SEARCH · Search PubMed

Results for “classifier”

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.

SourceResearch connectionFrom yearThrough year

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

At least 181 records · Page 10Linked to original sources

PubMed2000

Diagnostic value of perfusion MRI in classifying stroke.

Our study was designed to determine whether supplementary information obtained with perfusion MRI can enhance accuracy. We used delayed perfusion, as represented by time to peak map on perfusion MRI, to classify strokes in 39 patients. Strokes were classified as hemodynamic if delayed perfusion extended to a whole territory of the occluded arterial trunk; as embolic if delayed perfusion was absent or restricted to infarcts; as arteriosclerotic if infarcts were small, multiple, and located mainly in the basal ganglias; or as unclassified if the pathophysiology was unclear. We compared these findings with vascular lesions on cerebral angiography, neurological signs, infarction on MRI, ischemia on xenon-enhanced CT (Xe/CT) and collateral pathway development. Delayed perfusion clearly indicated the area of arterial occlusion. Strokes were classified as hemodynamic in 13 patients, embolic in 14 patients, arteriosclerotic in 6 patients and unclassified in 6 patients. Hemodynamic infarcts were seen only in deep white-matter areas such as the centrum semiovale or corona radiata, whereas embolic infarcts were in the cortex, cortex and subjacent white matter, and lenticulo-striatum. Embolic and arteriosclerotic infarcts occurred even in hemo-dynamically compromised hemispheres. Our findings indicate that perfusion MRI, in association with a detailed analysis of T2-weighted MRI of cerebral infarcts in the axial and coronal planes, can accurately classify stroke as hemodynamic, embolic or arteriosclerotic.

Adult↗

PubMed2000

Artificial neural networks for classifying olfactory signals.

For practical applications, artificial neural networks have to meet several requirements: Mainly they should learn quick, classify accurate and behave robust. Programs should be user-friendly and should not need the presence of an expert for fine tuning diverse learning parameters. The present paper demonstrates an approach using an oversized network topology, adaptive propagation (APROP), a modified error function, and averaging outputs of four networks described for the first time. As an example, signals from different semiconductor gas sensors of an electronic nose were classified. The electronic nose smelt different types of edible oil with extremely different a-priori-probabilities. The fully-specified neural network classifier fulfilled the above mentioned demands. The new approach will be helpful not only for classifying olfactory signals automatically but also in many other fields in medicine, e.g. in data mining from medical databases.

Algorithms↗

PubMed2002

Classification of EEG mental patterns by using two scalp electrodes and Mahalanobis distance-based classifiers.

OBJECTIVES: In this paper, we explored the use of quadratic classifiers based on Mahalanobis distance to detect mental EEG patterns from a reduced set of scalp recording electrodes. METHODS: Electrodes are placed in scalp centro-parietal zones (C3, P3, C4 and P4 positions of the international 10-20 system). A Mahalanobis distance classifier based on the use of full covariance matrix was used. RESULTS: The quadratic classifier was able to detect EEG activity related to imagination of movement with an affordable accuracy (97% correct classification, on average) by using only C3 and C4 electrodes. CONCLUSIONS: Such a result is interesting for the use of Mahalanobis-based classifiers in the brain computer interface area.

Biomedical Engineering↗

PubMed1992

[Left atrial myxomas: clinical characteristics, evaluation and considerations in classifying tumors].

Eleven patients underwent surgical excision for left atrial myxomas. Clinical symptoms, coronary angiographic findings and operative procedures were evaluated. Myxomas were classified into two types based on macroscopical findings, and clinical characteristics of these two types were analyzed. Seven cases (64%) classified as "lobular-type myxomas" were seen as lobulated, gelatinous and fragile. Four cases (36%) were classified as "round-type myxomas" were round and elastic soft. Primary symptoms included dyspnea on exertion in five cases (45%) and neurological disturbances in six cases (55%). Brain emboli were found in four patients by CT scan, and were classified as lobular-type myxomas. These eleven myxomas successfully removed in all cases. Four of these myxomas, which were pedunculated with fine fibrous stalks, were shaved along the base at the atrial septum or free wall. Others were excised completely along with a portion of the adjacent septum. Microscopic examination of the operative specimens revealed that two lobular-type myxomas with broad-based attachment to left atrial septum had invaded the atrial septum. All patients are doing well and have had no signs of myxoma recurrence at postoperative periods ranging from 10 months to 12 years (mean follow-up 5.3 years). Seven patients underwent selective coronary angiography due to a diagnosis of a coronary artery disease. All coronary angiograms were normal in all cases. In five (71%) of these seven, abnormally dilated atrial branches were seen as supplying the tumor. In two cases with round-type myxomas, neovascularity was evident and was made up of clusters of tortuous vessels with tumor blush.(ABSTRACT TRUNCATED AT 250 WORDS)

