Application of data mining techniques in the prediction of coronary artery disease : use of anaesthesia time-series and patient risk factor data

The high morbidity and mortality associated with atherosclerotic coronary vascular disease (CVD) and its complications are being lessened by the increased knowledge of risk factors, effective preventative measures and proven therapeutic interventions. However, significant CVD morbidity remains and sudden cardiac death continues to be a presenting feature for some subsequently diagnosed with CVD. Coronary vascular disease is also the leading cause of anaesthesia related complications. Stress electrocardiography/exercise testing is predictive of 10 year risk of CVD events and the cardiovascular variables used to score this test are monitored peri-operatively. Similar physiological time-series datasets are being subjected to data mining methods for the prediction of medical diagnoses and outcomes. This study aims to find predictors of CVD using anaesthesia time-series data and patient risk factor data. Several pre-processing and predictive data mining methods are applied to this data. Physiological time-series data related to anaesthetic procedures are subjected to pre-processing methods for removal of outliers, calculation of moving averages as well as data summarisation and data abstraction methods. Feature selection methods of both wrapper and filter types are applied to derived physiological time-series variable sets alone and to the same variables combined with risk factor variables. The ability of these methods to identify subsets of highly correlated but non-redundant variables is assessed. The major dataset is derived from the entire anaesthesia population and subsets of this population are considered to be at increased anaesthesia risk based on their need for more intensive monitoring (invasive haemodynamic monitoring and additional ECG leads). Because of the unbalanced class distribution in the data, majority class under-sampling and Kappa statistic together with misclassification rate and area under the ROC curve (AUC) are used for evaluation of models generated using different prediction algorithms. The performance based on models derived from feature reduced datasets reveal the filter method, Cfs subset evaluation, to be most consistently effective although Consistency derived subsets tended to slightly increased accuracy but markedly increased complexity. The use of misclassification rate (MR) for model performance evaluation is influenced by class distribution. This could be eliminated by consideration of the AUC or Kappa statistic as well by evaluation of subsets with under-sampled majority class. The noise and outlier removal pre-processing methods produced models with MR ranging from 10.69 to 12.62 with the lowest value being for data from which both outliers and noise were removed (MR 10.69). For the raw time-series dataset, MR is 12.34. Feature selection results in reduction in MR to 9.8 to 10.16 with time segmented summary data (dataset F) MR being 9.8 and raw time-series summary data (dataset A) being 9.92. However, for all time-series only based datasets, the complexity is high. For most pre-processing methods, Cfs could identify a subset of correlated and non-redundant variables from the time-series alone datasets but models derived from these subsets are of one leaf only. MR values are consistent with class distribution in the subset folds evaluated in the n-cross validation method. For models based on Cfs selected time-series derived and risk factor (RF) variables, the MR ranges from 8.83 to 10.36 with dataset RF_A (raw time-series data and RF) being 8.85 and dataset RF_F (time segmented time-series variables and RF) being 9.09. The models based on counts of outliers and counts of data points outside normal range (Dataset RF_E) and derived variables based on time series transformed using Symbolic Aggregate Approximation (SAX) with associated time-series pattern cluster membership (Dataset RF_ G) perform the least well with MR of 10.25 and 10.36 respectively. For coronary vascular disease prediction, nearest neighbour (NNge) and the support vector machine based method, SMO, have the highest MR of 10.1 and 10.28 while logistic regression (LR) and the decision tree (DT) method, J48, have MR of 8.85 and 9.0 respectively. DT rules are most comprehensible and clinically relevant. The predictive accuracy increase achieved by addition of risk factor variables to time-series variable based models is significant. The addition of time-series derived variables to models based on risk factor variables alone is associated with a trend to improved performance. Data mining of feature reduced, anaesthesia time-series variables together with risk factor variables can produce compact and moderately accurate models able to predict coronary vascular disease. Decision tree analysis of time-series data combined with risk factor variables yields rules which are more accurate than models based on time-series data alone. The limited additional value provided by electrocardiographic variables when compared to use of risk factors alone is similar to recent suggestions that exercise electrocardiography (exECG) under standardised conditions has limited additional diagnostic value over risk factor analysis and symptom pattern. The effect of the pre-processing used in this study had limited effect when time-series variables and risk factor variables are used as model input. In the absence of risk factor input, the use of time-series variables after outlier removal and time series variables based on physiological variable values’ being outside the accepted normal range is associated with some improvement in model performance.

