AUTHOR=Prelich Matthew T. , Matar Mona , Gokoglu Suleyman A. , Gallo Christopher A. , Schepelmann Alexander , Iqbal Asad K. , Lewandowski Beth E. , Britten Richard A. , Prabhu R. K. , Myers Jerry G. 

TITLE=Predicting Space Radiation Single Ion Exposure in Rodents: A Machine Learning Approach

JOURNAL=Frontiers in Systems Neuroscience

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/systems-neuroscience/articles/10.3389/fnsys.2021.715433

DOI=10.3389/fnsys.2021.715433

ISSN=1662-5137

ABSTRACT=This study presents a data-driven machine learning approach to predict individual Galactic Cosmic Radiation (GCR) ion exposure for 4He, 16O, 28Si, 48Ti, or 56Fe up to 15 cGy, based on Attentional Set-shifting (ATSET) experimental tests. The ATSET assay consists of a series of cognitive performance tasks on irradiated male Wistar rats. The GCR ion doses represent the expected cumulative radiation astronauts may receive during a Lunar or Mars mission on an individual ion basis. The primary objective is to synthesize and assess predictive models on a per-subject level through Machine Learning (ML) classifiers. The raw cognitive performance data from individual rodent subjects is used to build the models and to explore the capabilities of three different ML techniques for elucidating a range of correlations between received radiation on rodents and their performance outcomes. The analysis employs scores of input feature selections and different normalization approaches which yields varying degrees of model performance. The current study shows that Support Vector Machine, Gaussian Naïve Bayes, and Decision Tree ML models are capable of predicting individual ion exposure using ATSET scores where corresponding Matthews correlation coefficients and F1 scores reflect model performance exceeding random chance. The study suggests an effect on cognitive performance decrement in rodents due to single ion exposure between 0 to 15 cGy inasmuch as the models can discriminate between exposure levels in the performance score feature space. A number of observations about the utility and limitations in specific normalization routines and evaluation scores are examined and best practices observed.