Search

The measure went of anaesthetic depth during surgical anaesthesia has always been an inexact science where the experience of the anaesthetist is called upon to provide the control of drug administration. The anaesthetist has to maintain the patient at a suitable level of sedation by carefully controlling several anaesthetic drugs so that the surgical procedure can proceed without causing awareness in the patient. There have been many publications on the subject that have shed much light on the subject and which has as a result improved the control of anaesthetic depth.

The complexity of biological systems, unlike physical science applications, makes the development of computerised systems for medicine not a straightforward algorithmic solution because of the inherent uncertainty which arises as a natural occurrence in these types of applications. Human minds work from approximate data, extract meaningful information from massive data, and produce crisp solutions. Fuzzy logic provides a suitable basis for the ability to summarise and extract from masses of data impinging upon the human brain those facts that are related to the performance of the task at hand. In practice, a precise model may not exist for biological systems or it may be too difficult to model. In these cases fuzzy logic is considered as an appropriate tool for modelling and control, since our knowledge and experience are directly contained and presented in control strategies without explicit mathematical models. This paper surveys the utilisation of fuzzy logic in medical sciences, with an analysis of its possible future penetration. An application involving fuzzy reasoning and control paradigms in anaesthesia is described in some detail.

In multivariable control the study of loop interactions is of prime importance. The P or V-canonical form structures, where loop interactions are dealt with as feed-forward couplings, are popular transfer function representations used to describe multivariable processes. Another alternative design consists of a bank of several Single Input Single Output (SISO) controllers linked by feed-forward terms representing in fact the interactions as disturbances. This is the focus of this paper which proposes a new long-range predictive control algorithm for multivariable processes with feed-forward based on the popular Generalised Predictive Control (GPC) algorithm but using a Takagi-Sugeno Kang (TSK) piece-wise fuzzy modelling approach. To improve estimation a Long Range Predictive Identification (LRPI) algorithm for fuzzy modelling is also integrated within the approach. The performance of the adaptive control scheme is assessed using a series of experiments on the binary distillation column. The new proposed algorithm with a fuzzy model is shown to be more robust than the standard GPC algorithm which uses a crisp CARIMA model in terms of handling loop interactions.

Optical interference filters that have continuously modulated refractive indices throughout their thickness (rugates) are designed and fabricated using microwave plasma-assisted chemical vapour deposition techniques. Intelligent modelling and control techniques using on-line GA are described in this paper for modelling the process and improving the making of reflection filters.

A multi-sensor fusion system for monitoring and control depth of anaesthesia in the operating theatre, is described. Two types of anaesthesia measures were considered, the first is based on auditory evoked brain potentials, while the second measure is based on cardiovascular system signals. The first measure is based on analyses of the signal using wavelets and neuro-fuzzy inference, while the second measure is based on analysis of the measurements using rule-based fuzzy logic. The two measures are combined via fuzzy logic to give a final level of depth of anaesthesia. The depth of anaesthesia level is fed back to a Target Controlled Infusion System (TCI) for controlling the infusion of the drug propofol for maintaining a constant level of depth of anaesthesia.

This is the post-print version of the article. The official published version can be accessed from the link below. A multi-objective genetic algorithm is developed for the purpose of optimizing the rule-base of a Self-Organising Fuzzy Logic Control algorithm (SOFLC). The tuning of the SOFLC optimization is based on selection of the best shaped performance index for modifying the rule-base on-line. A comparative study is conducted between various methods of multi-objective genetic optimisation using the SOFLC algorithm on the muscle relaxant anaesthesia system, which includes a severe non-linearity, varying dynamics and time-delay.

This is the post-print version of the article. The official published version can be obtained from the link below. We describe the design process of a diagnostic system for monitoring the anaesthetic state of patients during surgical interventions under general anaesthesia. Mid-latency auditory evoked potentials (MLAEPs) obtained during general anaesthesia are used to design a neuro-fuzzy system for the determination of the level of unconsciousness after feature extraction using multiresolution wavelet analysis (MRWA). The neuro-fuzzy system proves to be a useful tool in eliciting knowledge for the fuzzy system: the anaesthetist's expertise is indirectly coded in the knowledge rule-base through the learning process with the training data. The anaesthetic depth of the patient, as deduced by the anaesthetist from the clinical signs and other haemodynamic variables, noted down during surgery, is subsequently used to label the MLAEP data accordingly. This anaesthetist-labelled data, used to train the neuro-fuzzy system, is able to produce a classifier that successfully interprets unseen data recorded from other patients. This system is not limited, however, to the combination of drugs used here. Indeed, the similar effects of inhalational and analgesic anaesthetic drugs on the MLAEPs demonstrate that the system could potentially be used for any anaesthetic and analgesic drug combination. We also suggest the use of a closed-loop architecture that would automatically provide the drug profile necessary to maintain the patient at a safe level of sedation.

