Background: Childhood cancer survivors are at risk for developing long term adverse health outcomes. To identify the risk of and risk factors for specific health outcomes, well-established cohorts... Show moreBackground: Childhood cancer survivors are at risk for developing long term adverse health outcomes. To identify the risk of and risk factors for specific health outcomes, well-established cohorts are needed with detailed information on childhood cancer diagnosis, treatment, and health outcomes. We describe the design, methodology, characteristics, and data availability of the Dutch Childhood Cancer Survivor Study LATER cohort (1963- 2001) part 1; questionnaire and linkage studies. Methods: The LATER cohort includes 5 year childhood cancer survivors, diagnosed in the period 1963- 2001, and before the age of 18 in any of the seven former pediatric oncology centers in the Netherlands. Information on health outcomes from survivors and invited siblings of survivors was collected by questionnaires and linkages to medical registries. Results: In total, 6165 survivors were included in the LATER cohort. Extensive data on diagnosis and treatment have been collected. Information on a variety of health outcomes has been ascertained by the LATER questionnaire study and linkages with several registries for subsequent tumors, health care use, and hospitalizations. Conclusion: Research with data of the LATER cohort will provide new insights into risks of and risk factors for long term health outcomes. This can enhance risk stratification for childhood cancer survivors and inform surveillance guidelines and development of interventions to prevent (the impact of) long term adverse health outcomes. The data collected will be a solid baseline foundation for future follow-up studies. Show less
Virgolin, M.; Alderliesten, T.; Witteveen, C.; Bosman, P.A.N. 2021
The Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) is a model-based EA framework that has been shown to perform well in several domains, including Genetic Programming (GP). Differently... Show moreThe Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) is a model-based EA framework that has been shown to perform well in several domains, including Genetic Programming (GP). Differently from traditional EAs where variation acts blindly, GOMEAlearns a model of interdependencies within the genotype, that is, the linkage, to estimate what patterns to propagate. In this article, we study the role of Linkage Learning (LL) performed by GOMEA in Symbolic Regression (SR). We show that the non-uniformity in the distribution of the genotype in GP populations negatively biases LL, and propose a method to correct for this. We also propose approaches to improve LL when ephemeral random constants are used. Furthermore, we adapt a scheme of interleaving runs to alleviate the burden of tuning the population size, a crucial parameter for LL, to SR. We run experiments on 10 real-world datasets, enforcing a strict limitation on solution size, to enable interpretability. We find that the new LL method outperforms the standard one, and that GOMEA outperforms both traditional and semantic GP. We also find that the small solutions evolved by GOMEA are competitive with tuned decision trees, making GOMEA a promising new approach to SR. Show less