Alternative analytical methods for the identification of cancer-related symptom clusters

Advances in symptom management strategies through a better understanding of cancer symptom clusters depend on the identification of symptom clusters that are valid and reliable. The purpose of this exploratory research was to investigate alternative analytical approaches to identify symptom clusters for patients with cancer, using readily accessible statistical methods, and to justify which methods of identification may be appropriate for this context. Three studies were undertaken: (1) a systematic review of the literature, to identify analytical methods commonly used for symptom cluster identification for cancer patients; (2) a secondary data analysis to identify symptom clusters and compare alternative methods, as a guide to best practice approaches in cross-sectional studies; and (3) a secondary data analysis to investigate the stability of symptom clusters over time. The systematic literature review identified, in 10 years prior to March 2007, 13 cross-sectional studies implementing multivariate methods to identify cancer related symptom clusters. The methods commonly used to group symptoms were exploratory factor analysis, hierarchical cluster analysis and principal components analysis. Common factor analysis methods were recommended as the best practice cross-sectional methods for cancer symptom cluster identification. A comparison of alternative common factor analysis methods was conducted, in a secondary analysis of a sample of 219 ambulatory cancer patients with mixed diagnoses, assessed within one month of commencing chemotherapy treatment. Principal axis factoring, unweighted least squares and image factor analysis identified five consistent symptom clusters, based on patient self-reported distress ratings of 42 physical symptoms. Extraction of an additional cluster was necessary when using alpha factor analysis to determine clinically relevant symptom clusters. The recommended approaches for symptom cluster identification using nonmultivariate normal data were: principal axis factoring or unweighted least squares for factor extraction, followed by oblique rotation; and use of the scree plot and Minimum Average Partial procedure to determine the number of factors. In contrast to other studies which typically interpret pattern coefficients alone, in these studies symptom clusters were determined on the basis of structure coefficients. This approach was adopted for the stability of the results as structure coefficients are correlations between factors and symptoms unaffected by the correlations between factors. Symptoms could be associated with multiple clusters as a foundation for investigating potential interventions. The stability of these five symptom clusters was investigated in separate common factor analyses, 6 and 12 months after chemotherapy commenced. Five qualitatively consistent symptom clusters were identified over time (Musculoskeletal-discomforts/lethargy, Oral-discomforts, Gastrointestinaldiscomforts, Vasomotor-symptoms, Gastrointestinal-toxicities), but at 12 months two additional clusters were determined (Lethargy and Gastrointestinal/digestive symptoms). Future studies should include physical, psychological, and cognitive symptoms. Further investigation of the identified symptom clusters is required for validation, to examine causality, and potentially to suggest interventions for symptom management. Future studies should use longitudinal analyses to investigate change in symptom clusters, the influence of patient related factors, and the impact on outcomes (e.g., daily functioning) over time.

Structural health monitoring : vibration-based damage detection and condition assessment of bridges

Structural health is a vital aspect of infrastructure sustainability. As a part of a vital infrastructure and transportation network, bridge structures must function safely at all times. However, due to heavier and faster moving vehicular loads and function adjustment, such as Busway accommodation, many bridges are now operating at an overload beyond their design capacity. Additionally, the huge renovation and replacement costs are a difficult burden for infrastructure owners. The structural health monitoring (SHM) systems proposed recently are incorporated with vibration-based damage detection techniques, statistical methods and signal processing techniques and have been regarded as efficient and economical ways to assess bridge condition and foresee probable costly failures. In this chapter, the recent developments in damage detection and condition assessment techniques based on vibration-based damage detection and statistical methods are reviewed. The vibration-based damage detection methods based on changes in natural frequencies, curvature or strain modes, modal strain energy, dynamic flexibility, artificial neural networks, before and after damage, and other signal processing methods such as Wavelet techniques, empirical mode decomposition and Hilbert spectrum methods are discussed in this chapter.

