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 343 records · Page 19Linked to original sources
PubMed2001

Long-term follow-up after ileoanal pouch procedure: algorithm for diagnosis, classification, and management of pouchitis.

PURPOSE: Inflammation of the ileoanal pouch (pouchitis) is one of the main complications after restorative proctocolectomy, yet its cause remains poorly understood. A standardized definition and diagnostic procedures in pouchitis are lacking. METHOD: We analyzed all cases of pouchitis occurring in a group of 308 patients (210 with ulcerative colitis, 98 with familial adenomatous polyposis) who took part in a prospective long-term follow-up program. The severity of pouchitis was measured using a pouchitis activity score (Heidelberg Pouchitis Activity Score). An algorithm for the classification and management of pouchitis was established which enables the clinician: 1) to determine the severity of pouchitis, 2) to differentiate between primary pouchitis and pouchitis caused by surgical complications (secondary pouchitis), and 3) to evaluate the course (acute vs. chronic (> 3 months)). RESULTS: The median duration of follow-up was 48 (range, 13-119) months. At least one episode of pouchitis was diagnosed in 29 percent of patients with ulcerative colitis and in 2 percent of familial adenomatous polyposis patients. Secondary pouchitis occurred in 6 percent of ulcerative colitis patients and was cured by surgical treatment in 13 (87 percent) of 15 cases. Primary pouchitis was diagnosed in 23 percent of ulcerative colitis patients, including 6 percent of all ulcerative colitis patients with chronic primary pouchitis. The latter showed poor response to medical treatment. In one case multifocal high-grade dysplasia occurred. Histologic examination of the excised pouch identified a carcinoma originating from the ileal mucosa. CONCLUSIONS: Ulcerative colitis patients after restorative proctocolectomy face a high risk of developing pouchitis. The algorithm used in this study was highly efficient in identifying patients with a secondary pouchitis who require surgical treatment and patients with chronic primary pouchitis. For the latter, long-term surveillance seems mandatory because of the risk of malignant transformation of the pouch mucosa.

Acute Disease↗
PubMed1993

An examination of inductive learning algorithms for the classification of sleep signals.

To determine their usefulness in sleep stage scoring, nine inductive learning algorithms have been tested against the sleep signals of 161 subjects representing more than 130,000 sleep events. The performance of each algorithm has been examined relative to the number of somnologist-supplied events, the simplicity of the induced rules, the percentage of all events correctly classified and the percentage of classified-events correctly classified. The last category is especially important in building reliable systems in a medical domain, where it is better for an event to be labeled "unknown" rather than incorrectly labeled. Algorithms showing the best overall performance are C4, MDL, and AIMS, generating the simplest rules, with a very high overall accuracy. PRG, a more conservative classifier, has a significantly higher accuracy on events that it is able to classify. COBWEB and the Nearest Neighbor method had marginally higher accuracy when the number of somnologist-supplied events is limited.

Algorithms↗
PubMed2025

MWENA: a novel sample re-weighting-based algorithm for disease classification and data interpretation using extracellular vesicles omics data.

BACKGROUND AND OBJECTIVE: Extracellular vesicles (EVs), considered as a form of liquid biopsy, have gained significant attention in recent years due to their stability and the preservation of disease markers. Research studies underscore the clinical significance of molecules found in EVs, highlighting their role as communicative mediators between cells. However, analyzing this data is challenging due to noisy measurements, having far more variables than samples, and some groups (e.g., disease subtypes or experimental conditions) having much less data than others. We therefore develop an algorithm to address aforementioned challenges for the classification of imbalanced EVs omics data. METHODS AND RESULTS: We propose the EV Meta-Weight Elastic Net Algorithm (MWENA), which utilizes logistic regression with elastic net regularization for the classification and identification of EV signatures, effectively addressing the challenges posed by high-dimensional small sample sizes. To mitigate issues related to class imbalance and high noise levels, MWENA incorporates an automatic sample re-weighting function, which uses a meta-net to adaptively learn generalizable patterns directly from the data itself. We validate the MWENA algorithm on both simulated data and EVs omics data, covering six classification tasks that involve four different types of diseases (pancreatic ductal adenocarcinoma, interstitial lung diseases, colorectal cancer, and ovarian cancer) and three clinical scenarios (disease diagnosis, disease-stage screening, and disease-subtype classification). Compared to other machine learning methods, MWENA demonstrates superiority in identifying small class samples and achieves the highest scores in both sensitivity and G-means. Biological analysis is also performed to further explore the significance of selected signatures as biological markers and their roles in disease mechanisms. CONCLUSIONS: We anticipate that our proposed approach will take a modest step in harnessing EV omics data to discover biomarkers, aiding researchers in gaining a comprehensive understanding of biological processes.