Adolescent↗

PubMed2005

Glucose-normalized standardized uptake value from (18)F-FDG PET in classifying lymphomas.

UNLABELLED: Our objective was to derive the best glucose sensitivity factor (g-value) and the most discriminating standardized uptake value (SUV) normalized to glucose for classifying indolent and aggressive lymphomas. METHODS: The maximum SUV obtained from (18)F-FDG PET over the area of biopsy in 102 patients was normalized by serum glucose ([Glc]) to a standard of 100 mg/dL. Discriminant analysis was performed by using each SUV(100) (SUV x {100/[Glc]}(g), calculated using various g-values ranging from -3.0 to 0, one at a time) as a variable against the lymphoma grades, and plotting the percentage of correct classifications against g (g-plot) to search for the best g-value in normalizing SUV(100) for classifying grades. To address the influence of the extreme glucose conditions, we repeated the same analyses in 12 patients with [Glc] < or = 70 mg/dL or [Glc] > or = 110 mg/dL. RESULTS: SUV(100) correctly classified lymphoma grades ranging from 62% to 73% (P < 0.0005), depending on the g-value, with a maximum at a g-value of -0.5. For the subgroup with extreme glucose values, the g-plot also revealed higher and more optimal discrimination at a g-value of -0.5 (92%) than at a g-value of 0 (83%) (P = 0.03). The discrimination deteriorated at g < -1 in both analyses. The box plot for all cases using a g-value of -0.5 showed little overlap in classifying lymphoma grades. For a visually selected threshold SUV(100) of 7.25, the sensitivity, specificity, and accuracy of identifying aggressive grades were 82%, 79%, and 81%, respectively. CONCLUSION: The results suggest that metabolic discrimination between lymphoma grades using a glucose-normalized SUV from (18)F-FDG PET is improved by introducing g-value as an extra degree of freedom.

Female↗

PubMedDate not supplied

Chronobiologic pattern discrimination of plasma hormones, notably DHEA-S and TSH, classifies an expansive personality.

Methods of chronobiologic pattern discrimination, a "monotest' involving the leave-one-out technique and a "maximin distance' algorithm for cluster analysis, along with stepwise discriminant analysis procedures and correlation techniques are used in the search for classifiers of personality. By these methods, chronoendocrine relations of an expansive personality are explored in data sampled around the clock in 4 seasons on 10 North American and 3 Japanese women. Of 12 plasma hormones determined in each season, DHEA-S shows a time-dependent relation to an expansive, egocentric personality assessed by an abbreviated version of the Minnesota Multiphasic Personality Inventory; time-dependent co-classifiers are TSH, LH, prolactin and cortisol. Cost-effective recommendations for sampling are thus proposed for further tests of endocrine factors classifying for an expansive personality and, perhaps, classifying also for any associated vulnerability or risk state.

Adolescent↗

PubMed1977

[Perception of schizophrenic patients in classifying pictures of facial expression].

The purpose of this study was to investigate the perception of schizophrenics in classifying pictures of various facial expressions. Schizophrenics were divided into five groups according to the duration of their hospitalization. In the first experiment, subjects were instructed to look at the pictures of three different kinds of facial expressions, anger, delight (laughing) and sadness (crying), and classify them into any categories they like. In comparison with normals, schizophrenics had a difficulty in recognizing the differences in the various facial expressions. In the second experiment, subjects were instructed to look at the same pictures and classify them into three groups of different facial expressions. In this case, schizophrenics were able to classify them almost as well as normals.