Expert elicitation and its interface with technology : a review with a view to designing Elicitator

Expert knowledge is valuable in many modelling endeavours, particularly where data is not extensive or sufficiently robust. In Bayesian statistics, expert opinion may be formulated as informative priors, to provide an honest reflection of the current state of knowledge, before updating this with new information. Technology is increasingly being exploited to help support the process of eliciting such information. This paper reviews the benefits that have been gained from utilizing technology in this way. These benefits can be structured within a six-step elicitation design framework proposed recently (Low Choy et al., 2009). We assume that the purpose of elicitation is to formulate a Bayesian statistical prior, either to provide a standalone expert-defined model, or for updating new data within a Bayesian analysis. We also assume that the model has been pre-specified before selecting the software. In this case, technology has the most to offer to: targeting what experts know (E2), eliciting and encoding expert opinions (E4), whilst enhancing accuracy (E5), and providing an effective and efficient protocol (E6). Benefits include: -providing an environment with familiar nuances (to make the expert comfortable) where experts can explore their knowledge from various perspectives (E2); -automating tedious or repetitive tasks, thereby minimizing calculation errors, as well as encouraging interaction between elicitors and experts (E5); -cognitive gains by educating users, enabling instant feedback (E2, E4-E5), and providing alternative methods of communicating assessments and feedback information, since experts think and learn differently; and -ensuring a repeatable and transparent protocol is used (E6).

Receptor-DNA interactions: EMSA and footprinting

Defining the precise promoter DNA sequence motifs where nuclear receptors and other transcription factors bind is an essential prerequisite for understanding how these proteins modulate the expression of their specific target genes. The purpose of this chapter is to provide the reader with a detailed guide with respect to the materials and the key methods required to perform this type of DNA-binding analysis. Irrespective of whether starting with purified DNA-binding proteins or somewhat crude cellular extracts, the tried-and-true procedures described here will enable one to accurately access the capacity of specific proteins to bind to DNA as well as to determine the exact sequences and DNA contact nucleotides involved. For illustrative purposes, we primarily have used the interaction of the androgen receptor with the rat probasin proximal promoter as our model system.

Vulnerability factors for disaster-induced child post-traumatic stress disorder : the case for low family resilience and previous mental illness

Objective: The aim of the present study was to investigate whether parent report of family resilience predicted children’s disaster-induced post-traumatic stress disorder (PTSD) and general emotional symptoms, independent of a broad range of variables including event-related factors, previous child mental illness and social connectedness. ---------- Methods: A total of 568 children (mean age = 10.2 years, SD = 1.3) who attended public primary schools, were screened 3 months after Cyclone Larry devastated the Innisfail region of North Queensland. Measures included parent report on the Family Resilience Measure and Strengths and Difficulties Questionnaire (SDQ)–emotional subscale and child report on the PTSD Reaction Index, measures of event exposure and social connectedness. ---------- Results: Sixty-four students (11.3%) were in the severe–very severe PTSD category and 53 families (28.6%) scored in the poor family resilience range. A lower family resilience score was associated with child emotional problems on the SDQ and longer duration of previous child mental health difficulties, but not disaster-induced child PTSD or child threat perception on either bivariate analysis, or as a main or moderator variable on multivariate analysis (main effect: adjusted odds ratio (ORadj) = 0.57, 95% confidence interval (CI) = 0.13–2.44). Similarly, previous mental illness was not a significant predictor of child PTSD in the multivariate model (ORadj = 0.75, 95%CI = 0.16–3.61). ---------- Conclusion: In this post-disaster sample children with existing mental health problems and those of low-resilience families were not at elevated risk of PTSD. The possibility that the aetiological model of disaster-induced child PTSD may differ from usual child and adolescent conceptualizations is discussed.

