Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection.

Feature selection is essential in medical area; however, its process becomes complicated with the presence of censoring which is the unique character of survival analysis. Most survival feature selection methods are based on Cox's proportional hazard model, though machine learning classifiers are preferred. They are less employed in survival analysis due to censoring which prevents them from directly being used to survival data. Among the few work that employed machine learning classifiers, partial logistic artificial neural network with auto-relevance determination is a well-known method that deals with censoring and perform feature selection for survival data. However, it depends on data replication to handle censoring which leads to unbalanced and biased prediction results especially in highly censored data. Other methods cannot deal with high censoring. Therefore, in this article, a new hybrid feature selection method is proposed which presents a solution to high level censoring. It combines support vector machine, neural network, and K-nearest neighbor classifiers using simple majority voting and a new weighted majority voting method based on survival metric to construct a multiple classifier system. The new hybrid feature selection process uses multiple classifier system as a wrapper method and merges it with iterated feature ranking filter method to further reduce features. Two endovascular aortic repair datasets containing 91% censored patients collected from two centers were used to construct a multicenter study to evaluate the performance of the proposed approach. The results showed the proposed technique outperformed individual classifiers and variable selection methods based on Cox's model such as Akaike and Bayesian information criterions and least absolute shrinkage and selector operator in p values of the log-rank test, sensitivity, and concordance index. This indicates that the proposed classifier is more powerful in correctly predicting the risk of re-intervention enabling doctor in selecting patients' future follow-up plan.

Preoperative cardiopulmonary exercise testing in England - a national survey.

BACKGROUND: Cardiopulmonary exercise testing (CPET) has become well established in the preoperative assessment of patients presenting for major surgery in the United Kingdom. There is evidence supporting its use in risk-stratifying patients prior to major high-risk surgical procedures.We set out to establish how CPET services in England have developed since the only survey on this subject was undertaken in 2008 (J Intensive Care Soc 2009, 10:275-278). METHODS: Availability of preoperative CPET and contact details were collected via a telephone survey and email invites to complete the online survey were sent to all contacts. The survey was live during March and April 2011. RESULTS: We received 123 (74%) responses from the 166 emails that were sent out. In total, 32% (53/166) of all adult anesthetic departments in England have access to preoperative CPET services and a further 4% (6) were in the process of setting up services. The number of departments offering preoperative CPET, including those in the process of setting up services, has risen from 42 in 2008 to 59 in 2011, a rise of over 40%. Only 61% of the clinics are run by anesthetists and 39% of clinics have trained cardiorespiratory technicians assisting in the performance of the test. Most of the clinics (55%) rely solely on a bicycle ergometer. Vascular surgical patients are the largest group of patients tested, and the majority of tests are run to a symptom-limited maximum. We estimate that 15,000 tests are performed annually for preoperative assessment in England. Only 37% of respondents were confident that the tests performed were being billed for. CONCLUSIONS: CPET is increasing in popularity as a preoperative risk assessment tool. There remains a lack of consistency in the way tests are reported and utilized. The results highlight the extent and diversity of the use of preoperative CPET and the potential for further research into its use in unstudied patient groups.