Classification of oximetry signals using Bayesian neural networks to assist in the detection of obstructive sleep apnoea syndrome

In the present study, multilayer perceptron (MLP) neural networks were applied to help in the diagnosis of obstructive sleep apnoea syndrome (OSAS). Oxygen saturation (SaO2) recordings from nocturnal pulse oximetry were used for this purpose. We performed time and spectral analysis of these signals to extract 14 features related to OSAS. The performance of two different MLP classifiers was compared: maximum likelihood (ML) and Bayesian (BY) MLP networks. A total of 187 subjects suspected of suffering from OSAS took part in the study. Their SaO2 signals were divided into a training set with 74 recordings and a test set with 113 recordings. BY-MLP networks achieved the best performance on the test set with 85.58% accuracy (87.76% sensitivity and 82.39% specificity). These results were substantially better than those provided by ML-MLP networks, which were affected by overfitting and achieved an accuracy of 76.81% (86.42% sensitivity and 62.83% specificity). Our results suggest that the Bayesian framework is preferred to implement our MLP classifiers. The proposed BY-MLP networks could be used for early OSAS detection. They could contribute to overcome the difficulties of nocturnal polysomnography (PSG) and thus reduce the demand for these studies.

Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis

In this study, a new entropy measure known as kernel entropy (KerEnt), which quantifies the irregularity in a series, was applied to nocturnal oxygen saturation (SaO 2) recordings. A total of 96 subjects suspected of suffering from sleep apnea-hypopnea syndrome (SAHS) took part in the study: 32 SAHS-negative and 64 SAHS-positive subjects. Their SaO 2 signals were separately processed by means of KerEnt. Our results show that a higher degree of irregularity is associated to SAHS-positive subjects. Statistical analysis revealed significant differences between the KerEnt values of SAHS-negative and SAHS-positive groups. The diagnostic utility of this parameter was studied by means of receiver operating characteristic (ROC) analysis. A classification accuracy of 81.25% (81.25% sensitivity and 81.25% specificity) was achieved. Repeated apneas during sleep increase irregularity in SaO 2 data. This effect can be measured by KerEnt in order to detect SAHS. This non-linear measure can provide useful information for the development of alternative diagnostic techniques in order to reduce the demand for conventional polysomnography (PSG). © 2011 IEEE.

The development and investigation of a novel pulsatile heart assist device

Cardiovascular diseases (CVD) contributed to almost 30% of worldwide mortality; with heart failure being one class of CVD. One popular and widely available treatment for heart failure is the intra-aortic balloon pump (IABP). This heart assist device is used in counterpulsation to improve myocardial function by increasing coronary perfusion, and decreasing aortic end-diastolic pressure (i.e. the resistance to blood ejection from the heart). However, this device can only be used acutely, and patients are bedridden. The subject of this research is a novel heart assist treatment called the Chronic Intermittent Mechanical Support (CIMS) which was conceived to offer advantages of the IABP device chronically, whilst overcoming its disadvantages. The CIMS device comprises an implantable balloon pump, a percutaneous drive line, and a wearable driver console. The research here aims to determine the haemodynamic effect of balloon pump activation under in vitro conditions. A human mock circulatory loop (MCL) with systemic and coronary perfusion was constructed, capable of simulating various degrees of heart failure. Two prototypes of the CIMS balloon pump were made with varying stiffness. Several experimental factors (balloon inflation/deflation timing, Helium gas volume, arterial compliance, balloon pump stiffness and heart valve type) form the factorial design experiments. A simple modification to the MCL allowed flow visualisation experiments using video recording. Suitable statistical tests were used to analyse the data obtained from all experiments. Balloon inflation and deflation in the ascending aorta of the MCL yielded favourable results. The sudden balloon deflation caused the heart valve to open earlier, thus causing longer valve opening duration in a cardiac cycle. It was also found that pressure augmentation in diastole was significantly correlated with increased cardiac output and coronary flowrate. With an optimum combination (low arterial compliance and low balloon pump stiffness), systemic and coronary perfusions were increased by 18% and 21% respectively, while the aortic end-diastolic pressure (forward flow resistance) decreased by 17%. Consequently, the ratio of oxygen supply and demand to myocardium (endocardial viability ratio, EVR) increased between 33% and 75%. The increase was mostly attributed to diastolic augmentation rather than systolic unloading.

