventricular, A-V dual, or dual/inhibited chamber (ie, combinations of atrial, ventricular and dual) pacing. An algorithm was developed for paced rhythm classification. The algorithm performance results show that accurate and robust pacemaker pulse detection and classification can be done in software on diagnostic bandwidth ECG signals.

Adult↗

PubMed1989

Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty.

Laser angioplasty, or the ablation of atherosclerotic plaque using laser energy, has tremendous potential to expand the scope of nonsurgical treatment of obstructive vascular disease. Clinical laser angioplasty, however, has been hindered by an unacceptable risk of vessel perforation. Laser-induced fluorescence spectroscopy can discriminate atherosclerotic from normal artery and may therefore be capable of guiding selective plaque ablation. To assess the feasibility of utilizing spectral information to discriminate arterial tissue type, several classification algorithms were developed and evaluated. Arterial fluorescence spectra from 350 to 700 nm were obtained from 100 human aortic specimens. Seven spectral classification algorithms were developed with the following techniques: multivariate linear regression, stepwise multivariate linear regression, principal components analysis, decision plane analysis, Bayes decision theory, principal peak ratio, and spectral width. The classification ability of each algorithm was evaluated by its application to the training set and to a validation set containing 82 additional spectra. All seven spectral classification algorithms prospectively classified atherosclerotic and normal aorta with an accuracy greater than 80 percent (range: 82-96 percent). Laser angioplasty systems incorporating spectral classification algorithms may therefore be capable of detection and selective ablation of atherosclerotic plaque.

Algorithms↗

PubMed2004

An efficient robust sound classification algorithm for hearing aids.

An efficient robust sound classification algorithm based on hidden Markov models is presented. The system would enable a hearing aid to automatically change its behavior for differing listening environments according to the user's preferences. This work attempts to distinguish between three listening environment categories: speech in traffic noise, speech in babble, and clean speech, regardless of the signal-to-noise ratio. The classifier uses only the modulation characteristics of the signal. The classifier ignores the absolute sound pressure level and the absolute spectrum shape, resulting in an algorithm that is robust against irrelevant acoustic variations. The measured classification hit rate was 96.7%-99.5% when the classifier was tested with sounds representing one of the three environment categories included in the classifier. False-alarm rates were 0.2%-1.7% in these tests. The algorithm is robust and efficient and consumes a small amount of instructions and memory. It is fully possible to implement the classifier in a DSP-based hearing instrument.

Acoustic Stimulation↗

PubMed1995

Classification-algorithm evaluation: five performance measures based on confusion matrices.

OBJECTIVE: The objective of this paper is to introduce, explain, and extend methods for comparing the performance of classification algorithms using error tallies obtained on properly sized, populated, and labeled data sets. METHODS: Two distinct contexts of classification are defined, involving "objects-by-inspection" and "objects-by-segmentation." In the former context, the total number of objects to be classified is unambiguously and self-evidently defined. In the latter, there is troublesome ambiguity. All five of the measures of performance here considered are based on confusion matrices, tables of counts revealing the extent of an algorithm's "confusion" regarding the true classifications. A proper measure of classification-algorithm performance must meet four requirements. A proper measure should obey six additional constraints. RESULTS: Four traditional measures of performance are critiqued in terms of the requirements and constraints. Each measure meets the requirements, but fails to obey at least one of the constraints. A nontraditional measure of algorithm performance, the normalized mutual information (NMI), is therefore introduced. Based on the NMI, methods for comparing algorithm performance using confusion matrices are devised. CONCLUSIONS: The five performance measures lead to similar inferences when comparing a trio of QRS-detection algorithms using a large data set. The modified NMI is preferred, however, because it obeys each of the constraints and is the most conservative measure of performance.

Algorithms↗

PubMedDate not supplied

Automatic classification algorithms of the EEG monitor Narcotrend for routinely recorded EEG data from general anaesthesia: a validation study.

Impacts of hypnotic drugs on brain function are reflected in the EEG. The EEG monitor Narcotrend performs an automatic classification of the EEG using a scale which was proposed by Kugler for visual evaluation of the EEG. In this article the results of a validation study of the automatic classification algorithms implemented in the EEG monitor Narcotrend are presented. Visual and automatic classification of EEG data recorded in routine clinical practice were compared. The correlation between visual and automatic assessment was high (Spearman rank correlation r = 0.90, prediction probability Pk = 0.90) and a sufficient agreement between visual and automatic assessment was achieved for 92% of the analysed EEG epochs. The results of the study suggest that the automatic classification algorithms implemented in the EEG monitor Narcotrend yield a reliable assessment of the depth of hypnosis.

