Improved fault diagnosis in multivariate systems using regression-based reconstruction

Subspace monitoring has recently been proposed as a condition monitoring tool that requires considerably fewer variables to be analysed compared to dynamic principal component analysis (PCA). This paper analyses subspace monitoring in identifying and isolating fault conditions, which reveals that the existing work suffers from inherent limitations if complex fault senarios arise. Based on the assumption that the fault signature is deterministic while the monitored variables are stochastic, the paper introduces a regression-based reconstruction technique to overcome these limitations. The utility of the proposed fault identification and isolation method is shown using a simulation example and the analysis of experimental data from an industrial reactive distillation unit.

The impact of biomarkers in multivariate algorithms for bladder cancer diagnosis in patients with hematuria

BACKGROUND: We appraised 23 biomarkers previously associated with urothelial cancer in a case-control study. Our aim was to determine whether single biomarkers and/or multivariate algorithms significantly improved on the predictive power of an algorithm based on demographics for prediction of urothelial cancer in patients presenting with hematuria. METHODS: Twenty-two biomarkers in urine and carcinoembryonic antigen (CEA) in serum were evaluated using enzyme-linked immunosorbent assays (ELISAs) and biochip array technology in 2 patient cohorts: 80 patients with urothelial cancer, and 77 controls with confounding pathologies. We used Forward Wald binary logistic regression analyses to create algorithms based on demographic variables designated prior predicted probability (PPP) and multivariate algorithms, which included PPP as a single variable. Areas under the curve (AUC) were determined after receiver-operator characteristic (ROC) analysis for single biomarkers and algorithms. RESULTS: After univariate analysis, 9 biomarkers were differentially expressed (t test; P

Comorbidities and current smoking status amongst patients starting renal replacement therapy in England, Wales and Northern Ireland from 2003 to 2008: national and centre-specific analyses

Introduction: The prevalence of comorbidities in incident renal replacement therapy (RRT) patients changes with age and varies between ethnic groups. This study describes these associations and the independent effect of comorbidities on outcomes. Methods: Adult patients starting RRT between 2003 and 2008 in centres reporting to the UK Renal Registry (UKRR) with data on comorbidity (n ¼ 14,909) were included. The UKRR studied the association of comorbidity with patient demographics, treatment modality, haemoglobin, renal function at start of RRT and subsequent listing for kidney transplantation. The relationship between comorbidities and mortality at 90 days and one year after 90 days from start of RRT was explored using Cox regression. Results: Completeness of comorbidity data was 40.0% compared with 54.3% in 2003. Of patients with data, 53.8% had one or more comorbidities. Diabetes mellitus and ischaemic heart disease were the most common conditions seen in 30.1% and 22.7% of patients respectively. Current smoking was recorded for 14.5% of incident RRT patients in the 6-year period. Comorbidities became more common with increasing age in all ethnic groups although the difference between the 65–74 and 75+ age groups was not significant. Within each age group, South Asians and Blacks had lower rates of comorbidity, despite higher rates of diabetes mellitus. In multivariate survival analysis, malignancy and ischaemic/neuropathic ulcers were the strongest independent predictors of poor survival at 1 year after 90 days from the start of RRT. Conclusion: Differences in prevalence of comorbid illnesses in incident RRT patients may reflect variation in access to health care or competing risk prior to commencing treatment. At the same time, smoking rates remained high in this ‘at risk’ population. Further work on this and ways to improve comorbidity reporting should be priorities for 2010–11.

Gene Sets Net Correlations Analysis (GSNCA): a multivariate differential coexpression test for gene sets

Motivation: To date, Gene Set Analysis (GSA) approaches primarily focus on identifying differentially expressed gene sets (pathways). Methods for identifying differentially coexpressed pathways also exist but are mostly based on aggregated pairwise correlations, or other pairwise measures of coexpression. Instead, we propose Gene Sets Net Correlations Analysis (GSNCA), a multivariate differential coexpression test that accounts for the complete correlation structure between genes.

Results: In GSNCA, weight factors are assigned to genes in proportion to the genes' cross-correlations (intergene correlations). The problem of finding the weight vectors is formulated as an eigenvector problem with a unique solution. GSNCA tests the null hypothesis that for a gene set there is no difference in the weight vectors of the genes between two conditions. In simulation studies and the analyses of experimental data, we demonstrate that GSNCA, indeed, captures changes in the structure of genes' cross-correlations rather than differences in the averaged pairwise correlations. Thus, GSNCA infers differences in coexpression networks, however, bypassing method-dependent steps of network inference. As an additional result from GSNCA, we define hub genes as genes with the largest weights and show that these genes correspond frequently to major and specific pathway regulators, as well as to genes that are most affected by the biological difference between two conditions. In summary, GSNCA is a new approach for the analysis of differentially coexpressed pathways that also evaluates the importance of the genes in the pathways, thus providing unique information that may result in the generation of novel biological hypotheses.

