SEARCH · PubMed Health

Results for “Multiple Classification Analysis”

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 217 records · Page 12Linked to original sources

PubMed2006

Multiple feature sets based categorization of laryngeal images.

This paper is concerned with an automated analysis of laryngeal images aiming to categorize the images into three decision classes, namely healthy, nodular, and diffuse. The problem is treated as an image analysis and classification task. Aiming to obtain a comprehensive description of laryngeal images, multiple feature sets exploiting information on image colour, texture, geometry, image intensity gradient direction, and frequency content are extracted. A separate support vector machine (SVM) is used to categorize features of each type into the decision classes. The final image categorization is then obtained based on the decisions provided by a committee of support vector machines. Bearing in mind a high similarity of the decision classes, the correct classification rate of over 94% obtained when testing the system on 785 laryngeal images recorded at the Department of Otolaryngology, Kaunas University of Medicine is rather promising.

Algorithms↗

PubMedDate not supplied

A case-based learning approach to grouping cases with multiple malformations.

A case-based classification system can provide assistance to specialists in dysmorphology. This article describes a case-based model designed to assist in identification and retrospective analysis of rare types of syndromes that have proved difficult to diagnose. The primary task of diagnosis is complemented by a learning, or grouping, task. Using data sets of diagnosed cases in related categories of syndromes, we demonstrate how a case-based learning algorithm can extend the retrieval and indexing mechanisms of standard databases to provide a focus for analysis of syndrome classifications.

Abnormalities, Multiple↗

PubMed2005

The maturation of myeloma cells correlates with sensitivity to chemotherapeutic agents.

We analyzed both morphologic and phenotypic findings of myeloma cells before and after chemotherapy in 21 patients with multiple myeloma. The morphologic analysis was based on the Greipp classification, and phenotypic analysis was performed by 3-color flow cytometry using the CD38 plasma gating method (Marrow plasma 38). Results with flow cytometry using a combination of MPC1, CD49e, and CD45 supported the morphologic findings for the myeloma cells. Treatment with 3 or 4 cycles of VAD (vincristine, doxorubicin, and dexamethasone) therapy was effective in reducing the total numbers of myeloma cells, but the proportion of immature myeloma cells increased after this treatment. However, the immature myeloma cells were reduced by high-dose melphalan (HD-Mel) therapy followed by autologous stem cell transplantation (ASCT). High-dose cyclophosphamide treatment for stem cell harvesting did not show an effect on the residual immature myeloma cells after VAD treatment. In addition, thalidomide was not effective in reducing the numbers of immature myeloma cells. These results suggest that VAD (3 or 4 cycles) therapy plus HD-Mel followed by ASCT is a reasonable treatment for multiple myeloma and that Marrow plasma 38 analysis is a useful method for monitoring the response of multiple myeloma to chemotherapy.

ADP-ribosyl Cyclase↗

PubMed1989

The limitations of multivariate statistical methods in the mensuration of human misery.

Multivariate statistical methods have been widely used in the analysis of the multiple symptom data which are routinely collected in psychiatric research on the classification of depressive illnesses. The most commonly used methods, those of factor analysis and discriminant function analysis, were introduced into research on the classification of depressive illness with unreasonably high expectations about what they could achieve. The failure to realize these expectations has produced scepticism in some quarters about the usefulness of multivariate methods in psychiatric research. When evaluated more circumspectly, multivariate statistical methods have made a contribution to our understanding of depressive illnesses, and they will continue to do so, if they are used with more reasonable expectations.

Analysis of Variance↗

PubMed2001

Analysis of risk factors predictive of distant failure after targeted chemoradiation for advanced head and neck cancer.

BACKGROUND: Distant metastasis (DM) is the most common mode of recurrence among patients with advanced head and neck carcinoma treated with intra-arterial cisplatin and radiotherapy (RADPLAT). OBJECTIVE: To identify which patients are at greatest risk for DM and would benefit the most from new strategies designed to treat occult metastases. METHODS: Between 1993 and 1999, 250 patients with advanced head and neck cancer were treated by RADPLAT. Excluded from the analysis were 10 patients who either did not complete the protocol or were unavailable for follow-up and 39 patients with persistent disease or local recurrence. The incidence and the risk factors for DM in these patients were evaluated in a model that included the following factors: age, T and N classification, site of tumor, histologic grade, number (0, 1, or >1) and position (high vs low) of neck levels involved, and bilateral nodal disease. Multiple stepwise logistic regression was used for the analysis. RESULTS: In a univariate analysis, the following variables correlated to DM: N classification (P =.02), site of tumor (P =.01), lower neck nodes (P =.002), number of neck levels involved (P =.001), and bilateral nodal disease (P =.02). In a multivariate analysis, the most significant risk factors for DM were the number of neck levels involved and the site of the primary tumor (P<.001). The highest odds ratios for DM were among patients with multiple levels of nodal involvement (3.17) and patients with hypopharyngeal carcinoma (2.8). CONCLUSIONS: Patients with more than 1 level of clinical nodal involvement and patients with hypopharyngeal carcinoma have the highest risk of developing DM as the initial site of failure and would benefit most from treatment strategies that address occult distant disease.