Axial length charges during accommodation in myopes and emmetropes

Purpose: To investigate the influence of accommodation upon axial length (and a comprehensive range of ocular biometric parameters), in populations of young adult myopic and emmetropic subjects. Methods: Forty young adult subjects had ocular biometry measured utilizing a non-contact optical biometer (Lenstar LS 900) based upon the principle of optical low coherence reflectometry, under three different accommodation demands (0 D, 3 D and 6 D). Subjects were classified as emmetropes (n=19) or myopes (n=21) based upon their spherical equivalent refraction (mean emmetropic refraction -0.05 ± 0.27DS and mean myopic refraction -1.82 ± 0.84 DS). Results: Axial length changed significantly with accommodation, with a mean increase of 11.9 ± 12.3 µm and 24.1 ± 22.7 µm for the 3 D and 6 D accommodation stimuli respectively. A significant axial elongation associated with accommodation was still evident even following correction of the axial length data for potential error due to lens thickness change. The mean ‘corrected’ increase in axial length was 5.2 ± 11.2 µm, and 7.4 ± 18.9 µm for the 3 D and 6 D stimuli respectively. There was no significant difference between the myopic and emmetropic populations in terms of the magnitude of change in axial length with accommodation, regardless of whether the data were corrected or not. A number of other ocular biometric parameters, such as anterior chamber depth, lens thickness and vitreous chamber depth also exhibited significant change with accommodation. The myopic and emmetropic populations also exhibited no significant difference in the magnitude of change in these parameters with accommodation. Conclusions: The eye undergoes a significant axial elongation associated with a brief period of accommodation, and the magnitude of this change in eye length increases for larger accommodation demands, however there is no significant difference in the magnitude of eye elongation in myopic and emmetropic subjects.

Human optical axial length and defocus

Purpose: To investigate the short term influence of imposed monocular defocus upon human optical axial length (the distance from anterior cornea to retinal pigment epithelium) and ocular biometrics. Methods: Twenty-eight young adult subjects (14 myopes and 14 emmetropes) had eye biometrics measured before and then 30 and 60 minutes after exposure to monocular (right eye) defocus. Four different monocular defocus conditions were tested, each on a separate day: control (no defocus), myopic (+3 D defocus), hyperopic (-3 D defocus) and diffuse (0.2 density Bangerter filter) defocus. The fellow eye was optimally corrected (no defocus). Results: Imposed defocus caused small but significant changes in optical axial length (p<0.0001). A significant increase in optical axial length (mean change +8 ± 14 μm, p=0.03) occurred following hyperopic defocus, and a significant reduction in optical axial length (mean change -13 ± 14 μm, p=0.0001) was found following myopic defocus. A small increase in optical axial length was observed following diffuse defocus (mean change +6 ± 13 μm, p=0.053). Choroidal thickness also exhibited some significant changes with certain defocus conditions. No significant difference was found between myopes and emmetropes in the changes in optical axial length or choroidal thickness with defocus. Conclusions: Significant changes in optical axial length occur in human subjects following 60 minutes of monocular defocus. The bi-directional optical axial length changes observed in response to defocus implies the human visual system is capable of detecting the presence and sign of defocus and altering optical axial length to move the retina towards the image plane.

Exploring retinal and functional markers of diabetic neuropathy

Diabetic peripheral neuropathy (DPN) is one of the most debilitating complications of diabetes. DPN is a major cause of foot ulceration and lower limb amputation. Early diagnosis and management is a key factor in reducing morbidity and mortality. Current techniques for clinical assessment of DPN are relatively insensitive for detecting early disease or involve invasive procedures such as skin biopsies. There is a need for less painful, non-invasive and safe evaluation methods. Eye care professionals already play an important role in the management of diabetic retinopathy; however recent studies have indicated that the eye may also be an important site for the diagnosis and monitoring of neuropathy. Corneal nerve morphology has been shown to be a promising marker of diabetic neuropathy occurring elsewhere in the body, and emerging evidence tentatively suggests that retinal anatomical markers and a range of functional visual indicators could similarly provide useful information regarding neural damage in diabetes – although this line of research is, as yet, less well established. This review outlines the growing body of evidence supporting a potential diagnostic role for retinal structure and visual functional markers in the diagnosis and monitoring of peripheral neuropathy in diabetes.