Multivariate analysis of regional-scale geochemical data for environmental monitoring

A compositional multivariate approach is used to analyse regional scale soil geochemical data obtained as part of the Tellus Project generated by the Geological Survey Northern Ireland (GSNI). The multi-element total concentration data presented comprise XRF analyses of 6862 rural soil samples collected at 20cm depths on a non-aligned grid at one site per 2 km2. Censored data were imputed using published detection limits. Using these imputed values for 46 elements (including LOI), each soil sample site was assigned to the regional geology map provided by GSNI initially using the dominant lithology for the map polygon. Northern Ireland includes a diversity of geology representing a stratigraphic record from the Mesoproterozoic, up to and including the Palaeogene. However, the advance of ice sheets and their meltwaters over the last 100,000 years has left at least 80% of the bedrock covered by superficial deposits, including glacial till and post-glacial alluvium and peat. The question is to what extent the soil geochemistry reflects the underlying geology or superficial deposits. To address this, the geochemical data were transformed using centered log ratios (clr) to observe the requirements of compositional data analysis and avoid closure issues. Following this, compositional multivariate techniques including compositional Principal Component Analysis (PCA) and minimum/maximum autocorrelation factor (MAF) analysis method were used to determine the influence of underlying geology on the soil geochemistry signature. PCA showed that 72% of the variation was determined by the first four principal components (PC’s) implying “significant” structure in the data. Analysis of variance showed that only 10 PC’s were necessary to classify the soil geochemical data. To consider an improvement over PCA that uses the spatial relationships of the data, a classification based on MAF analysis was undertaken using the first 6 dominant factors. Understanding the relationship between soil geochemistry and superficial deposits is important for environmental monitoring of fragile ecosystems such as peat. To explore whether peat cover could be predicted from the classification, the lithology designation was adapted to include the presence of peat, based on GSNI superficial deposit polygons and linear discriminant analysis (LDA) undertaken. Prediction accuracy for LDA classification improved from 60.98% based on PCA using 10 principal components to 64.73% using MAF based on the 6 most dominant factors. The misclassification of peat may reflect degradation of peat covered areas since the creation of superficial deposit classification. Further work will examine the influence of underlying lithologies on elemental concentrations in peat composition and the effect of this in classification analysis.

Alcoholic Beverage Preference and Dietary Habits in Elderly across Europe: Analyses within the Consortium on Health and Ageing: Network of Cohorts in Europe and the United States (CHANCES) Project

INTRODUCTION: The differential associations of beer, wine, and spirit consumption on cardiovascular risk found in observational studies may be confounded by diet. We described and compared dietary intake and diet quality according to alcoholic beverage preference in European elderly.

METHODS: From the Consortium on Health and Ageing: Network of Cohorts in Europe and the United States (CHANCES), seven European cohorts were included, i.e. four sub-cohorts from EPIC-Elderly, the SENECA Study, the Zutphen Elderly Study, and the Rotterdam Study. Harmonized data of 29,423 elderly participants from 14 European countries were analyzed. Baseline data on consumption of beer, wine, and spirits, and dietary intake were collected with questionnaires. Diet quality was assessed using the Healthy Diet Indicator (HDI). Intakes and scores across categories of alcoholic beverage preference (beer, wine, spirit, no preference, non-consumers) were adjusted for age, sex, socio-economic status, self-reported prevalent diseases, and lifestyle factors. Cohort-specific mean intakes and scores were calculated as well as weighted means combining all cohorts.

RESULTS: In 5 of 7 cohorts, persons with a wine preference formed the largest group. After multivariate adjustment, persons with a wine preference tended to have a higher HDI score and intake of healthy foods in most cohorts, but differences were small. The weighted estimates of all cohorts combined revealed that non-consumers had the highest fruit and vegetable intake, followed by wine consumers. Non-consumers and persons with no specific preference had a higher HDI score, spirit consumers the lowest. However, overall diet quality as measured by HDI did not differ greatly across alcoholic beverage preference categories.

DISCUSSION: This study using harmonized data from ~30,000 elderly from 14 European countries showed that, after multivariate adjustment, dietary habits and diet quality did not differ greatly according to alcoholic beverage preference.

Genetically monomorphic brown trout (Salmo trutta L.) populations as revealed by mitochondrial DNA, multi-locus and single-locus minisatellite (VNTR) analyses.

Normally, populations of brown trout are genetically highly variable. Two adjacent populations from NW Scotland, which had previously been found to be monomorphic for 46 protein-coding loci, were studied by higher resolution techniques. Analyses of mitochondrial DNA, multilocus DNA fingerprints and eight specific minisatellite loci revealed no genetic variation among individuals or genetic differences between the two populations. Continual low effective population sizes or severe repeated bottlenecks, as a result of low or variable recruitment, probably explain the atypical absence of genetic variation in these trout populations. Growth data do not provide any evidence of a reduction in fitness in trout from these populations.

