Purpose or Objective The societal and clinical impact of post-radiotherapy Adverse Events (AE) have highlighted the need of molecular and cellular parameters that can predict the outcome of the treatment. Recent studies have stressed the role of the nucleoshuttling of the ATM protein in the response to radiation, and the statistical performances of this molecular endpoint to predict individual radiosensitivity. The purpose of this study was to develop a predictive assay based on the quantification of the pATM proteins by ELISA method Material and Methods This study was performed on 40 skin fibroblasts from 14 radioresistant and 26 AE patients. Patients were divided in 2 groups, radioresistant (CTCAE<2) and radiosensitive (CTCAE≥2). The quantity of nuclear pATM molecules was assessed by ELISA method compared to the pATM immunofluorescence foci data. The statistical analysis is based on a binary decision diagram built with the CART (Classification And Regression Tree) method proposed by L. Breiman et al. (1984). The Ward distance was used to perform the classification analysis. Results For each cell line, the resulted quantities of nuclear pATM molecules were found in agreement with the immunofluorescence data, in order to provide a reliable evaluation of the statistical performance of the assay. Sensitivity, specificity and AUC values: Sens=0.68, Spec=0.95 and AUC=0.82, emphasize promising results in terms of classification performance. Conclusion This study showed that the assessment of nuclear pATM quantity by an ELISA assay can be the basis of a radiosensitivity predictive test with promising performances.