Assessing Nonlinearity in Harderian Gland Tumor Induction Using Three Combined HZE-irradiated Mouse Datasets

A competing risks machine learning study of neutron dose, fractionation, age, and sex effects on mortality in 21,000 mice

This study explores the impact of densely-ionizing radiation on non-cancer and cancer diseases, focusing on dose, fractionation, age, and sex effects. Using historical mortality data from approximately 21,000 mice exposed to fission neutrons, we employed random survival forest (RSF), a powerful machine learning algorithm accommodating nonlinear dependencies and interactions, treating cancer and non-cancer outcomes as competing risks. Unlike traditional parametric models, RSF avoids strict assumptions and captures complex data relationships through decision tree ensembles. SHAP (SHapley Additive exPlanations) values and variable importance scores were employed for interpretation. The findings revealed clear dose-response trends, with cancer being the predominant cause of mortality. SHAP value dose-response shapes differed, showing saturation for cancer hazard at high doses (> 2 Gy) and a more linear pattern at lower doses. Non-cancer responses remained more linear throughout the entire dose range. There was a potential inverse dose rate effect for cancer, while the evidence for non-cancer was less conclusive. Sex and age effects were less pronounced. This investigation, utilizing machine learning, enhances our understanding of the patterns of non-cancer and cancer mortality induced by densely-ionizing radiations, emphasizing the importance of such approaches in radiation research, including space travel and radioprotection.

Of Men and Mice: Using Terrestrial Radiation Epidemiology Methods to Inform Analysis of Animal Models for Space Radiation Risk Assessment

Prediction of cancer risk from space radiation exposure is critical to ensure spaceflight crewmembers are adequately informed of the risks they face when accepting assignments to ambitious long-duration exploratory missions. Although epidemiological studies have assessed the effects of exposure to terrestrial radiation, no robust epidemiological studies of humans exposed to space radiation exist to support estimates of the risk from space radiation exposure. Mouse data derived from recent irradiation experiments provides valuable information to successfully develop mouse-based excess risks models for assessing relative biological effectiveness for heavy ions that can provide information to scale unique space radiation exposures so that excess risks estimated for terrestrial radiation can be adjusted for space radiation risk assessment. Bayesian analyses were used to simulate linear slopes for excess risk models with several different effect modifiers for attained age and sex. Relative biological effectiveness values for all-solid cancer mortality were calculated from the ratio of the heavy-ion linear slope to the gamma linear slope using the full posterior distribution and resulted in values that were substantially lower than what is currently applied in risk assessment. These analyses provide an opportunity to improve characterization of parameters used in the current NASA Space Cancer Risk (NSCR) model and generate new hypotheses for future animal experiments using out-bred mouse populations.

Modeling of ionizing radiation-induced chromosome aberration and tumor prevalence based on two classes of DNA double-strand breaks clustering in chromatin domains

There has been some controversy over the use of radiobiological models when modeling the dose-response curves of ionizing radiation (IR)-induced chromosome aberration and tumor prevalence, as those curves usually show obvious non-targeted effects (NTEs) at low doses of high linear energy transfer (LET) radiation. The lack of understanding the contribution of NTEs to IR-induced carcinogenesis can lead to distinct deviations of relative biological effectiveness (RBE) estimations of carcinogenic potential, which are widely used in radiation risk assessment and radiation protection. In this work, based on the initial pattern of two classes of IR-induced DNA double-strand breaks (DSBs) clustering in chromatin domains and the subsequent incorrect repair processes, we proposed a novel radiobiological model to describe the dose-response curves of two carcinogenic-related endpoints within the same theoretical framework. The representative experimental data was used to verify the consistency and validity of the present model. The fitting results indicated that, compared with targeted effect (TE) and NTE models, the current model has better fitting ability when dealing with the experimental data of chromosome aberration and tumor prevalence induced by multiple types of IR with different LETs. Notably, the present model without introducing an NTE term was adequate to describe the dose-response curves of IR-induced chromosome aberration and tumor prevalence with NTEs in low-dose regions. Based on the fitting parameters, the LET-dependent RBE values were calculated for three given low doses. Our results showed that the RBE values predicted by the current model gradually decrease with the increase of doses for the endpoints of chromosome aberration and tumor prevalence. In addition, the calculated RBE was also compared with those evaluated from other models. These analyses show that the proposed model can be used as an alternative tool to well describe dose-response curves of multiple carcinogenic-related endpoints and effectively estimate RBE in low-dose regions.

Improving astronaut cancer risk assessment from space radiation with an ensemble model framework

A new approach to NASA space radiation risk modeling has successfully extended the current NASA probabilistic cancer risk model to an ensemble framework able to consider sub-model parameter uncertainty as well as model-form uncertainty associated with differing theoretical or empirical formalisms. Ensemble methodologies are already widely used in weather prediction, modeling of infectious disease outbreaks, and certain terrestrial radiation protection applications to better understand how uncertainty may influence risk decision-making. Applying ensemble methodologies to space radiation risk projections offers the potential to efficiently incorporate emerging research results, allow for the incorporation of future models, improve uncertainty quantification, and reduce the impact of subjective bias. Moreover, risk forecasting across an ensemble of multiple predictive models can provide stakeholders additional information on risk acceptance if current health/medical standards cannot be met for future space exploration missions, such as human missions to Mars. In this work, ensemble risk projections implementing multiple sub-models of radiation quality, dose and dose-rate effectiveness factors, excess risk, and latency are presented. Initial consensus methods for ensemble model weights and correlations to account for individual model bias are discussed. In these analyses, the ensemble forecast compares well to results from NASA's current operational cancer risk projection model used to assess permissible mission durations for astronauts. However, a large range of projected risk values are obtained at the upper 95th confidence level where models must extrapolate beyond available biological data sets. Closer agreement is seen at the median ± one sigma due to the inherent similarities in available models. Identification of potential new models, epidemiological data, and methods for statistical correlation between predictive ensemble members are discussed. Alternate ways of communicating risk and acceptable uncertainty with respect to NASA's current permissible exposure limits are explored.

Machine Learning Models to Predict Cognitive Impairment of Rodents Subjected to Space Radiation

This research uses machine-learned computational analyses to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is from a rodent model exposed to ≤15 cGy of individual galactic cosmic radiation (GCR) ions: 4He, 16O, 28Si, 48Ti, or 56Fe, expected for a Lunar or Mars mission. This work investigates rats at a subject-based level and uses performance scores taken before irradiation to predict impairment in attentional set-shifting (ATSET) data post-irradiation. Here, the worst performing rats of the control group define the impairment thresholds based on population analyses via cumulative distribution functions, leading to the labeling of impairment for each subject. A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the simple discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the compound discrimination (CD) stage. On a subject-based level, implementing machine learning (ML) classifiers such as the Gaussian naïve Bayes, support vector machine, and artificial neural networks identifies rats that have a higher tendency for impairment after GCR exposure. The algorithms employ the experimental prescreen performance scores as multidimensional input features to predict each rodent's susceptibility to cognitive impairment due to space radiation exposure. The receiver operating characteristic and the precision-recall curves of the ML models show a better prediction of impairment when 56Fe is the ion in question in both SD and CD stages. They, however, do not depict impairment due to 4He in SD and 28Si in CD, suggesting no dose-dependent impairment response in these cases. One key finding of our study is that prescreen performance scores can be used to predict the ATSET performance impairments. This result is significant to crewed space missions as it supports the potential of predicting an astronaut's impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. Future research can focus on constructing ML ensemble methods to integrate the findings from the methodologies implemented in this study for more robust predictions of cognitive decrements due to space radiation exposure.