Fault Diagnosis in Internal Combustion Engines Using Nonlinear Multivariate Statistics

This paper presents a statistical-based fault diagnosis scheme for application to internal combustion engines. The scheme relies on an identified model that describes the relationships between a set of recorded engine variables using principal component analysis (PCA). Since combustion cycles are complex in nature and produce nonlinear relationships between the recorded engine variables, the paper proposes the use of nonlinear PCA (NLPCA). The paper further justifies the use of NLPCA by comparing the model accuracy of the NLPCA model with that of a linear PCA model. A new nonlinear variable reconstruction algorithm and bivariate scatter plots are proposed for fault isolation, following the application of NLPCA. The proposed technique allows the diagnosis of different fault types under steady-state operating conditions. More precisely, nonlinear variable reconstruction can remove the fault signature from the recorded engine data, which allows the identification and isolation of the root cause of abnormal engine behaviour. The paper shows that this can lead to (i) an enhanced identification of potential root causes of abnormal events and (ii) the masking of faulty sensor readings. The effectiveness of the enhanced NLPCA based monitoring scheme is illustrated by its application to a sensor fault and a process fault. The sensor fault relates to a drift in the fuel flow reading, whilst the process fault relates to a partial blockage of the intercooler. These faults are introduced to a Volkswagen TDI 1.9 Litre diesel engine mounted on an experimental engine test bench facility.

Behavioural and histopathological analyses of ibuprofen treatment on the effect of aggregated AB (1-42) injections in the rat

It has been suggested that inflammatory processes may play a role in the development of Alzheimerâ??s disease (AD), and that nonsteroidal anti-inflammatory drug treatments may provide protection against the onset of AD. In the current study male Wistar rats were trained in two-lever operant chambers under an alternating lever cyclic-ratio ratio (ALCR) schedule. When responding showed no trends, subjects were divided into groups. One group was bilaterally injected into the CA3 area of the hippocampus with 5 μl of aggregated β-amyloid (Aβ) suspension, and one group was bilaterally injected into the CA3 area of the hippocampus with 5 μl of sterile saline. Subgroups were treated twice daily with 0.1 ml (40 mg/kg) ibuprofen administered orally. The results indicated that chronic administration of ibuprofen protected against detrimental behavioural effects following aggregated Aβ injections. Withdrawal of ibuprofen treatment from aggregated Aβ-injected subjects produced a decline in behavioural performance to the level of the non-treated aggregated Aβ-injected group. Ibuprofen treatment reduced the numbers of reactive astrocytes following aggregated Aβ injection, and withdrawal of ibuprofen resulted in an increase of reactive astrocytes. These results suggest that induced inflammatory processes may play a role in AD, and that ibuprofen treatment may protect against some of the symptoms seen in AD.

The SPHERE Study: Secondary prevention of heart disease in general practice: protocol of a randomised controlled trial of tailored practice and patient care plans with parallel qualitative, economic and policy analyses. [ISRCTN24081411]

Background: The aim of the SPHERE study is to design, implement and evaluate tailored practice and personal care plans to improve the process of care and objective clinical outcomes for patients with established coronary heart disease (CHD) in general practice across two different health systems on the island of Ireland.CHD is a common cause of death and a significant cause of morbidity in Ireland. Secondary prevention has been recommended as a key strategy for reducing levels of CHD mortality and general practice has been highlighted as an ideal setting for secondary prevention initiatives. Current indications suggest that there is considerable room for improvement in the provision of secondary prevention for patients with established heart disease on the island of Ireland. The review literature recommends structured programmes with continued support and follow-up of patients; the provision of training, tailored to practice needs of access to evidence of effectiveness of secondary prevention; structured recall programmes that also take account of individual practice needs; and patient-centred consultations accompanied by attention to disease management guidelines.

Methods: SPHERE is a cluster randomised controlled trial, with practice-level randomisation to intervention and control groups, recruiting 960 patients from 48 practices in three study centres (Belfast, Dublin and Galway). Primary outcomes are blood pressure, total cholesterol, physical and mental health status (SF-12) and hospital re-admissions. The intervention takes place over two years and data is collected at baseline, one-year and two-year follow-up. Data is obtained from medical charts, consultations with practitioners, and patient postal questionnaires. The SPHERE intervention involves the implementation of a structured systematic programme of care for patients with CHD attending general practice. It is a multi-faceted intervention that has been developed to respond to barriers and solutions to optimal secondary prevention identified in preliminary qualitative research with practitioners and patients. General practitioners and practice nurses attend training sessions in facilitating behaviour change and medication prescribing guidelines for secondary prevention of CHD. Patients are invited to attend regular four-monthly consultations over two years, during which targets and goals for secondary prevention are set and reviewed. The analysis will be strengthened by economic, policy and qualitative components.