A machine learning method for improving the accuracy of radiation biodosimetry by combining data from the dicentric chromosomes and micronucleus assays

Abstract

A large-scale malicious or accidental radiological event can expose vast numbers of people to ionizing radiation. The dicentric chromosome (DCA) and cytokinesis-block micronucleus (CBMN) assays are well-established biodosimetry methods for estimating individual absorbed doses after radiation exposure. Here we used machine learning (ML) to test the hypothesis that combining automated DCA and CBMN assays will improve dose reconstruction accuracy, compared with using either cytogenetic assay alone. We analyzed 1349 blood sample aliquots from 155 donors of different ages (3–69 years) and sexes (49.1% males), ex vivo irradiated with 0–8 Gy at dose rates from 0.08 Gy/day to ≥ 600 Gy/s. We compared the performances of several state-of-the-art ensemble ML methods and found that random forest generated the best results, with R2 for actual vs. reconstructed doses on a testing data subset = 0.845, and mean absolute error = 0.628 Gy. The most important predictor variables were CBMN and DCA frequencies, and age. Removing CBMN or DCA data from the model significantly increased squared errors on testing data (p-values 3.4 × 10–8 and 1.1 × 10–6, respectively). These findings demonstrate the promising potential of combining CBMN and DCA assay data to reconstruct radiation doses in realistic scenarios of heterogeneous populations exposed to a mass-casualty radiological event.

Assessment of Micronuclei Frequency in the Peripheral Blood of Adult and Pediatric Patients Receiving Fractionated Total Body Irradiation

“…This highlights the important need for future prospective population studies to comprehensively assess individual radiosensitivity using validated biomarkers of radiation exposure. In future work, our goal is to build on these patient datasets for dose and time after TBI (and PBI) exposures and use novel machine learning methods developed in our group to combine MN/BN, NDI, and NLR endpoints to more accurately determine the magnitude of cytogenetic DNA damage in peripheral blood T lymphocytes and likelihood of developing hematopoietic injury following radiation exposure [Shuryak et al, 2022[Shuryak et al, , 2023.…”

High Resolution and Automatable Cytogenetic Biodosimetry Using In Situ Telomere and Centromere Hybridization for the Accurate Detection of DNA Damage: An Overview

“…Importantly, the analysis can be made operator independent [ 11 , 44 ]. Last, but not least, software has been developed that allows the satisfactory automation of chromosomal aberrations scoring [ 11 , 12 , 45 , 46 , 47 , 48 , 49 ]. Thus, the technique has significantly reduced the labor-intensive and time-consuming burden of enumerating chromosome aberrations in the classical “gold standard” assay.…”

Multiwell-based G0-PCC assay for radiation biodosimetry

“…In the current global circumstances, the risk of large-scale ionizing radiation exposure due to military conflicts, terrorist activities, and accidents remains a constant concern [1]. Despite this, the general population lacks access to radiation-monitoring devices, which are typically only available to specialized personnel.…”