Artif Intell Med.

Fuzzy Arden Syntax: A fuzzy programming language for medicine.

Publication Date: 2010 Feb 16 PMID: 20167457
Authors: Vetterlein, T. - Mandl, H. - Adlassnig, K. P.
Journal: Artif Intell Med

OBJECTIVE: The programming language Arden Syntax has been optimised for use in clinical decision support systems. We describe an extension of this language named Fuzzy Arden Syntax, whose original version was introduced in S. Tiffe's dissertation on "Fuzzy Arden Syntax: Representation and Interpretation of Vague Medical Knowledge by Fuzzified Arden Syntax" (Vienna University of Technology, 2003). The primary aim is to provide an easy means of processing vague or uncertain data, which frequently appears in medicine. METHODS: For both propositional and number data types, fuzzy equivalents have been added to Arden Syntax. The Boolean data type was generalised to represent any truth degree between the two extremes 0 (falsity) and 1 (truth); fuzzy data types were introduced to represent fuzzy sets. The operations on truth values and real numbers were generalised accordingly. As the conditions to decide whether a certain programme unit is executed or not may be indeterminate, a Fuzzy Arden Syntax programme may split. The data in the different branches may be optionally aggregated subsequently. RESULTS: Fuzzy Arden Syntax offers the possibility to formulate conveniently Medical Logic Modules (MLMs) based on the principle of a continuously graded applicability of statements. Furthermore, ad hoc decisions about sharp value boundaries can be avoided. As an illustrative example shows, an MLM making use of the features of Fuzzy Arden Syntax is not significantly more complex than its Arden Syntax equivalent; in the ideal case, a programme handling crisp data remains practically unchanged when compared to its fuzzified version. In the latter case, the output data, which can be a set of weighted alternatives, typically depends continuously from the input data. CONCLUSION: In typical applications an Arden Syntax MLM can produce a different output after only slight changes of the input; discontinuities are in fact unavoidable when the input varies continuously but the output is taken from a discrete set of possibilities. This inconvenience can, however, be attenuated by means of certain mechanisms on which the programme flow under Fuzzy Arden Syntax is based. To write a programme making use of these possibilities is not significantly more difficult than to write a programme according to the usual practice.

post to: CiteULike

A machine learning-based approach to prognostic analysis of thoracic transplantations.

Publication Date: 2010 Feb 12 PMID: 20153956
Authors: Delen, D. - Oztekin, A. - Kong, Z. J.
Journal: Artif Intell Med

OBJECTIVE: The prediction of survival time after organ transplantations and prognosis analysis of different risk groups of transplant patients are not only clinically important but also technically challenging. The current studies, which are mostly linear modeling-based statistical analyses, have focused on small sets of disparate predictive factors where many potentially important variables are neglected in their analyses. Data mining methods, such as machine learning-based approaches, are capable of providing an effective way of overcoming these limitations by utilizing sufficiently large data sets with many predictive factors to identify not only linear associations but also highly complex, non-linear relationships. Therefore, this study is aimed at exploring risk groups of thoracic recipients through machine learning-based methods. METHODS AND MATERIAL: A large, feature-rich, nation-wide thoracic transplantation dataset (obtained from the United Network for Organ Sharing-UNOS) is used to develop predictive models for the survival time estimation. The predictive factors that are most relevant to the survival time identified via, (1) conducting sensitivity analysis on models developed by the machine learning methods, (2) extraction of variables from the published literature, and (3) eliciting variables from the medical experts and other domain specific knowledge bases. A unified set of predictors is then used to develop a Cox regression model and the related prognosis indices. A comparison of clustering algorithm-based and conventional risk grouping techniques is conducted based on the outcome of the Cox regression model in order to identify optimal number of risk groups of thoracic recipients. Finally, the Kaplan-Meier survival analysis is performed to validate the discrimination among the identified various risk groups. RESULTS: The machine learning models performed very effectively in predicting the survival time: the support vector machine model with a radial basis Kernel function produced the best fit with an R(2) value of 0.879, the artificial neural network (multilayer perceptron-MLP-model) came the second with an R(2) value of 0.847, and the M5 algorithm-based regression tree model came last with an R(2) value of 0.785. Following the proposed method, a consolidated set of predictive variables are determined and used to build the Cox survival model. Using the prognosis indices revealed by the Cox survival model along with a k-means clustering algorithm, an optimal number of "three" risk groups is identified. The significance of differences among these risk groups are also validated using the Kaplan-Meier survival analysis. CONCLUSIONS: This study demonstrated that the integrated machine learning method to select the predictor variables is more effective in developing the Cox survival models than the traditional methods commonly found in the literature. The significant distinction among the risk groups of thoracic patients also validates the effectiveness of the methodology proposed herein. We anticipate that this study (and other AI based analytic studies like this one) will lead to more effective analyses of thoracic transplant procedures to better understand the prognosis of thoracic organ recipients. It would potentially lead to new medical and biological advances and more effective allocation policies in the field of organ transplantation.

post to: CiteULike

Modified tabu search approach for variable selection in quantitative structure-activity relationship studies of toxicity of aromatic compounds.

Publication Date: 2010 Feb 10 PMID: 20153153
Authors: Shen, Q. - Shi, W. M. - Kong, W.
Journal: Artif Intell Med

OBJECTIVE: Variable selection is a key step in developing a successful quantitative structure-activity relationships (QSAR) analysis system. Tabu search (TS) can be used for variable selection which employs a flexible memory system to avoid convergence to local minima. But the convergence speed of TS depends on the initial solution and is slow. It usually reaches local minima since a single candidate solution is used to generate offspring. In the present paper, the TS algorithm was modified to assist TS to find the promising regions of the search space rapidly. METHODS AND MATERIALS: A version of modified TS algorithm is proposed to select variables in QSAR modeling and to predict toxicity of some aromatic compounds. In the modified TS, the information which shares mechanism among the best position of all iteration and the personal position is introduced in the step of generating neighbors of the given solution. The move function which directs the moving of the solution is recorded as tabu. The modified Cp statistic is employed as fitness function. RESULTS AND CONCLUSIONS: For comparison, the conventional TS and stepwise regression were also examined. Experimental results demonstrate that the modified TS is a useful tool for variable selection which converges quickly towards the optimal position.

post to: CiteULike