Emotions↗

PubMed1998

Automatic classifiers for the interpretation of electrocardiograms.

The morphological diagnosis of ECGs is a pattern recognition procedure. The way the clinician does this is not clearly elucidated. Nevertheless, several models aimed at achieving identical results by automatic means are empleyed. While in the doctor's case this is not exactly so, the computer task for ECG interpretation comprises two distinct and sequential phases: feature extraction and classification. A set of signal measurements containing information for the characterization of the waveform is first obtained. These waveform descriptors are then used to allocate the ECG to one or more diagnostic classes in the classification phase. The classifier can embody rules-of-thumb used by the clinician to decide between conflicting ECG diagnosis and formal or fuzzy logic as a reasoning tool (heuristic classifiers). On the other hand, it can use complex and even abstract signal features as waveform descriptors and different discriminant function models for class allocation (statistical classifiers). More recently, artificial neural network techniques have also been used for signal classification. The authors review feature selection techniques and classification strategies, problems and methods of performance evaluation and results obtained by different classification approaches. A brief discussion of the relative merits of the two main types of ECG classifiers, logical and statistical, is included.

Diagnosis, Computer-Assisted↗

PubMed1999

Classifying individuals based on predictors of random effects. Multicenter AIDS Cohort Study.

Often one wishes to describe individuals according to whether their average exposure over a period of time is above or below some meaningful threshold. In this article, we treat predictors of random effects as diagnostic tools to aid in such classification, given that the true unobservable mean exposure for each of a set of individuals is defined according to a mixed linear model. Viewing candidate predictors in this light engenders the consideration of a unique set of performance criteria, and invites the use of nomenclature commonly used by epidemiologists and decision analysts to evaluate diagnostic techniques. We describe these criteria analytically and graphically under a random effects analysis of variance model, with the expressed goal of classifying subjects with regard to their true mean. Given knowledge of the model parameters, we compare typical predictors and illustrate the fact that completely new alternatives can arise depending on the particular set of criteria emphasized. We include a brief simulation study in which we also compare prediction methods according to various classification criteria, after incorporating estimates of the unknown model parameters. We provide two examples using data from participants in the Multicenter AIDS Cohort Study. In the first example, we seek to classify HIV seronegative individuals based on their mean diastolic blood pressure. In the second, via a natural extension to a randomized regression model, we classify HIV seropositive individuals according to their CD4+ slope over time.

Analysis of Variance↗

PubMed1998

Neo-adjuvant chemotherapy and supracricoid partial laryngectomy with cricohyoidopexy for advanced endolaryngeal carcinoma classified as T3-T4: 5-year oncologic results.

BACKGROUND: Historically, total laryngectomy with voice-prosthesis insertion and near-total laryngectomy were the surgical options advocated for advanced supraglottic and transglottic tumors classified as T3-T4. METHODS: The present retrospective study reviewed our experience with neo-adjuvant chemotherapy and supracricoid partial laryngectomy with cricohyoidopexy (SCPL-CHP) in a series of 60 patients with an isolated, untreated, advanced supraglottic/transglottic invasive squamous cell carcinoma classified as T3-T4. RESULTS: The Kaplan-Meier 5-year actuarial survival, local failure, nodal failure, and distant metastasis estimates were 72.7%, 8.3%, 9.2%, and 9.8%, respectively. Survival was significantly reduced in patients with nodal failure (p = .001) and distant metastasis (p = .007). Overall, a 91.7% laryngeal preservation rate and a 98.3% local control rate were achieved. CONCLUSION: Our report was a retrospective analysis and did not present a control group exclusively managed with SCPL-CHP. Therefore, we were unable to demonstrate that the use of neo-adjuvant chemotherapy prior to SCPL-CHP allowed for an increase in local control, laryngeal preservation, and survival. However, the use of neo-adjuvant chemotherapy allowed for remobilization of a fixed arytenoid cartilage in 10 patients who thus became amenable to SCPL-CHP. The key role of neo-adjuvant chemotherapy in this series was as a prognostic indicator for suitability for SCPL-CHP in the case of supraglottic-transglottic tumor with arytenoid cartilage fixation. Our data also supported the notion that SCPL-CHP is a valid alternative to total laryngectomy with voice prosthesis insertion and near-total laryngectomy in selected patients with a previously untreated supraglottic/transglottic invasive squamous cell carcinoma classified as T3-T4. Furthermore, the successful use (in terms of surgical outcome, laryngeal preservation, and survival) of SCPL-CHP after neo-adjuvant chemotherapy suggested that laryngeal organ-preservation strategies, in advanced endolaryngeal transglottic and/or supraglottic invasive squamous cell carcinoma, should not be limited to the use of laryngeal radiotherapy after neo-adjuvant chemotherapy.