Adult↗

PubMed1992

Case-mix groups for VA hospital-based home care.

The purpose of this study is to group hospital-based home care (HBHC) patients homogeneously by their characteristics with respect to cost of care to develop alternative case mix methods for management and reimbursement (allocation) purposes. Six Veterans Affairs (VA) HBHC programs in Fiscal Year (FY) 1986 that maximized patient, program, and regional variation were selected, all of which agreed to participate. All HBHC patients active in each program on October 1, 1987, in addition to all new admissions through September 30, 1988 (FY88), comprised the sample of 874 unique patients. Statistical methods include the use of classification and regression trees (CART software: Statistical Software; Lafayette, CA), analysis of variance, and multiple linear regression techniques. The resulting algorithm is a three-factor model that explains 20% of the cost variance (R2 = 20%, with a cross validation R2 of 12%). Similar classifications such as the RUG-II, which is utilized for VA nursing home and intermediate care, the VA outpatient resource allocation model, and the RUG-HHC, utilized in some states for reimbursing home health care in the private sector, explained less of the cost variance and, therefore, are less adequate for VA home care resource allocation.

Aftercare↗

PubMed1985

Biochemical enzyme analysis in acute leukaemia.

This report summarises the current knowledge regarding the clinical utility of biochemical enzyme markers for both diagnostic and therapeutic purposes in acute leukaemia. The enzymes studied most extensively in this field are terminal deoxynucleotidyl transferase, adenosine deaminase, 5'-nucleotidase, purine nucleoside phosphorylase, and acid phosphatase, esterase, hexosaminidase isoenzymes. For each enzyme, the quantitative and qualitative characteristics in various immunologically defined subclasses of acute leukaemia are described. The quantitative evaluation of enzyme activities represents an adjunctive classification technique which should be incorporated into the multivariate analysis, the "multiple marker analysis." By qualitative characterisation pronounced heterogeneity of leukaemia subsets is uncovered. The application of 2'-deoxycoformycin, a specific inhibitor of adenosine deaminase, and the potential usefulness of two other enzymes as targets for treatment with selective agents is discussed. The concept that gene products expressed at certain developmental stages of normal cells can similarly be detected in leukaemic cells (which therefore seem to be "frozen" or "arrested" at this particular maturation/differentiation stage) is supported by the results obtained in enzyme studies. Besides their practical clinical importance for classification and treatment of acute leukaemias, biochemical enzyme markers constitute a valuable research tool to disclose biological properties of leukaemic cells.

5'-Nucleotidase↗

PubMed2005

SELDI-TOF MS profiling of serum for detection of the progression of chronic hepatitis C to hepatocellular carcinoma.

Proteomic profiling of serum is an emerging technique to identify new biomarkers indicative of disease severity and progression. The objective of our study was to assess the use of surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF MS) to identify multiple serum protein biomarkers for detection of liver disease progression to hepatocellular carcinoma (HCC). A cohort of 170 serum samples obtained from subjects in the United States with no liver disease (n = 39), liver diseases not associated with cirrhosis (n = 36), cirrhosis (n = 38), or HCC (n = 57) were applied to metal affinity protein chips for protein profiling by SELDI-TOF MS. Across the four test groups, 38 differentially expressed proteins were used to generate multiple decision classification trees to distinguish the known disease states. Analysis of a subset of samples with only hepatitis C virus (HCV)-related disease was emphasized. The serum protein profiles of control patients were readily distinguished from each HCV-associated disease state. Two-way comparisons of chronic hepatitis C, HCV cirrhosis, or HCV-HCC versus healthy had a sensitivity/specificity range of 74% to 95%. For distinguishing chronic HCV from HCV-HCC, a sensitivity of 61% and a specificity of 76% were obtained. However, when the values of known serum markers alpha fetoprotein, des-gamma carboxyprothrombin, and GP73 were combined with the SELDI peak values, the sensitivity and specifity improved to 75% and 92%, respectively. In conclusion, SELDI-TOF MS serum profiling is able to distinguish HCC from liver disease before cirrhosis as well as cirrhosis, especially in patients with HCV infection compared with other etiologies.