Limited information estimation and evaluation of DSGE models

We advance the proposition that dynamic stochastic general equilibrium (DSGE) models should not only be estimated and evaluated with full information methods. These require that the complete system of equations be specified properly. Some limited information analysis, which focuses upon specific equations, is therefore likely to be a useful complement to full system analysis. Two major problems occur when implementing limited information methods. These are the presence of forward-looking expectations in the system as well as unobservable non-stationary variables. We present methods for dealing with both of these difficulties, and illustrate the interaction between full and limited information methods using a well-known model.

Diagnostic and treatment pathways for men with prostate cancer in Queensland : investigating spatial and demographic inequalities

Background: Patterns of diagnosis and management for men diagnosed with prostate cancer in Queensland, Australia, have not yet been systematically documented and so assumptions of equity are untested. This longitudinal study investigates the association between prostate cancer diagnostic and treatment outcomes and key area-level characteristics and individual-level demographic, clinical and psychosocial factors.---------- Methods/Design: A total of 1064 men diagnosed with prostate cancer between February 2005 and July 2007 were recruited through hospital-based urology outpatient clinics and private practices in the centres of Brisbane, Townsville and Mackay (82% of those referred). Additional clinical and diagnostic information for all 6609 men diagnosed with prostate cancer in Queensland during the study period was obtained via the population-based Queensland Cancer Registry. Respondent data are collected using telephone and self-administered questionnaires at pre-treatment and at 2 months, 6 months, 12 months, 24 months, 36 months, 48 months and 60 months post-treatment. Assessments include demographics, medical history, patterns of care, disease and treatment characteristics together with outcomes associated with prostate cancer, as well as information about quality of life and psychological adjustment. Complementary detailed treatment information is abstracted from participants’ medical records held in hospitals and private treatment facilities and collated with health service utilisation data obtained from Medicare Australia. Information about the characteristics of geographical areas is being obtained from data custodians such as the Australian Bureau of Statistics. Geo-coding and spatial technology will be used to calculate road travel distances from patients’ residences to treatment centres. Analyses will be conducted using standard statistical methods along with multilevel regression models including individual and area-level components.---------- Conclusions: Information about the diagnostic and treatment patterns of men diagnosed with prostate cancer is crucial for rational planning and development of health delivery and supportive care services to ensure equitable access to health services, regardless of geographical location and individual characteristics. This study is a secondary outcome of the randomised controlled trial registered with the Australian New Zealand Clinical Trials Registry (ACTRN12607000233426)

An investigation of the relationship between subjective sleep quality, loneliness and mood in an Australian sample: Can daily routine explain the links?

Background: Loneliness and low mood are associated with significant negative health outcomes including poor sleep, but the strength of the evidence underlying these associations varies. There is strong evidence that poor sleep quality and low mood are linked, but only emerging evidence that loneliness and poor sleep are associated. Aims: To independently replicate the finding that loneliness and poor subjective sleep quality are associated and to extend past research by investigating lifestyle regularity as a possible mediator of relationships, since lifestyle regularity has been linked to loneliness and poor sleep. Methods: Using a cross-sectional design, 97 adults completed standardized measures of loneliness, lifestyle regularity, subjective sleep quality and mood. Results: Loneliness was a significant predictor of sleep quality. Lifestyle regularity was not a predictor of, nor associated with, mood, sleep quality or loneliness. Conclusions: This study provides an important independent replication of the association between poor sleep and loneliness. However, the mechanism underlying this link remains unclear. A theoretically plausible mechanism for this link, lifestyle regularity, does not explain the relationship between loneliness and poor sleep. The nexus between loneliness and poor sleep is unlikely to be broken by altering the social rhythm of patients who present with poor sleep and loneliness.