Adult↗

PubMed1994

A clinical trial of continuous cisplatin-fluorouracil induction chemotherapy and supracricoid partial laryngectomy for glottic carcinoma classified as T2.

BACKGROUND: Vertical partial laryngectomy (VPL) and radiation therapy (RT) are the recommended conventional conservative options for glottic carcinoma classified as T2. In series presenting more than 100 patients with a minimum 3-year follow-up, however, local recurrence rates were reported as 22-43.5%. The authors' experience with a new strategy based on continuous cisplatin-fluorouracil induction chemotherapy (IC) and supracricoid partial laryngectomy with cricohyoepiglottopexy (CHEP) is presented. METHODS: A retrospective analysis of 67 patients who presented with untreated moderately to well differentiated invasive glottic carcinoma classified as T2, managed from 1983 to 1991 with IC and CHEP, was conducted. Statistical analysis of survival, local control, nodal control, distant metastasis, and metachronous second primary tumor incidence was based on the Kaplan-Meier actuarial method. Univariate analysis was performed to analyze the relationships between various factors and survival, local recurrence, and nodal recurrence. Clinical response, histologic response, IC toxicity and postoperative course were reported. RESULTS: The Kaplan-Meier 5-year survival, local recurrence, nodal recurrence, distant metastasis, and metachronous second primary tumor estimate were 92.3%, 5.6%, 1.5%, 1.8%, and 5.6%, respectively. Overall laryngeal preservation was achieved in 65 patients (97%). Ultimate local control was achieved in all patients but one. Nodal recurrence was statistically more likely in patients presenting with a local recurrence. Analysis of the specimens demonstrated complete histologic response to IC in 25 (37.3%) patients. A strong statistical relation (P < 0.0001) was noted between complete clinical response after IC and complete histologic response. CONCLUSIONS: The change from the prevailing treatment modalities of RT and VPL to a new multimodal strategy (IC+CHEP) did not decrease survival and allowed for an increase in laryngeal preservation rate. The high rate (37.3%) of complete histologic response suggests that IC deserves further consideration in the management of patients with glottic carcinoma classified as T2. The favorable results achieved in this series, when compared with historic controls, should stimulate prospective clinical trials comparing the two surgical procedures (CHEP vs. VPL with or without IC) for resection of Stage II glottic carcinoma.

Adult↗

PubMed1980

The tradeoff of cell classifier error rates.

In gynecologic cytodiagnosis it is generally agreed that specimen false negative errors are more serious than false positives. When classifying individual cells, however, it is not obvious how one should adjust the parameters that control the two cell error rates. In the case where a specimen classifier follows a cell classifier, one can calculate the sample size required to achieve specified overall performance. This analysis shows that for the small abnormal cell proportions encountered in cervical cytology, cell false positives should be kept so low that a substantial portion of the abnormal cells are missed.

Cervix Uteri↗

PubMed2004

Application of stepwise discriminant analysis to classify commercial orange juices using chiral micellar electrokinetic chromatography-laser induced fluorescence data of amino acids.