Adult↗

PubMed1996

Multivariate discriminant analysis of the electromyographic interference pattern: statistical approach to discrimination among controls, myopathies and neuropathies.

The stepwise linear discriminant analysis method is used to develop optimal combinations of features measured from the electromyographic interference pattern, with the aim of minimising the misclassification rate in controls while maximising the correct classification rates in patients with disease. This discriminant analysis among multiple groups leads to the determination of the optimal discriminating surface in a multivariable space and can also produce a severity of disease likelihood index. Applying these combinations of features to 186 studies performed in the biceps muscle, 81% of all studies are accurately classified as being normal, myopathic or neuropathic. An algorithm to perform this stepwise multigroup linear discriminant analysis is described.

Diagnosis, Differential↗

PubMed2000

A nationwide, multicenter, case-control study comparing risk factors, treatment, and outcome for vancomycin-resistant and -susceptible enterococcal bacteremia.

National Nosocomial Resistance Surveillance Group participants from 22 hospitals across the United States reviewed medical records for hospitalized patients with vancomycin-resistant enterococcal (VRE) or vancomycin-susceptible enterococcal (VSE) bacteremia to identify risk factors associated with the acquisition of VRE bacteremia, describe genetic traits of VRE strains, and identify factors predictive of clinical outcome. VRE cases were matched to VSE controls within each institution. Multiple logistic regression (LR) and classification and regression tree (CART) analysis were used to probe for factors associated with VRE bacteremia and clinical outcome. A total of 150 matched-pairs of VRE cases and VSE controls were collected from 1995 to 1997. Using LR, the following were found to be highly associated with VRE bacteremia: history of AIDS, positive HIV status, or drug abuse (OR 9.58); prior exposure with parenteral vancomycin (OR 8.37); and liver transplant history (OR 6. 75). CART analysis revealed that isolation of Enterococcus faecium, prior vancomycin exposure, and serum creatinine values > or = 1.1 mg/dl were predictors of VRE bacteremia. Greater proportions of clinical failure (60% versus 40%, P < 0.001) and all-cause mortality (52% versus 27%, P < 0.001) were seen in patients with VRE versus VSE bacteremia. Results from both LR and CART indicated that patients with persisting enterococcal bacteremia, intubation at baseline, higher APACHE II scores, and VRE bacteremia were at greater risk for poor outcome.

APACHE↗

PubMed2026

Genetic diversity and recombination of NA-PRRSV field strains in Vietnam: Implications for vaccine efficacy.

Porcine reproductive and respiratory syndrome (PRRS) causes severe reproductive losses in pregnant sows and piglets, resulting in substantial economic impact on the swine industry worldwide. However, due to the significant genetic diversity and rapid evolutionary changes of the pathogen, continuous surveillance and detailed genetic analysis of circulating strains are essential. The current study aimed to evaluate the genetic diversity of the hypervariable (HV) region of non-structural protein 2 (nsp2) among North American PRRSV strains isolated from swine farms in Vietnam. Phylogenetic analysis and multiple sequence alignment were conducted to determine subtype classification and assess genetic variability. A total of 48 field isolates were obtained, of which 12.5% belonged to classical NA-PRRSV, 16.6% to NADC30-like and 70.9% to HP-PRRSV, primarily distributed across sublineages 1.4, 5.1, 8.7 and 8.9. Amino acid comparisons found multiple insertions, deletions and substitutions at various positions within the hypervariable region of nsp2. The study revealed substantial genetic variation in the HV region of nsp2 among NA-PRRSV field strains, largely associated with recombination and immune escape. These findings highlight epidemiological risks to vaccine efficacy and underscore the need for continuous molecular surveillance to support effective PRRSV control in Vietnam.

PRRSV↗

PubMed2005

Determination of smoking and obesity as periodontitis risks using the classification and regression tree method.