Sequence Changes in Six Variants of Rice Tungro Bacilliform Virus and Their Phylogenetic Relationships

The DNA of three biological variants, G1, Ic and G2, which originated from the same greenhouse isolate of rice tungro bacilliform virus (RTBV) at the International Rice Research Institute (IRRI), was cloned and sequenced. Comparison of the sequences revealed small differences in genome sizes. The variants were between 95 and 99% identical at the nucleotide and amino acid levels. Alignment of the three genome sequences with those of three published RTBV sequences (Phi-1, Phi-2 and Phi-3) revealed numerous nucleotide substitutions and some insertions and deletions. The published RTBV sequences originated from the same greenhouse isolate at IRRI 20, 11 and 9 years ago. All open reading frames (ORFs) and known functional domains were conserved across the six variants. The cysteine-rich region of ORF3 showed the greatest variation. When the six DNA sequences from IRRI were compared with that of an isolate from Malaysia (Serdang), similar changes were observed in the cysteine-rich region in addition to other nucleotide substitutions and deletions across the genome. The aligned nucleotide sequences of the IRRI variants and Serdang were used to analyse phylogenetic relationships by the bootstrapped parsimony, distance and maximum-likelihood methods. The isolates clustered in three groups: Serdang alone; Ic and G1; and Phi-1, Phi-2, Phi-3 and G2. The distribution of phylogenetically informative residues in the IRRI sequences shared with the Serdang sequence and the differing tree topologies for segments of the genome suggested that recombination, as well as substitutions and insertions or deletions, has played a role in the evolution of RTBV variants. The significance and implications of these evolutionary forces are discussed in comparison with badnaviruses and caulimoviruses.

Medication warnings about driving : risk perceptions among French and Australian Communities

Increased crash risk is associated with sedative medications and researchers and health-professionals have called for improvements to medication warnings about driving. The tiered warning system in France since 2005 indicates risk level, uses a color-coded pictogram, and advises the user to seek the advice of a doctor before driving. In Queensland, Australia, the mandatory warning on medications that may cause drowsiness advises the user not to drive or operate machinery if they self-assess that they are affected, and calls attention to possible increased impairment when combined with alcohol. Objectives The reported aims of the study were to establish and compare risk perceptions associated with the Queensland and French warnings among medication users. It was conducted to complement the work of DRUID in reviewing the effectiveness of existing campaigns and practice guidelines. Methods Medication users in France and Queensland were surveyed using warnings about driving from both contexts to compare risk perceptions associated with each label. Both samples were assessed for perceptions of the warning that carried the strongest message of risk. The Queensland study also included perceptions of the likelihood of crash and level of impairment associated with the warning. Results Findings from the French study (N = 75) indicate that when all labels were compared, the majority of respondents perceived the French Level-3 label as the strongest warning about risk concerning driving. Respondents in Queensland had significantly stronger perceptions of potential impairment to driving ability, z = -13.26, p <.000 (n = 325), and potential chance of having a crash, z = -11.87, p < .000 (n = 322), after taking a medication that displayed the strongest French warning, compared with the strongest Queensland warning. Conclusions Evidence suggests that warnings about driving displayed on medications can influence risk perceptions associated with use of medication. Further analyses will determine whether risk perceptions influence compliance with the warnings.

Identification of novel markers for uncomplicated lower genital tract infections and upper genital tract pathology due to Chlamydia trachomatis.

Background: Untreated Chlamydia trachomatis infections in women can result in disease sequelae such as salpingitis and pelvic inflammatory disease (PID), ultimately culminating in tubal occlusion and infertility. Whilst nucleic acid amplification tests can effectively diagnose uncomplicated lower genital tract (LGT) infections, they are not suitable for diagnosing upper genital tract (UGT) pathological sequelae. As a consequence, this study aimed to identify serological markers that can, with a high degree of sensitivity and specificity, discriminate between LGT infections and UGT pathology. Methods: Plasma was collected from 73 women with a history of LGT infection, UGT pathology due to C. trachomatis or no serological evidence of C. trachomatis infection. Western blotting was used to analyse antibody reactivity against extracted chlamydial proteins. Sensitivity and specificity of differential markers were also calculated. Results: Four antigens (CT157, CT423, CT727 and CT396) were identified and found to be capable of discriminating between the infection and disease sequelae state. Sensitivity and specificity calculations showed that our assay for diagnosing LGT infection had a sensitivity and specificity of 75% and 76% respectively, whilst the assay for identifying UGT pathology demonstrated 80% sensitivity and 86% specificity. Conclusions: The use of these assays could potentially facilitate earlier diagnoses in women suffering UGT pathology due to C. trachomatis.