Systematic analysis and modeling of the FLASH sparing effect as a function of dose rate and dose

Online searches through Web of Science and PubMed were conducted on 15 September, 2023 for articles published after 1950 using the following terms: TS = (ultra high dose rate OR ultra-high dose rate OR ultrahigh dose rate) AND TS = (in vivo OR animal model OR mice OR preclinical). The queries produced 980 results in total, with 564 results left after removing duplicate entries.The titles and abstracts were reviewed manually by two authors and the full-text of suitable manuscripts was further screened considering the factors such as topics, experiment condition and methods, research objects, endpoints, etc. The detailed record identification and screening flows based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) are summarized in Figure 1. Finally, forty articles were included in our analysis.The FLASH effect was confirmed if there were significant differences in experimental phenomena and data under the two radiation conditions. In the same article, the research items with different endpoints but otherwise identical conditions were regarded as one item. As summarized in Table 1, a total of 131 items were extracted from the 40 articles included in the analysis. For each item, the FLASH effect (1 represents significant sparing effect and 0 represents no sparing effect) and detailed parameters were recorded, including type and energy of the radiation, dose, dose rate, experimental object, pulse characteristics (if provided), etc.According to emulate the quantitative analyses of normal tissue effect in the clinic (QUANTEC), the probability of triggering the FLASH effect as a function of mean dose rate or dose was analyzed with the binary logistic regression model. The analysis was done using the SPSS software. For the statistical data items, there are large imbalances in the number of data entries with and without FLASH effect (people are more inclined to report the research with positive results). Therefore, a more balanced dataset was obtained by oversampling using the K-Means SMOTE algorithm (Figure S1), which was implemented using Python based on the imblearn library.The ROC curve (receiver operating characteristic curve) was plotted as FPR (False Positive Rate) against TPR (True Positive Rate) at different threshold values. The classification model was validated using the AUC (area under ROC curve) value, which was threshold and scale invariant.