BACKGROUND: A model that focuses on personal risk factors associated with poor lifestyle has been proposed for the etiology of generalized periodontitis. Numerous investigations have linked individual lifestyle-related factors to periodontitis risk; however, a definite relationship among lifestyle-related factors remains unclear. The objective of this study was to determine which lifestyle-related factors demonstrated the greater impact on periodontitis risk. METHODS: The association of lifestyle-related factors, such as smoking status and obesity, with periodontitis was assessed in 372 Japanese workers via a self-administered questionnaire. Smoking status and obesity were evaluated in terms of pack-years and body mass index (BMI), respectively. Clinical periodontal examination included probing depth (PD). The effective impact on periodontitis risk was analyzed by the classification and regression tree (CART) method and multiple logistic regression analysis. RESULTS: Simple logistic regression analyses revealed that factors such as age, gender, alcohol consumption, smoking status, BMI, and frequency of toothbrushing were associated with periodontitis. CART results demonstrated a significant correlation between periodontitis and pack-years, BMI, and age; in contrast, alcohol consumption, gender, and toothbrushing frequency were not correlated with periodontitis. The strongest factor for periodontitis risk was pack-years of smoking. Additionally, both pack-years and BMI exhibited clear dose-response relationships with periodontitis. These relationships were maintained despite adjustment for known confounding factors. CONCLUSIONS: Smoking displays the greatest impact on periodontitis among lifestyle-related factors. Both smoking and obesity are independent risk indicators for periodontitis; moreover, these parameters exhibit a dose-response relationship with respect to periodontitis risk.

Adult↗

PubMed1983

Differential diagnosis of viral, mycoplasmal and bacteraemic pneumococcal pneumonias on admission to hospital.

The hospital records of 150 patients with viral, mycoplasma and bacteraemic pneumococcal pneumonia were analyzed retrospectively to ascertain the discriminative value, regarding the aetiological diagnosis, of the information obtained on admission from the patient history, physical examination, simple laboratory tests and chest X-ray. With stepwise multiple discriminant analysis, the five best variables led to correct classification of 92% of bacteraemic pneumococcal, 88% of mycoplasmal, 76% of viral, and 85% of all pneumonias. Addition of a further nine variables increased the total discriminating capacity to only 89%. The best discriminating variables were the C-reactive protein determination, the presence or absence of predisposing disease or previous antibiotic treatment, the erythrocyte sedimentation rate, the presence of lymphocytosis and the band neutrophile count.

Adult↗

PubMed1997

Calculation of LDL-cholesterol by using apolipoprotein B for classification of nonchylomicronemic dyslipemia.

In this paper we propose a calculation of LDL-cholesterol (LDL-C) not affected by hypertriglyceridemia by using lipid quantities directly measured in total serum. We also propose an algorithm for the classification of nonchylomicronemic dyslipemias. Plasma apolipoproteins (apo) A-I, B, total cholesterol (TC), triglycerides (TG), and cholesterol of lipoproteins were measured in a group of 38 normolipemic and 120 dyslipemic patients (42 phenotype IIa, 38 IIb, and 40 IV) classified according to TG and LDL-C values. Discriminant analysis was applied to obtain the best classification with the lowest number of quantities directly measured from total serum (TC, TG, and apo B), and multiple regression analysis was performed to find an equation to calculate LDL-C from these quantities. Apo B seems to be a useful discriminator between normolipemic and phenotype IIa patients, by using a cutoff value of 1.35 g/L obtained by ROC curve analysis. The proposed algorithm, based on lipid quantities measured by easily automated methods, is shown to be a good alternative for the classification of nonhyperchylomicronemic dyslipemia. LDL-C calculated from TC, TG, and apo B proved a better estimate of true LDL-C than the estimate obtained with Friedewald's formula.

Algorithms↗

PubMed1998

Do groups of women aged 50 to 75 match the national average mammography rate?

CONTEXT: As mammography rates increase, an important question is how closely groups of women match or do not match the national-level, average screening percentage. OBJECTIVE: This study employed a classification-tree methodology to combine individual risk factors from multiple logistic regression, in order to more comprehensively define groups of women less (or more) likely to be screened. DESIGN/SETTING: This report was a secondary data analysis drawing on data from the 1992 National Health Interview Survey, Cancer Control Supplement (NHIS-CCS). PARTICIPANTS: Analyses examined mammography status of women aged 50-75 (n = 1,727). MAIN OUTCOME MEASURE: The dependent variable was having a screening mammogram in the past 2 years. Multiple logistic regression (SUDAAN) was conducted first to select significant correlates of screening. A classification-tree analysis (CHAID subroutine of SPSS) was then used to combine the significant correlates into exclusive and exhaustive subgroups. RESULTS: A total of 13 subgroups were identified, of which only six approximated the overall population screening rate. The lowest screening occurred in small clusters of women, which, when added together, formed a larger percentage of the population who were not screened within the past 2 years. CONCLUSIONS: Efforts to increase mammography may face the challenge of identifying relatively small pockets of women and addressing their individual barriers. Further work should be done to find efficient ways to combine individual risk factors into groups at risk for not being screened.