Extracellular Vesicles↗
PubMed2004

Application of recently developed computer algorithm for automatic classification of unstructured radiology reports: validation study.

PURPOSE: To validate the accuracy of Lexicon Mediated Entropy Reduction (LEXIMER), a new information theory-based computer algorithm developed by the authors for independent analysis and classification of unstructured radiology reports based on the presence of clinically important findings (F(T), where (T) represents "true") and recommendations for subsequent action (R(T)). MATERIALS AND METHODS: The study was approved by the Human Research Committee of the institutional review board. Consecutive de-identified radiology reports (n = 1059) comprising results of barium studies (n = 99), computed tomography (n = 107), mammography (n = 90), magnetic resonance imaging (n = 108), nuclear medicine (n = 99), positron emission tomography (n = 106), radiography (n = 212), ultrasonography (n = 131), and vascular procedures (n = 107) were independently analyzed by two radiologists and then with LEXIMER to categorize the reports into F(T) and F(T)0 (containing or not containing clinically important findings) categories and R(T) and R(T)0 (containing or not containing recommendations for subsequent action) categories. Accuracy, sensitivity, specificity, and positive and negative predictive values of LEXIMER for placing reports into F(T) and F(T)0 and R(T) and R(T)0 categories were assessed by using appropriate statistical tests. RESULTS: There was strong interobserver concordance between the two radiologists for placing radiology reports into F(T) and R(T) categories (kappa = 0.9, P < .01). For the LEXIMER program, accuracy, sensitivity, specificity, and positive and negative predictive values, respectively, were 97.5% (95% confidence interval [CI]: 96.6%, 98.5%), 98.9% (95% CI: 97.9%, 99.6%), 94.9% (95% CI: 93.1%, 96.0%), 97.5% (95% CI: 96.6%, 98.0%), and 97.7% (95% CI: 95.8%, 98.8%) for placing radiology reports into F(T) and F(T)0 categories and 99.6% (95% CI: 99.2%, 99.9%), 98.2% (95% CI: 95.0%, 99.6%), 99.9% (95% CI: 99.4%, 99.99%), 99.4% (95% CI: 96.3%, 99.9%), and 99.7% (95% CI: 98.9%, 99.9%) for placing reports into R(T) and R(T)0 categories. CONCLUSION: LEXIMER is an accurate automated engine for evaluating the percentage positivity of clinically important findings and rates of recommendation for subsequent action in unstructured radiology reports.

Algorithms↗
PubMed2000

A classification system and algorithm for reconstruction of maxillectomy and midfacial defects.