Algorithms↗

PubMed1995

Evaluation of partial classification algorithms using ROC curves.

When using computer programs for decision support in clinical routine, an assessment or a comparison of the underlying classification algorithms is essential. In classical (forced) classification, the classification rule always selects exactly one alternative. A number of proven discriminant measures are available here, e.g.sensitivity and error rate. For probabilistic classification, a series of additional measures has been developed [1]. However, for many clinical applications, there are models where an observation is classified into several classes (partial classification), e.g., models from artificial intelligence, decision analysis, or fuzzy set theory. In partial classification, the discriminatory ability (Murphy) can be adjusted a priori to any level, in most practical cases. Here the usual measures do not apply. We investigate the preconditions for assessment and comparison based on medical decision theory. We focus on problems in the medical domain and establish a methodological framework. When using partial classification procedures, a ROC analysis in the classical sense is no longer appropriate. In forced classification for two classes, the problem is to find a cutoff point on the ROC curve; while in partial classification, you have to find two of them. They characterize the elements being classified as coming from both classes. This extends to several classes. We propose measures corresponding to the usual discriminant measures for forced classification (e.g., sensitivity and error rate) and demonstrate the effects using the ROC approach. For this purpose, we extend the existing method for forced classification in a mathematically sound manner. Algorithms for the construction of thresholds can easily be adapted. Two specific measurement models, based on parametric and non-parametric approaches, will be introduced. The basic methodology is suitable for all partial classification problems, whereas the extended ROC analysis assumes a rank order of the selected alternatives. The method is based on the black box principle and makes use only of the results of the compared algorithms and some general intuitive principles. Therefore, algorithms arising from different "philosophical" approaches may also be compared according to their results. For demonstration purposes, a clinical example from cranial computed tomography is presented. Linear discriminant analysis as a reference is compared to a Bayesian and a fuzzy procedure.

Algorithms↗

PubMedDate not supplied

Classification algorithms for hip fracture prediction based on recursive partitioning methods.

This article presents 2 modifications to the classification and regression tree. The authors improved the robustness of a split in the test sample approach and developed a cost-saving classification algorithm by selecting noninferior to the optimum splits from variables with lower cost or being used in parent splits. The new algorithm was illustrated by 43 predictive variables for 5-year hip fracture previously documented in the Study of Osteoporotic Fractures. The authors generated the robust optimum classification rule without consideration of classification variable costs and then generated an alternative cost-saving rule with equivalent diagnostic utility. A 6-fold cross-validation study proved that the cost-saving alternative classification is statistically noninferior to the optimal one. Their modified classification and regression tree algorithm can be useful in clinical applications. A dual X-ray absorptiometry hip scan and information from clinical examinations can identify subjects with elevated 5-year hip fracture risk without loss of efficiency to more costly and complicated algorithms.

Absorptiometry, Photon↗

PubMed2005

A review and comparison of classification algorithms for medical decision making.

Within a health care setting, it is often desirable from both clinical and operational perspective to capture the uncertainty and variability amongst a patient population, for example to predict individual patient outcomes, risks or resource needs. Homogeneity brings the benefits of increased certainty in individual patient needs and resource utilisation, thus providing an opportunity for both improved clinical diagnosis and more efficient planning and management of health care resources. A number of classification algorithms are considered and evaluated for their relative performances and practical usefulness on different types of health care datasets. The algorithms are evaluated using four criteria: accuracy, computational time, comprehensibility of the results and ease of use of the algorithm to relatively statistically naive medical users. The research has shown that there is not necessarily a single best classification tool, but instead the best performing algorithm will depend on the features of the dataset to be analysed, with particular emphasis on health care data, which are discussed in the paper.

Algorithms↗

PubMed1999

Classification algorithms applied to narrative reports.