The use of chiral amino acids content and stepwise discriminant analysis to classify three types of commercial orange juices (i.e., nectars, orange juices reconstituted from concentrates, and pasteurized orange juices not from concentrates) is presented. Micellar electrokinetic chromatography with laser-induced fluorescence (MEKC-LIF) and beta-cyclodextrins are used to determine L- and D-amino acids previously derivatized with fluorescein isothiocyanate (FITC). This chiral MEKC-LIF procedure is easy to implement and provides information about the main amino acids content in orange juices (i.e., L-proline; L-aspartic acid, D-Asp, L-serine, L-asparagine, L-glutamic acid, D-Glu, L-alanine, L-.arginine, D-Arg, and the non-chiral gamma-amino-n-butyric acid (GABA), i.e., gamma-aminobutyric acid). From these results, it is clearly demonstrated that some D-amino acids occur naturally in orange juices. Application of stepwise discriminant analysis to 26 standard samples showed that the amino acids L-Arg, L-Asp and GABA were the most important variables to differentiate the three groups of samples. With these three selected amino acids a 100% correct classification of the samples was obtained either by standard or by leave-one-out cross-validation procedures. These classification functions based on the content in L-Arg, L-Asp and GABA were also applied to nine test samples and provided an adequate classification and/or interesting information on these samples. It is concluded that chiral MEKC-LIF analysis of amino acids and stepwise discriminant analysis can be used as a consistent procedure to classify commercial orange juices providing useful information about their quality and processing. To our knowledge, this is the first report about the combined use of chiral capillary electrophoresis and discriminant techniques to classify foods.

Amino Acids↗

PubMed2026

The machine-learning classifier ALLCatchR2 identifies 20 T-ALL subtypes across cohorts and age groups.

T-cell acute lymphoblastic leukemia (T-ALL) comprises molecularly diverse subtypes, but robust cross-cohort validations and operational gene-expression definitions are lacking. To establish a gene-expression-anchored framework for T-ALL subtyping, we aggregated 2314 transcriptomes (15 cohorts, age: 0.8-90.8 years). An extended unsupervised approach defined 17 main clusters and 3 subclusters in samples with high blast fractions. Supervised analyses added an overarching immature T-ALL (early T cell precursor [ETP]-like) definition and resolved the LMO2 γδ-like subtype. All clusters contained samples from at least two cohorts. Characteristic genomic driver enrichments were consistent across cohorts, while gene-expression clusters did not correspond exclusively to single driver events but also reflected developmental origins. A machine-learning classifier based on ALLCatchR, our B-cell acute lymphoblastic leukemia (B-ALL) classifier, identified these 20 transcriptomic subtypes and the immature T-ALL (ETP-like) signature with 0.995-1.0 accuracy in a validation set (n = 203). Testing the classifier on a second hold-out data set (n = 265 samples) showed that 92.7% of predictions matched with corresponding driver alterations. Across all samples, 83.2% of cases received high-confidence predictions, 7.3% candidate predictions, and 9.5% remained unclassified, largely because of low blast fractions. We identified a novel gene-expression cluster markedly enriched (P < 0.001) for clonal hematopoiesis mutations (IDH2 R140Q, DNMT3A) and a stem-/progenitor cell-like gene expression. This novel clonal hematopoiesis-related T-ALL subtype was observed in six cohorts and accounted for 8.9% of adults and 39.5% of patients aged >50 years. We extended ALLCatchR into ALLCatchR2, a free R package that now enables B-/T-lineage separation, gene-expression subtyping, blast estimation, and developmental annotation to harmonize T-ALL classification across studies and clinical contexts.

Journal Article↗

PubMedDate not supplied

Quantification of white matter and gray matter volumes from T1 parametric images using fuzzy classifiers.

White matter (WM) and gray matter (GM) were accurately measured using a technique based on a single standardized fuzzy classifier (FC) for each tissue. Fuzzy classifier development was based on experts' visual assessments of WM and GM boundaries from a set of T1 parametric MR images. The fuzzy classifier method's accuracy was validated and optimized by a set of T1 phantom images that were based on hand-detailed human brain cryosection images. Nine sets of axial T1 images of varying thickness equally distributed throughout the brain were simulated. All T1 data sets were mapped to the standardized FCs and rapidly segmented into WM and GM voxel fraction images. Resulting volumes revealed that, in most cases, the difference between measured and actual volumes was less than 5%. This was consistent throughout most of the brain, and as expected, the accuracy improved to generally less than 2% for the 1-mm simulated brain slices.

