Genetic Algorithms (GAs) are non-linear adaptive optimization methods that mimic natural evolution processes via non-exhaustive searches among randomly generated solutions. Genetic Algorithms are highly operative for searching through large or complex data structures seeking the optimal solution for decision, classification, optimization and simulation.
Genetic algorithms are based on the ideas of natural selection and genetics. Non-figurative representations also called ‘chromosomes’ or ‘genotype’ of candidate solutions and ‘individuals’ or ‘phenotypes’ are subject to Genetic Algorithm optimization problems. To simplify the idea, a Genetic Algorithm search space is comprised of genes corresponding with letters, chromosomes equal to words and the genotype with a word family.
Genetic Algorithms mimic “the survival of the fittest” of individuals dominating over the weaker ones over successive generations which is analogous with the behavior of DNA chromosomes within a population of individuals.
Genetic algorithms are dependent on existing data (population) to identify patterns. They in principle operate in the following steps:
- Encoding problems in a string and generating an initial population
- Calculation of the fitness value for each representation (chromosome) via genetic operation
- Iterations of reproduction including stochastic selection of parents to reproduce, application of the genetic algorithm (mutation, crossover) to the parents and evaluation of the children’s fitness value to insert them into the population to replace weaker individuals of the present one.
Genetic Algorithms are explored in medical applications to characterize patterns and results.
For example, optimizing image analysis such as, assessing classes of cells in blood cell microscope images or for facilitating magnetic resonance tomography (MRT) treatment planning and 3D visualization of image data. Genetic algorithms developed for mammography were adapted for mining patient’s having abdominal aortic aneurysms by analyzing abdominal computed tomography (CT) scan reports for common patterns and features of successful and unsuccessful surgeries.
Genetic algorithms can be used for optimizing pharmaceutical products. Recently, it was shown that Genetic Algorithms were able to identify additional anti-bacterial peptides with a high activity during a study.
Finally, it was shown that Genetic Algorithms enhance the precision of artificial neural networks (ANNs) such as for hip-bone fracture prediction or for optimizing efficient search strategies of ANNs to predict and discriminate pneumonia within a training group.
This suggests that combining Genetic Algorithms and artificial neural networks to form genetic algorithm neural networks (GANNs) is an important approach for improving the analysis of medical data.