Multi-objective optimisation of cancer chemotherapy using evolutionary algorithms.
Petrovski, Andrei; McCall, John
Carlos Artemio Coello Coello
The main objectives of cancer treatment in general, and of cancer chemotherapy in particular, are to eradicate the tumour and to prolong the patient survival time. Traditionally, treatments are optimised with only one objective in mind. As a result of this, a particular patient may be treated in the wrong way if the decision about the most appropriate treatment objective was inadequate. To partially alleviate this problem, we show in this paper how the multi-objective approach to chemotherapy optimisation can be used. This approach provides the oncologist with versatile treatment strategies that can be applied in ambiguous cases. However, the conflicting nature of treatment objectives and the non-linearity of some of the constraints imposed on treatment schedules make it difficult to utilise traditional methods of multiobjective optimisation. Evolutionary Algorithms (EA), on the other hand, are often seen as the most suitable method for tackling the problems exhibiting such characteristics. Our present study proves this to be true and shows that EA are capable of finding solutions undetectable by other optimisation techniques.
|Start Date||Mar 7, 2001|
|Publication Date||Dec 31, 2001|
|Publisher||Springer (part of Springer Nature)|
|Series Title||Lecture notes in computer science|
|Institution Citation||PETROVSKI, A. and MCCALL, J. 2001. Multi-objective optimisation of cancer chemotherapy using evolutionary algorithms. In Zitzler, E., Thiele, L., Deb, K., Coello Coello, C.A. and Corne, D. (eds.) Proceedings of the 1st International conference on evolutionary multi-criterion optimization (EMO 2001), 7-9 March 2001, Zurich, Switzerland. Lecture notes in computer science, 1993. Berlin: Springer [online], pages 531-545. Available from: https://doi.org/10.1007/3-540-44719-9_37|
|Keywords||Approximation; Evolutionary algorithms; Genetic algorithms; Multi-criterion optimisation; Multiple criteria decision making; Optimal solutions; Pareto-optimal solutions; Scheduling; Algorithms; Evolution; Multi-objective optimisation; Optimisation; Uncert|
PETROVSKI 2001 Multi-objective optimisation of cancer
You might also like
Programming heterogeneous parallel machines using refactoring and Monte–Carlo tree search.
Evolving interval-based representation for multiple classifier fusion.
WEC: weighted ensemble of text classifiers.
Multi-layer heterogeneous ensemble with classifier and feature selection.