Background Osteoporotic hip fractures with a significant morbidity and excess mortality among the elderly have imposed huge health and economic burdens on societies worldwide. In this age- and sex-matched case control study, we examined the risk factors of hip fractures and assessed the fracture risk by conditional logistic regression (CLR) and ensemble artificial neural network (ANN). The performances of these two classifiers were compared. Methods The study population consisted of 217 pairs (149 women and 68 men) of fractures and controls with an age older than 60 years. All the participants were interviewed with the same standardized questionnaire including questions on 66 risk factors in 12 categories. Univariate CLR analysis was initially conducted to examine the unadjusted odds ratio of all potential risk factors. The significant risk factors were then tested by multivariate analyses. For fracture risk assessment, the participants were randomly divided into modeling and testing datasets for 10-fold cross validation analyses. The predicting models built by CLR and ANN in modeling datasets were applied to testing datasets for generalization study. The performances, including discrimination and calibration, were compared with non-parametric Wilcoxon tests. Results In univariate CLR analyses, 16 variables achieved significant level, and six of them remained significant in multivariate analyses, including low T score, low BMI, low MMSE score, milk intake, walking difficulty, and significant fall at home. For discrimination, ANN outperformed CLR in both 16- and 6-variable analyses in modeling and testing datasets (p? Conclusions The risk factors of hip fracture are more personal than environmental. With adequate model construction, ANN may outperform CLR in both discrimination and calibration. ANN seems to have not been developed to its full potential and efforts should be made to improve its performance.

"Copyright © 2012 Maysam Abbod et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited." The purpose of this special issue is to promote research and developments of the best work in the field of hybrid intelligent systems for biomedical applications.

Various SISO feedback control techniques have been applied successfully to muscle relaxant anaesthesia in simulations and clinical trials. SISO generalised predictive control (GPC) altogether with self-organising control using fuzzy logic theory (SOFLC) are among these techniques. A multivariable model combining muscle relaxation (paralysis) and anaesthesia (unconsciousness) has been identified. The multivariable version of GPC in its basic form as well as its different extensions to include model following and observer filter polynomials is outlined in addition to the multivariable version of SOFLC. Both of these strategies are applied to the previous model whose parameters were chosen according to a Monte-Carlo method. The robustness of both control strategies is investigated and the results presented and discussed, enabling a comparison to be made between self-adaptive and self-organising techniques. It is concluded that, when a detailed mathematical model structure is available, GPC provides better control than SOFLC. >

The primary cause for the slowness of the Border Gateway Protocol (BGP) convergence delay is the Minimum Route Advertisement Interval (MRAI). The MRAI is a timer with a default value of 30 seconds, which forces the BGP routers to wait for at least that amount of time before sending an advertisement for the same prefix. This process can delay important BGP advertisements. To date, there has been no specific value used by all the networks around the Internet. This paper aims to find the optimum value for the MRAI timer that maximally reduces the convergence time without increasing the number of advertisement messages. The optimal MRAI value founded by this paper reduced the convergence time by minimum 45%.

New techniques for the prediction of tumour behaviour are needed as statistical analysis has a poor accuracy and is not applicable to the individual. Artificial intelligence (AI) may provide these suitable methods. We have previously shown that the predictive accuracies of neuro-fuzzy modelling (NFM) and artificial neural networks (ANN), two methods of AI, are superior to traditional statistical methods for the behaviour of bladder cancer (Catto et al, 2003). In this paper, we explain the AI techniques required to produce these predictive models. We used 9 parameters, which were a combination of experimental molecular biomarkers and conventional clinicopathological data, to predict the risk of tumour progression in a population of 109 patients with bladder cancer, NFM, using fuzzy logic to model data, achieved similar or superior predictive accuracy to ANN, which required cross-validation. However, unlike the impenetrable opaque structure of neural networks, the rules of NFM are transparent, enabling validation from clinical knowledge and the manipulation of input variables to allow exploratory predictions.