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.

Clinical Use of the Volume-Time Curve for Endotracheal Tube Cuff Management

BACKGROUND: Previous investigation showed that the volume-time curve technique could be an alternative for endotracheal tube (ETT) cuff management. However, the clinical impact of the volume-time curve application has not been documented. the purpose of this study was to compare the occurrence and intensity of a sore throat, cough, thoracic pain, and pulmonary function between these 2 techniques for ETT cuff management: volume-time curve technique versus minimal occlusive volume (MOV) technique after coronary artery bypass grafting. METHODS: A total of 450 subjects were randomized into 2 groups for cuff management after intubation: MOV group (n = 222) and volume-time curve group (n = 228). We measured cuff pressure before extubation. We performed spirometry 24 h before and after surgery. We graded sore throat and cough according to a 4-point scale at 1, 24, 72, and 120 h after extubation and assessed thoracic pain at 24 h after extubation and quantified the level of pain by a 10-point scale. RESULTS: the volume-time curve group presented significantly lower cuff pressure (30.9 +/- 2.8 vs 37.7 +/- 3.4 cm H2O), less incidence and intensity of sore throat (1 h, 23.7 vs 51.4%; and 24 h, 18.9 vs 40.5%, P < .001), cough (1 h, 19.3 vs 48.6%; and 24 h, 18.4 vs 42.3%, P < .001), thoracic pain (5.2 +/- 1.8 vs 7.1 +/- 1.7), better preservation of FVC (49.5 +/- 9.9 vs 41.8 +/- 12.9%, P = .005), and FEV1, (46.6 +/- 1.8 vs 38.6 +/- 1.4%, P = .005) compared with the MOV group. CONCLUSIONS: the subjects who received the volume-time curve technique for ETT cuff management presented a significantly lower incidence and severity of sore throat and cough, less thoracic pain, and minimally impaired pulmonary function than those subjects who received the MOV technique during the first 24 h after coronary artery bypass grafting.

The use of short time-on-stream in situ spectroscopic transient kinetic isotope techniques to investigate the mechanism of hydrocarbon selective catalytic reduction (HC-SCR) of NOx at low temperatures

The problem of differentiating between active and spectator species that have similar infrared spectra has been addressed by developing short time-on-stream in situ spectroscopic transient isotope experimental techniques (STOS-SSITKA). The techniques have been used to investigate the reaction mechanism for the reduction of nitrogen oxides (NOx) by hydrocarbons under lean-burn (excess oxygen) conditions on a silver catalyst. Although a nitrate-type species tracks the formation of isotopically labeled dinitrogen, the results show that this is misleading because a nitrate-type species has the same response to an isotopic switch even under conditions where no dinitrogen is produced. In the case of cyanide and isocyanate species, the results show that it is possible to differentiate between slowly reacting spectator isocyanate species, probably adsorbed on the oxide support, and reactive isocyanate species, possibly on or close to the active silver phase. The reactive isocyanate species responds to an isotope switch at a rate that matches that of the rate of formation of the main product, dinitrogen. It is concluded that these reactive isocyanates could potentially be involved in the reduction of NOx whereas there is no evidence to support the involvement of nitrate-type species that are observable by infrared spectroscopy.

The use of Short Time on Stream (STOS) transient kinetics to investigate the role of hydrogen in enhancing NOx reduction over silver catalysts

The role of hydrogen in promoting the reduction by ammonia of NOx on silver catalysts has been investigated using a Short Time on Stream (STOS) technique to allow differentiation between potentially reactive intermediates and relatively inactive spectator species. Under these conditions, we have used DRIFTS to identify surface nitrate species that are formed and removed on a timescale of seconds. This is in contrast to nitrate species observed under normal steady-state conditions which can continue to form over many tens of minutes. Since this timescale of seconds is very similar to the response rate at which the NH3/NOx to N-2 reaction is accelerated when H-2 is added, or decelerated when H-2 is removed, we conclude that this fast-forming and fast disappearing nitrate species is most probably adsorbed on or close to the active Ag sites. The removal of such a blocking nitrate species from the active sites can explain the effect of H-2 in greatly increasing the rate of the overall de-NOx reaction. 

Use of Short Time-on-Stream Attenuated Total Internal Reflection Infrared Spectroscopy To Probe Changes in Adsorption Geometry for Determination of Selectivity in the Hydrogenation of Citral

Abstract Image

A new experimental procedure based on attenuated total reflection infrared spectroscopy has been developed to investigate surface species under liquid phase reaction conditions. The technique has been tested by investigating the enhanced selectivity in the hydrogenation of α,β-unsaturated aldehyde citral over a 5% Pt/SiO2 catalyst toward unsaturated alcohols geraniol/nerol, which occurs when citronellal is added to the reaction. The change in selectivity is proposed to be the result of a change in the citral adsorption mode in the presence of citronellal. Short time on stream attenuated total internal reflection infrared spectroscopy has allowed identification of the adsorption modes of citral. With no citronellal, citral adsorbs through both the C═C and C═O groups; however, in the presence of citronellal, citral adsorption occurs through the C═O group only, which is proposed to be the cause of the altered reaction selectivity.