Narrative text reports represent a significant source of clinical data. However, the information stored in these reports is inaccessible to many automated decision support systems. Data mining techniques can assist in extracting information from narrative data. Multiple classification methods, such as rule generation, decision trees, Bayesian classifiers, and information retrieval were used to classify a set of 200 chest X-ray reports according to 6 clinical conditions indicated. A general-purpose natural language processor was used to convert the narrative text into a coded form that could be used by the classification algorithms. Significant differences in performance were found between algorithms. The best performing algorithm applied to the processor output was significantly better than information retrieval applied to raw text. Predictor variables from the coded processor output were limited to avoid overfitting. Methods that limited by domain knowledge performed significantly better than those that limited by conditional probabilities of the variables in the training set. Algorithms were also shown to be dependent on training set size.

Algorithms↗

PubMed2004

The Narcotrend Index: classification algorithm, correlation with propofol effect-site concentrations, and comparison with spectral parameters.

A reliable assessment of the depth of hypnosis during sedation and general anaesthesia using the EEG is a subject of current interest. The Narcotrend Index implemented in the latest version 4.0 of the EEG monitor Narcotrend provides an automatic classification of the EEG on a scale ranging from 100 (awake) to 0 (very deep hypnosis, EEG suppression). The classification algorithms implemented in the EEG monitor Narcotrend are described. In a study the correlation of the propofol effect-site concentration with the Narcotrend Index and with the traditional spectral parameters total power, relative power in the standard frequency bands delta, theta, alpha, and beta, median frequency, 95% spectral edge frequency, burst-compensated spectral edge frequency, and spectral entropy was investigated. The Narcotrend Index had the highest average correlation with the propofol effect-site concentration and the smallest variability of the individual correlation values. Moreover, the Narcotrend Index was the only parameter which showed a monophasic trend over the whole investigated time period. The Narcotrend monitor can make a significant contribution to the improvement of the quality of anaesthesia by adjusting the dosage of hypnotics to individual patient needs.

Adolescent↗

PubMed1998

A new classification algorithm for discrimination of ventricular from supraventricular tachycardia in a dual chamber implantable cardioverter defibrillator.

INTRODUCTION: The high incidence of inappropriate therapies due to supraventricular tachycardia remains a major unsolved problem of implantable cardioverter defibrillators. We report a new detection formula for discrimination of ventricular tachycardia from supraventricular tachycardia in a patient with a dual chamber implantable cardioverter defibrillator and a new atrioventricular classification algorithm. METHODS AND RESULTS: The enhanced detection algorithm performs a stepwise arrhythmia analysis. The rhythm is first classified on the basis of cycle length. Each episode is then classified as supraventricular or ventricular on the basis of atrioventricular association, stability of circle length, and origin of acceleration. Sophisticated diagnostic information is provided by atrioventricular markers and electrogram recordings. Successful discrimination of two spontaneous episodes of ventricular tachycardia and supraventricular tachycardia is demonstrated. CONCLUSION: This new dual chamber detection algorithm may significantly improve the specificity of tachyarrhythmia detection without sacrificing sensitivity, thereby reducing the number of spurious shocks in patients with recurrent supraventricular tachycardias. Further studies are needed to assess the sensitivity and specificity of this detection algorithm.

Algorithms↗

PubMed2006

Classification algorithms for microcalcifications in mammograms (Review).

Early detection is the key to improve breast cancer prognosis. The only proven effective method of breast cancer early detection is mammography. An early sign of 30-50% of breast cancer is the appearance of clusters of fine, granular microcalcifications and 60-80% of breast carcinomas reveal microcalcification clusters upon histological examination. The high correlation between the appearance of the microcalcification clusters and diseases, proves that computer aided diagnosis (CAD) systems for automated classification of microcalcification clusters will be very useful and helpful for breast cancer control. The fuzzy nature of microcalcification, the low contrast and the low ability of distinguishing them from their surroundings make automated characterization of them extremely difficult. In this study, we give an overview of the currently available literature on characterization of malignant and benign microcalcifications. We compare and evaluate some of the classification algorithms on microcalcifications in mammograms used in various CAD systems, which are separated into categories according to the method in use. Neural networks are used in applications where only a few decisions are required concerning an amount of data. The k-nearest neighbour classifier distinguishes unknown patterns based on the similarity to known samples and the decision tree approach is much simpler than neural networks and does not need extensive knowledge of the probability distribution of the features.

Algorithms↗