Artifacts↗

PubMed2005

Frequency of malignancy in lesions classified as probably benign after dynamic contrast-enhanced breast MRI examination.

PURPOSE: To determine the chance of malignancy in lesions classified as "probably benign" by dynamic magnetic resonance imaging (MRI), in a heterogeneous population. MATERIALS AND METHODS: Reports from 473 patients, from March 1994 to March 2002, who underwent breast MRI were retrospectively reviewed. A total of 79 patients (17%) had lesions classified as probably benign after the MRI, which required further imaging follow-up. We evaluated subsequent MRI, mammographic reports, and clinical follow-up in these patients and established the frequency of malignancy in this group. RESULTS: MRI classified probably benign lesion were diagnosed in 79 women because of focal or diffuse mild enhancement and benign dynamic enhancement curves in the area of the mammographic abnormality, or because of the presence of microcalcifications on the mammogram, or because of incidental enhancing lesions. Two-year radiographic and/or clinical follow-up was available in 68 women. On follow-up, four women (6%) were diagnosed with cancer between 14 and 18 months after the initial MRI. CONCLUSION: Patients with a lesion assessed as probably benign by dynamic contrast enhanced MRI have a higher chance of malignancy than patients with probably benign lesions (Breast Imaging Reporting and Data System category 3, BI-RADS 3) seen on mammography. These patients should be informed of the increased risk of cancer and be given the option of biopsy or close follow-up.

Adult↗

PubMed2005

Texture analysis for tissue discrimination on T1-weighted MR images of the knee joint in a multicenter study: Transferability of texture features and comparison of feature selection methods and classifiers.

PURPOSE: To investigate the reproducibility and transferability of texture features between MR centers, and to compare two feature selection methods and two classifiers. MATERIALS AND METHODS: Coronal T1-weighted MR images of the knees of 63 patients, divided into three groups, were included in the study. MR images were obtained at three different MR centers. Regions of interest (ROIs) were drawn in the bone marrow and fat tissue. Then texture analysis (TA) of the ROIs was performed, and the most discriminant features were identified using Fisher coefficients and POE+ACC (probability of classification error and average correlation coefficients). Based on these features, artificial neural network (ANN) and k-nearest-neighbor (k-NN) classifiers were used for tissue discrimination. RESULTS: Although the texture features differed among the MR centers, features from one center could be successfully used for tissue discrimination in texture data on MR images from other centers. The best results were achieved using the ANN classifier in combination with features selected by POE+ACC. CONCLUSION: The differences in texture features extracted from MR images from different centers seem to have only a small impact on the results of tissue discrimination.

Adipose Tissue↗

PubMed2002

Development of a non-invasive strategy to classify bladder outlet obstruction in male patients with LUTS.

To diagnose bladder outlet obstruction in male patients with lower urinary tract symptoms (LUTS), it is necessary to measure the bladder pressure via a transurethral (or suprapubic) catheter. This procedure incurs some risk of urinary tract infection and urethral trauma and is sometimes painful to the patient. We developed an external condom catheter to measure non-invasively the bladder pressure and developed a strategy to classify bladder outlet obstruction (BOO) based on this measurement. Seventy-five patients with a wide range of urological diagnoses underwent a pressure-flow study followed by a non-invasive study. We tested five different strategies to classify the patients using the provisional International Continence Society (ICS) method for definition of obstruction as the gold standard. Leakage of the external catheter occurred in eight (40%) of the first 20 tested patients. In the remaining 55 patients, only five (9%) of the measurements failed because of leakage. Of the 75 patients, 56 were successfully tested non-invasively. According to the ICS nomogram, the PFS showed that 22 of these patients were non-obstructed, 12 patients were equivocal, and 22 patients were obstructed. Ten of these 56 patients strained, and we found that the relatively high abdominal pressures in these patients were not reflected in the externally measured bladder pressure. Of the remaining 46 patients, 12 of 13 non-obstructed patients and 30 of 33 combined equivocal and obstructed patients could be correctly classified. We developed a simple, non-invasive classification strategy to identify BOO in those male patients who did not strain during voiding.

Catheterization↗