An overview of Total Factor Productivity estimations adjusted for pollutant outputs:an application to sugarcane farming

The conventional Total Factor Productivity (TFP) measurement does not incorporate the effects of undesirable outputs, which are harmful to the environment. Using sugarcane farming in Kenya, this paper illustrates the differences between the conventional Malmquist index measures where the environment variable is not adjusted and environment-adjusted measures using both hyperbolic and directional distance functions. The mean TFP change estimates for the conventional Malmquist index, adjusted hyperbolic index and Luenberger indicator were 3.13%, 0.11% and 2.21%, respectively. The conventional non-adjusted measure lies between the two adjusted measures of hyperbolic index and Luenberger indicator. © 2012 Inderscience Enterprises Ltd.

The 'law of requisite variety' may assist climate change negotiations:a review of the Kyoto and Durban meetings

Ashby wrote about cybernetics, during which discourse he described a Law that attempts to resolve difficulties arising in complex situations – he suggested using variety to combat complexity. In this paper, we note that the delegates to the UN Framework Convention on Climate Change (UNFCCC) meeting in Kyoto, 1997, were offered a ‘simplifying solution’ to cope with the complexity of discussing multiple pollutants allegedly contributing to ‘climate change’. We assert that the adoption of CO2eq has resulted in imprecise thinking regarding the ‘carbon footprint’ – that is, ‘CO2’ – to the exclusion of other pollutants. We propose, as Ashby might have done, that the CO2eq and other factors within the ‘climate change’ negotiations be disaggregated to allow careful and specific individual solutions to be agreed on each factor. We propose a new permanent and transparent ‘action group’ be in charge of agenda setting and to manage the messy annual meetings. This body would be responsible for achieving accords at these annual meetings, rather than forcing this task on national hosts. We acknowledge the task is daunting and we recommend moving on from Ashby's Law to Beer's Viable Systems approach.

Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome

The relationship between sleep apnoea–hypopnoea syndrome (SAHS) severity and the regularity of nocturnal oxygen saturation (SaO2) recordings was analysed. Three different methods were proposed to quantify regularity: approximate entropy (AEn), sample entropy (SEn) and kernel entropy (KEn). A total of 240 subjects suspected of suffering from SAHS took part in the study. They were randomly divided into a training set (96 subjects) and a test set (144 subjects) for the adjustment and assessment of the proposed methods, respectively. According to the measurements provided by AEn, SEn and KEn, higher irregularity of oximetry signals is associated with SAHS-positive patients. Receiver operating characteristic (ROC) and Pearson correlation analyses showed that KEn was the most reliable predictor of SAHS. It provided an area under the ROC curve of 0.91 in two-class classification of subjects as SAHS-negative or SAHS-positive. Moreover, KEn measurements from oximetry data exhibited a linear dependence on the apnoea–hypopnoea index, as shown by a correlation coefficient of 0.87. Therefore, these measurements could be used for the development of simplified diagnostic techniques in order to reduce the demand for polysomnographies. Furthermore, KEn represents a convincing alternative to AEn and SEn for the diagnostic analysis of noisy biomedical signals.

The application of laser welding on Left Ventricular Assist Device (LVAD)

A successful and useful treatment for end-stage heart failure is Left ventricular assist device (LVAD). An important part - a hydrodynamically suspended impeller exposed to corrosive conditions, required to sealed hermetically into micro packages. Laser beam welded (LBW) Ti6Al4V alloy has been adopted in anti-corrosion micro packages for the impeller of a (LVAD). Thin and narrow welds were required for such medical equipment. Pulsed Nd:YAG welding was successfully adopted as sealing method for the impeller. ©2011 IEEE.