Aged↗

PubMed1997

A rule-based expert system for the automatic classification of DNA "ploidy" histograms measured by the CAS 200 image analysis system.

DNA "ploidy" histogram interpretation is one of the most important sources of variation in DNA image cytometry and is influenced by multiple technical factors such as scaling, selection of peaks, and variable classification criteria. A rule-based expert system was developed to automate and eliminate subjectivity from this interpretative process. Ninety-eight Feulgen stained histologic sections from patients with breast, colon, and lung cancer were measured with the CAS 200 image analysis system (Becton Dickinson, Santa Clara, CA); they included diploid (n = 42), aneuploid (n = 46), tetraploid (n = 7), and multiploid (n = 3) examples. The data was converted from listmode format into ASCII with the aid of CELLSHEET software (JVC Imaging, Elmhurst, IL). Individual microphotometric nuclear measurements were sorted to one of 64 bins based on DNA index. The 64 bins were then divided into 5 semi-arbitrarily defined ranges: hypodiploid, diploid, aneuploid, tetraploid, and hypertetraploid. The nuclear percentages in each range were calculated with EXCEL 4.0 (Microsoft, Redmond, WA). The histograms were divided into 2 equal sets: training and testing. The data from the training set were used to develop 16 IF-THEN rules to classify the histograms into diploid, aneuploid, or tetraploid. A macro was programmed in EXCEL to automate all these operations. The rule-based expert system classified correctly 45/50 histograms of the training set. Two tetraploid histograms were classified as aneuploid. Three multiploid histograms were classified as tetraploid. All histograms in the testing set were correctly classified by the expert system. The potential role of rule-based expert system technology for the objective classification of DNA "ploidy" histograms measured by image cytometry is discussed.

Automation↗

PubMed1991

Association between neuroepithelial tumor and multiple intestinal polyposis (Turcot's syndrome): report of a case and critical analysis of the literature.

We report a case of association of a brain tumor with multiple intestinal polyposis (Turcot's syndrome) and offer a critical analysis of the relevant literature with a view to revising the classification of the syndrome in relation to familial multiple polyposis and Gardner's syndrome. For this purpose, we considered only cases of intestinal polyposis associated with a primary neuroepithelial tumor (medulloblastoma, glioma, or glioblastoma) as originally described by Turcot. Differences emerged, depending on the central nervous system tumor type, which suggests that this neoplastic association may be classified as two distinct syndromes.

Adenomatous Polyposis Coli↗

PubMed2003

Discriminant validity and relative precision for classifying patients with nonspecific neck and back pain by anatomic pain patterns.

STUDY DESIGN: Secondary analysis of a previously described cohort of prospective, consecutive patients with acute neck or low back pain referred to outpatient rehabilitation was performed. OBJECTIVE: To estimate discriminant validity and relative precision of two classification procedures (first visit vs multiple visit) in discriminating short-term pain intensity and perceived disability outcomes. SUMMARY OF BACKGROUND DATA: Centralization and noncentralization are pain responses used to classify patients and predict outcomes. Different time frames have been proposed for operationally defining these responses, which are problematic for comparing outcomes across clinical trials. Classifying patients according to pain response observed from initial examination (first visit) and over time (multiple visits) influences prevalence within categories and interpretation of classification usefulness, which merits further investigation. METHODS: Patients with acute onset of nonspecific neck or low back pain referred to two outpatient physical therapy clinics completed body pain diagrams, pain intensity ratings, and disability questionnaires at initial evaluation, during each visit, and at discharge. Therapists collected data enabling patient classification on initial examination and throughout treatment. Differences in pain and disability from intake to discharge from rehabilitation across classification categories were used to assess discriminant validity. Relative precision was estimated by determining ratios of analysis of covariance F values between classification procedures for pain and disability. RESULTS: Both classification procedures discriminated categories for change in pain and disability. The multiple-visit classification procedure was more precise for discriminating outcomes than the first-visit classification procedure. CONCLUSION: Multiple-visit classification of patients into specific pain pattern subgroups is recommended when pain intensity and disability outcomes are of interest.

Adult↗