Maxillectomy defects become more complex when critical structures such as the orbit, globe, and cranial base are resected, and reconstruction with distant tissues becomes essential. This study reviews all maxillectomy defects reconstructed immediately using pedicled and free flaps to establish (1) a classification system and (2) an algorithm for reconstruction of these complex problems. Over a 5-year period, 60 flaps were used to reconstruct defects classified as the following: type I, limited maxillectomy (n = 7); type II, subtotal maxillectomy (n = 10); type IIIa, total maxillectomy with preservation of the orbital contents (n = 13); type IIIb, total maxillectomy with orbital exenteration (n = 18); and type IV, orbitomaxillectomy (n = 10). Free flaps (45 rectus abdominis and 10 radial forearm) were used in 55 patients (91.7 percent), and the temporalis muscle was transposed in five elderly patients who were not free-flap candidates. Vascularized (radial forearm osteocutaneous) bone flaps were used in four of the 60 patients (6.7 percent) and nonvascularized bone grafts in 17 (28.3 percent). Simultaneous reconstruction of the oral commissure using an Estandler procedure was performed in 10 patients with maxillectomy and through-and-through soft-tissue defects. Free-flap survival was 100 percent, with reexploration in five of 55 patients (9.1 percent) and partial-flap necrosis in one patient. Seven of the 60 patients (11.7 percent) had systemic complications, and four died within 30 days of hospitalization. Fifty patients had more than 6 months of follow-up with a mean time of 27.7 (+/- 15.6) months. Postoperative radiotherapy was administered in 32 of these patients (64.0 percent). Chewing and speech functions were assessed in 36 patients with type II, IIIa, and IIIb defects. A prosthetic denture was fixed in 15 of 36 patients (41.7 percent). Return to an unrestricted diet was seen in 16 patients (44.4 percent), a soft diet in 17 (47.2 percent), and a liquid diet in three (8.3 percent). Speech was assessed as normal in 14 of 36 patients (38.9 percent), near normal in 15 (41.7 percent), intelligible in six (16.7 percent), and unintelligible in one patient (2.8 percent). Globe and periorbital soft-tissue position was assessed in 14 patients with type I and IIIa defects. There were no cases of enophthalmos, and one patient had a mild vertical dystopia. Ectropion was observed in 10 of 14 patients (71.4 percent). Oral competence was considered good in all 10 patients with excision/reconstruction of the oral commissure; however, two patients (20 percent) developed microstomia after receiving radiotherapy. Aesthetic results were evaluated at least 6 months after reconstruction in 50 patients. They were good to excellent in 29 patients (58 percent) for whom cheek skin and lip were not resected, and poor to fair (42 percent) when the external skin or orbital contents were excised. Secondary procedures were required in 16 of 50 patients (32.0 percent). Free-tissue transfer provides the most effective and reliable form of immediate reconstruction for complex maxillectomy defects. The rectus abdominis and radial forearm flaps in combination with immediate bone grafting or as osteocutaneous flaps reliably provide the best aesthetic and functional results. An algorithm based on the type of maxillary resection can be followed to determine the best approach to reconstruction.

Algorithms↗
PubMed1999

Comparison of genetic algorithms and other classification methods in the diagnosis of female urinary incontinence.

Galactica, a newly developed machine-learning system that utilizes a genetic algorithm for learning, was compared with discriminant analysis, logistic regression, k-means cluster analysis, a C4.5 decision-tree generator and a random bit climber hill-climbing algorithm. The methods were evaluated in the diagnosis of female urinary incontinence in terms of prediction accuracy of classifiers, on the basis of patient data. The best methods were discriminant analysis, logistic regression, C4.5 and Galactica. Practically no statistically significant differences existed between the prediction accuracy of these classification methods. We consider that machine-learning systems C4.5 and Galactica are preferable for automatic construction of medical decision aids, because they can cope with missing data values directly and can present a classifier in a comprehensible form. Galactica performed nearly as well as C4.5. The results are in agreement with the results of earlier research, indicating that genetic algorithms are a competitive method for constructing classifiers from medical data.

Algorithms↗
PubMed2005

Pulmonary hypertension: classification and diagnostic algorithm.

Pulmonary arterial hypertension (PAH) is defined as a group of diseases characterized by a progressive increase in pulmonary vascular resistance leading to right ventricular failure and premature death. Recently, the diagnostic approach has been more clearly defined according to the new clinical classification and with consensus reached on algorithms of various investigative tests and procedures that exclude other causes and ensure an accurate diagnosis of PAH. The diagnostic procedures include clinical history and physical examination, ECG, chest X-ray, transthoracic Doppler echocardiography, pulmonary function tests, arterial blood gas analysis, ventilation and perfusion lung scan, high-resolution computed tomography of the lungs, contrast-enhanced spiral computed tomography of the lungs and pulmonary angiography, blood tests and immunology, abdominal ultrasound scan, exercise capacity assessment, and hemodynamic evaluation. Invasive and non-invasive markers of disease severity, either biomarkers or physiological parameters and tests that can be widely applied, have been proposed to reliably monitor the clinical course.

