A particle swarm based hybrid system for imbalances medical data sampling

Background
Medical and biological data are commonly with small sample size, missing values, and most importantly, imbalanced class distribution. In this study we propose a particle swarm based hybrid system for remedying the class imbalance problem in medical and biological data mining. This hybrid system combines the particle swarm optimization (PSO) algorithm with multiple classifiers and evaluation metrics for evaluation fusion. Samples from the majority class are ranked using multiple objectives according to their merit in compensating the class imbalance, and then combined with the minority class to form a balanced dataset.

Results
One important finding of this study is that different classifiers and metrics often provide different evaluation results. Nevertheless, the proposed hybrid system demonstrates consistent improvements over several alternative methods with three different metrics. The sampling results also demonstrate good generalization on different types of classification algorithms, indicating the advantage of information fusion applied in the hybrid system.

Conclusion
The experimental results demonstrate that unlike many currently available methods which often perform unevenly with different datasets the proposed hybrid system has a better generalization property which alleviates the method-data dependency problem. From the biological perspective, the system provides indication for further investigation of the highly ranked samples, which may result in the discovery of new conditions or disease subtypes.

Medical tourism : a comparison of Australian, French and South Korean medical and health tourists to Thailand.

The high cost of surgery in Western countries has led to an increase in the demand for surgery in developing countries (York, 2008). The objective of this article is to examine the utilization and satisfaction with medical and health services purchased by Australian, French and South Korean visitors to Thailand. In late 2006 a face-to-face survey was conducted with 1,200 randomly selected tourists who had visited Thailand. Results show substantial usage of medical and health services. Satisfaction levels vary across type of service provided and by country of origin of tourist. Recommendations are provided to the national tourism authority. Future research directions are discussed.

Medical error and decision making : learning from the past and present in intensive care

Background : Human error occurs in every occupation. Medical errors may result in a near miss or an actual injury to a patient that has nothing to do with the underlying medical condition. Intensive care has one of the highest incidences of medical error and patient injury in any specialty medical area; thought to be related to the rapidly changing patient status and complex diagnoses and treatments.

Purpose : The aims of this paper are to: (1) outline the definition, classifications and aetiology of medical error; (2) summarise key findings from the literature with a specific focus on errors arising from intensive care areas; and (3) conclude with an outline of approaches for analysing clinical information to determine adverse events and inform practice change in intensive care.

Data source : Database searches of articles and textbooks using keywords: medical error, patient safety, decision making and intensive care. Sociology and psychology literature cited therein.

Findings : Critically ill patients require numerous medications, multiple infusions and procedures. Although medical errors are often detected by clinicians at the bedside, organisational processes and systems may contribute to the problem. A systems approach is thought to provide greater insight into the contributory factors and potential solutions to avoid preventable adverse events.

Conclusion : It is recommended that a variety of clinical information and research techniques are used as a priority to prevent hospital acquired injuries and address patient safety concerns in intensive care.

Applications of nanomedicine in antibacterial medical therapeutics and diagnostics

The need for new and effective/efficient antibacterial therapeutics and diagnostics is necessary if we want to be able to maintain and improve the protection against pathogenic bacteria. Bacteria are becoming increasingly resistant to traditionally used antibiotics and as a result are a major health concern. The number of deaths and hospitalizations due to bacteria is increasing. Current methods of bacterial diagnostics are inefficient as they lack speed and ultra sensitivity and cannot be performed on site. This is where nanomedicine is playing a vital role. The discovery of new and innovative materials through the improvement in fabrication techniques has seen the establishment of an influx of novel antibacterial therapeutics and diagnostics. The goal of this review is to highlight the research that has been done through the implementation of nanomaterials and nanotechnologies for antibacterial medical therapeutic and diagnostic.

Fracture toughness of titanium foams for medical applications

The fracture behavior of titanium open foam is characterized and the R-curves of crack propagation from pre-cracks are measured. The crack growth has been optically observed, the measured initiation toughness, J_IC, has been analyzed and the effect of material morphology on the J_IC is discussed. The fracture toughness was found to be dependent on the expanding crack bridging zone at the back of the crack tip. The compact tension specimens also have some plastic collapse along the ligaments and it has shown that the titanium foam with a higher relative density is tougher. The non-uniform stressing within the plastic zone at the crack tip and the plastic collapse of cell topology behind the tip was found to be the primary cause of the R-curve behavior in low relative density titanium foams.