Rapid single-nucleotide polymorphism-based identification of clonal Pseudomonas aeruginosa isolates from patients with cystic fibrosis by the use of real-time PCR and high-resolution melting curve analysis

Pseudomonas aeruginosa genotyping relies mainly upon DNA fingerprinting methods, which can be subjective, expensive and time-consuming. The detection of at least three different clonal P. aeruginosa strains in patients attending two cystic fibrosis (CF) centres in a single Australian city prompted the design of a non-gel-based PCR method to enable clinical microbiology laboratories to readily identify these clonal strains. We designed a detection method utilizing heat-denatured P. aeruginosa isolates and a ten-single-nucleotide polymorphism (SNP) profile. Strain differences were detected by SYBR Green-based real-time PCR and high-resolution melting curve analysis (HRM10SNP assay). Overall, 106 P. aeruginosa sputum isolates collected from 74 patients with CF, as well as five reference strains, were analysed with the HRM10SNP assay, and the results were compared with those obtained by pulsed-field gel electrophoresis (PFGE). The HRM10SNP assay accurately identified all 45 isolates as members of one of the three major clonal strains characterized by PFGE in two Brisbane CF centres (Australian epidemic strain-1, Australian epidemic strain-2 and P42) from 61 other P. aeruginosa strains from Australian CF patients and two representative overseas epidemic strain isolates. The HRM10SNP method is simple, is relatively inexpensive and can be completed in <3 h. In our setting, it could be made easily available for clinical microbiology laboratories to screen for local P. aeruginosa strains and to guide infection control policies. Further studies are needed to determine whether the HRM10SNP assay can also be modified to detect additional clonal strains that are prevalent in other CF centres.

Use of the statistical properties of the wavelet-transform coefficients for optimization of integration time in Fourier transform spectrometry

We show that an analysis of the mean and variance of discrete wavelet coefficients of coaveraged time-domain interferograms can be used as a specification for determining when to stop coaveraging. We also show that, if a prediction model built in the wavelet domain is used to determine the composition of unknown samples, a stopping criterion for the coaveraging process can be developed with respect to the uncertainty tolerated in the prediction.

On the use of a time sequence of surface pressures in four-dimensional data assimilation

The possibility of using a time sequence of surface pressure observations in four-dimensional data assimilation is being investigated. It is shown that a linear multilevel quasi-geostrophic model can be updated successfully with surface data alone, provided the number of time levels are at least as many as the number of vertical levels. It is further demonstrated that current statistical analysis procedures are very inefficient to assimilate surface observations, and it is shown by numerical experiments that the vertical interpolation must be carried out using the structure of the most dominating baroclinic mode in order to obtain a satisfactory updating. Different possible ways towards finding a practical solution are being discussed.

Preliminary experimental evaluation of the immediate angiographic occlusion time with use of the AMPLATZER vascular plug II for carotid artery occlusion

Delayed occlusion time in parent artery occlusion of brain-supplying vessels might carry risk for thromboembolic complications. Vascular plug devices are successfully used in cardiopulmonary and peripheral interventions to occlude high-flow lesions and have been adapted for use in neurointerventions. The purpose of the present study was to experimentally evaluate the immediate occlusion time of the AMPLATZER vascular plug (AVP) II-a second-generation cylindrical, self-expandable, resheathable nitinol wire mesh consisting of three lobes-in the carotid artery.

The use of real-time ultrasound imaging for biofeedback of lumbar multifudus muscle contraction in healthy subjects

Study Design: Randomized controlled trial. Objective: To determine if the provision of visual biofeedback using real-time ultrasound imaging enhances the ability to activate the multifidus muscle. Background: Increasingly clinicians are using real-time ultrasound as a form of biofeedback when re-educating muscle activation. The effectiveness of this form of biofeedback for the multifidus muscle has not been reported. Methods and Measures: Healthy subjects were randomly divided into groups that received different forms of biofeedback. All subjects received clinical instruction on how to activate the multifidus muscle isometrically prior to testing and verbal feedback regarding the amount of multifidus contraction, which occurred during 10 repetitions (acquisition phase). In addition, 1 group received visual biofeedback (watched the multifidus muscle contract) using real-time ultrasound imaging. All subjects were reassessed a week later (retention phase). Results: Subjects from both groups improved their voluntary contraction of the multifidus muscle in the acquisition phase (P

Rapid identification and differentiation of Mycobacterium avium subspecies paratuberculosis types by use of real-time PCR and high-resolution melt analysis of the MAP1506 locus

High-resolution melt (HRM) analysis can identify sequence polymorphisms by comparing the melting curves of amplicons generated by real-time PCR amplification. We describe the application of this technique to identify Mycobacterium avium subspecies paratuberculosis types I, II, and III. The HRM approach was based on type-specific nucleotide sequences in MAP1506, a member of the PPE (proline-proline-glutamic acid) gene family.