Algorithms↗
PubMed1998

Comparison of professional judgment versus an algorithm for nutrition status classification.

OBJECTIVES: The classification of a patient's nutrition status is important for identifying patients who require nutrition care, for designing effective nutrition interventions, and for measuring severity of illness. The objective of this study was to evaluate the reliability and validity of two variants of the Department of Veterans Affairs' nutrition status classification: professional judgment versus an algorithm. METHODS: The study consisted of two phases, both of which included providing a sample of approximately 60 registered dietitians and 60 clinical dietetic technicians with data on 16 (phase I) and 20 (phase II) patients, to which they assigned nutrition statuses using both professional judgment and the algorithm. Improvements in instructions and training were implemented between the two phases. Interrater reliability of the responses was calculated, and content validity was measured by comparing the staff's responses with those of an expert panel. RESULTS: Reliability improved significantly between phases for both professional judgment and the algorithm. Greater reliability and validity were observed with use of the algorithm, by both dietitians and technicians, during both phases. CONCLUSION: Classification of a patient's nutrition status is important in the delivery of cost-effective health care. The Department of Veterans Affairs' nutrition status classification is a good one for assessing nutrition status quickly and reliably, especially when an algorithm is used. The results underscore the advantages of a classification system based on an algorithm when the system is designed to be used by many different staff across multiple facilities.

Adult↗
PubMed2005

An EM algorithm for shape classification based on level sets.

In this paper, we propose an expectation-maximization (EM) approach to separate a shape database into different shape classes, while simultaneously estimating the shape contours that best exemplify each of the different shape classes. We begin our formulation by employing the level set function as the shape descriptor. Next, for each shape class we assume that there exists an unknown underlying level set function whose zero level set describes the contour that best represents the shapes within that shape class. The level set function for each example shape in the database is modeled as a noisy measurement of the appropriate shape class's unknown underlying level set function. Based on this measurement model and the judicious introduction of the class labels as the hidden data, our EM formulation calculates the labels for shape classification and estimates the shape contours that best typify the different shape classes. This resulting iterative algorithm is computationally efficient, simple, and accurate. We demonstrate the utility and performance of this algorithm by applying it to two medical applications.

Algorithms↗
PubMed1996

An enhanced feature extraction algorithm for EMG pattern classification.

We present an enhanced feature extraction algorithm which combines block and adaptive processing to identify motion command for the control of a prosthetic arm. The algorithm is capable of precise and stable feature extraction. A sample application with the block processing stationary model parameters is provided to evaluate the feasibility of the adaptive cepstrum vector extracted by the proposed algorithm for electromyographic (EMG) pattern classification.

Algorithms↗
PubMed2001

Selecting informative genes with parallel genetic algorithms in tissue classification.

Recent advances in biotechnology offer the ability to measure the levels of expression of thousands of genes in parallel. Analysis of such data can provide understanding and insight into gene function and regulatory mechanisms. Several machine learning approaches have been used to aid to understand the functions of genes. However, these tasks are made more difficult due to the noisy nature of array data and the overwhelming number of gene features. In this paper, we use the parallel genetic algorithm to filter out the informative genes relative to classification. By combing with the classification method proposed by Golub et al. and Slonim et al., we classify the data sets with tissues of different classes, and the preliminary results are presented in this paper.

Algorithms↗
PubMed1993

Texture classification and segmentation algorithms in man and machines.

In this paper an attempt is made to review the types of processes developed by the author, and others, to classify and segment textures and to compare, where possible, such algorithms with what has been proposed to occur in human vision. In particular, this paper is concerned with evaluating the proposed constituent processes from a 'cognitive engineering' perspective where, in order to have an adequate model for either human or machine texture processing, complete segmentation or classification or both must be attained.

Algorithms↗
PubMed1996

Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue.

