Regresar

Sofia: Selection of medical features by induced alterations in numeric labels

Abstract:

This work deals with the improvement of multi-target pbkp_rediction models through a proposed optimization called Selection Of medical Features by Induced Alterations in numeric labels (SOFIA). This method performs a data transformation when: (1) weighting the features, (2) performing small perturbations on numeric labels and (3) selecting the features that are relevant in the trained multi-target pbkp_rediction models. With the purpose of decreasing the computational cost in the SOFIA method, we consider those multi-objective optimization metaheuristics that support parallelization. In this sense, we propose an extension of the Natural Optimization (NO) approach for Simulated Annealing to support a multi-objective (MO) optimization. This proposed extension, called MONO, and some multiobjective evolutionary algorithms (MOEAs) are considered when performing the SOFIA method to improve pbkp_rediction models in a multi-stage migraine treatment. This work also considers the adaptation of these metaheuristics to run on GPUs for accelerating the exploration of a larger space of solutions and improving results at the same time. The obtained results show that accuracies close to 88% are obtained with the MONO metaheuristic when employing eight threads and when running on a GPU. In addition, training times have been decreased from more than 8 h to less than 45 min when running the algorithms on a GPU. Besides, classification models trained with the SOFIA method only require 15 medical features or fewer to pbkp_redict treatment responses. All in all, the methods proposed in this work remarkably improve the accuracy of multi-target pbkp_rediction models for the OnabotulinumtoxinA (BoNT-A) treatment, while selecting those relevant features that allow us to know in advance the response to every stage of the treatment.