MAAGs: the next generation. A study of the development of medical audit advisory groups and the arrangements for supporting clinical audit in primary care

Background: MAAGs have, historically, been disparate organisations with a lack of central direction, albeit with the same goal: to develop and support the performance of audit in primary care. This goal has been (and is being) achieved in a number of ways all over the country. In the last two years, MAAGs have witnessed many changes in primary care and are adapting themselves to suit these new arrangements at a local level.

Aim: To formalise our knowledge of where MAAGs are going, how they are getting there and the support they are receiving.

Method: A postal questionnaire to the 104 MAAGs in England and Wales, addressing 6 main issues of relevance to the development of MAAGs and the support they are receiving.

Results: At least two MAAGs have dissolved, leaving a possible total of 102 still in existence. Of these, 76 (74.5%) responded to the survey. The composition of the MAAG committee has changed dramatically since the inception of MAAGs in 1990, and staffing levels appear to have risen substantially. MAAGs appear to be more adequately funded by their health authorities than has previously been reported and many are actively seeking additional sources of funding. There is still large variation in levels of MAAG funding. Furthermore, funding is unrelated to the number of GPs or practices served. Security for MAAG staff appears to have been addressed in many areas, with 84% of MAAGs having at least one member of staff on a permanent employment contract. Many MAAGs are developing rolling programmes in an attempt to eliminate the short-sighted approach to the development of clinical audit that has existed since MAAGs were first set up.

Conclusion: Many MAAGs (with the obvious exception of those that have been dissolved) appear to be thriving without central direction or initiative. It is now evident that we were a little hasty in our concerns for the future of MAAGs beyond April 1996. It would seem that many organisations have taken the situation which arose two years ago as an opportunity to grow and develop in ways that may not have been possible within the confines of the Health Circular.

Medical image retrieval with query-dependent feature fusion based on one-class SVM

Due to the huge growth of the World Wide Web, medical images are now available in large numbers in online repositories, and there exists the need to retrieval the images through automatically extracting visual information of the medical images, which is commonly known as content-based image retrieval (CBIR). Since each feature extracted from images just characterizes certain aspect of image content, multiple features are necessarily employed to improve the retrieval performance. Meanwhile, experiments demonstrate that a special feature is not equally important for different image queries. Most of existed feature fusion methods for image retrieval only utilize query independent feature fusion or rely on explicit user weighting. In this paper, we present a novel query dependent feature fusion method for medical image retrieval based on one class support vector machine. Having considered that a special feature is not equally important for different image queries, the proposed query dependent feature fusion method can learn different feature fusion models for different image queries only based on multiply image samples provided by the user, and the learned feature fusion models can reflect the different importances of a special feature for different image queries. The experimental results on the IRMA medical image collection demonstrate that the proposed method can improve the retrieval performance effectively and can outperform existed feature fusion methods for image retrieval.

QDFA : query-dependent feature aggregation for medical image retrieval

We propose a novel query-dependent feature aggregation (QDFA) method for medical image retrieval. The QDFA method can learn an optimal feature aggregation function for a multi-example query, which takes into account multiple features and multiple examples with different importance. The experiments demonstrate that the QDFA method outperforms three other feature aggregation methods.

A new query dependent feature fusion approach for medical image retrieval based on one-class SVM

With the development of the internet, medical images are now available in large numbers in online repositories, and there exists the need to retrieval the medical images in the content-based ways through automatically extracting visual information of the medical images. Since a single feature extracted from images just characterizes certain aspect of image content, multiple features are necessarily employed to improve the retrieval performance. Furthermore, a special feature is not equally important for different image queries since a special feature has different importance in reflecting the content of different images. However, most existed feature fusion methods for image retrieval only utilize query independent feature fusion or rely on explicit user weighting. In this paper, based on multiply query samples provided by the user, we present a novel query dependent feature fusion method for medical image retrieval based on one class support vector machine. The proposed query dependent feature fusion method for medical image retrieval can learn different feature fusion models for different image queries, and the learned feature fusion models can reflect the different importance of a special feature for different image queries. The experimental results on the IRMA medical image collection demonstrate that the proposed method can improve the retrieval performance effectively and can outperform existed feature fusion methods for image retrieval.