We investigated a new approach to feature selection, and demonstrated its application in the task of differentiating regions of interest (ROIs) on mammograms as either mass or normal tissue. The classifier included a genetic algorithm (GA) for image feature selection, and a linear discriminant classifier or a backpropagation neural network (BPN) for formulation of the classifier outputs. The GA-based feature selection was guided by higher probabilities of survival for fitter combinations of features, where the fitness measure was the area Az under the receiver operating characteristic (ROC) curve. We studied the effect of different GA parameters on classification accuracy, and compared the results to those obtained with stepwise feature selection. The data set used in this study consisted of 168 ROIs containing biopsy-proven masses and 504 ROIs containing normal tissue. From each ROI, a total of 587 features were extracted, of which 572 were texture features and 15 were morphological features. The GA was trained and tested with several different partitionings of the ROIs into training and testing sets. With the best combination of the GA parameters, the average test Az value using a linear discriminant classifier reached 0.90, as compared to 0.89 for stepwise feature selection. Test Az values with a BPN classifier and a more limited feature pool were 0.90 with GA-based feature selection, and 0.89 for stepwise feature selection. The use of a GA in tailoring classifiers with specific design characteristics was also discussed. This study indicates that a GA can provide versatility in the design of linear or nonlinear classifiers without a trade-off in the effectiveness of the selected features.

Algorithms↗
PubMed2004

IRIS II study: the IRIS II score--assessment of a new clinical algorithm for the classification of insulin resistance in patients with Type 2 diabetes.

AIMS: With the increasing availability of new drugs for the treatment of insulin resistance in patients with Type 2 diabetes, simple methods for their identification is an important challenge. The aim of our study was to compute a new algorithm for estimating insulin resistance in a routine clinical setting. METHODS: Clinical data and blood samples were collected from 4265 Type 2 diabetic patients from 149 clinical sites. A clinical algorithm to estimate insulin resistance was developed by stepwise multiple regression analysis. The new generated score was compared with the HOMAIR-score, calculated from fasting insulin and glucose levels measured in a central laboratory. In a subgroup of 48 patients, the score was verified against a frequently sampled intravenous glucose tolerance test with subsequent modified minimal model analysis according to Bergman. RESULTS: Multiple regression analysis revealed fasting blood glucose, BMI, triglycerides and HDL as the most powerful predictors of insulin resistance which were used for further computation of the IRIS II score. A significant overall correlation was found between the HOMAIR-score and the new clinical IRIS II score (r = 0.42; P < 0.0001). Compared with HOMAIR, the new score revealed a specificity of 0.95, a sensitivity of 0.34 and a positive predictive value of 0.95. This was in good agreement with the subset analysis of the intravenous glucose tolerance test, where a sensitivity of 0.37 and a specificity of 0.85 of the IRIS II score was calculated. Patients with insulin resistance according to the IRIS II score revealed an increased odds ratio for overall vascular complications (1.28; 1.11-1.46; P < 0.001). CONCLUSIONS: The new IRIS II score can identify insulin resistance in Type 2 diabetic patients with high predictive value and high specificity.

Algorithms↗
PubMed2000

Mapping a quantitative trait locus via the EM algorithm and Bayesian classification.

Mapping a locus controlling a quantitative genetic trait (e.g., blood pressure) to a specific genomic region is of considerable interest. Data on the quantitative trait under consideration and several codominant genetic markers with known genomic locations are collected from members of families and statistically analyzed to draw inferences on the genomic position of the trait locus. The vector of parameters of interest comprises the pairwise recombination fractions, theta, between the putative quantitative trait locus and the marker loci. One of the major complications in estimating theta for a quantitative trait in humans is the lack of haplotype information on members of families. The purpose of this study was to devise a computationally simple and efficient method of estimation of theta in the absence of haplotype information. We have proposed a two-stage estimation procedure using the expectation-maximization (EM) algorithm. In the first stage, parameters of the QTL are estimated based on data of a sample of unrelated individuals. From estimates thus obtained, we have used a Bayes' rule to infer QTL genotypes of parents in families. Finally, in the second stage of the procedure, we have proposed an EM algorithm for obtaining the maximum likelihood estimate of theta based on data of informative families (which are identified upon inferring parental QTL genotypes performed in the first stage). We have shown, using simulated data, that the proposed procedure is cost-effective, computationally simple, and statistically efficient. As expected, analysis of data on multiple markers jointly is more efficient than the analysis based on single markers.

Algorithms↗