A predictive model for clinical outcomes in human acute radiation syndrome

«Radiation and Risk», 2026, vol. 35, No. 1, pp.117-126

DOI: 10.21870/0131-3878-2026-35-1-117-126

Authors

Pustovoyt V.I. – Head of Dep., MD
Umnikov A.S. – Head of Lab., C. Sc., Med.
Bogomolov A.V. – Lead. Researcher, D. Sc., Tech., Prof. SRC – FMBC. Contacts: 46 Zhivopisnaya str., Moscow, Russia, 123098; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it. .
State Research Center – Burnasyan Federal Medical Biophysical Center of Federal Medical Biological Agency, Moscow

Abstract

Acute radiation syndrome remains one of the most clinically complex forms of human radiation injury, necessitating accurate and reproducible tools for forecasting clinical outcomes. Given the ethical and practical limitations associated with conducting randomized clinical trials in radiation medicine, pre-dictive models based on retrospective data acquire particular significance. The aim of this study was to ensure an acceptable level of accuracy in forecasting clinical outcomes of human ARS, to stand-ardize diagnostic procedures, and to justify personalized therapeutic strategies under conditions of limited time and resources through the development and validation of a prognostic model that inte-grates individual radiation dose burdens, clinical and laboratory indicators, and disease dynamics. The model was constructed using an international dataset derived from a retrospective analysis of 1441 clinical cases of acute radiation syndrome accumulated over the past 70 years, utilizing linear discriminant analysis. The forecasted clinical outcome – favorable or unfavorable – is based on six clinico-radiobiological parameters: cytogenetic dose, severity of the syndrome, radionuclide incorpo-ration, time elapsed since exposure, duration of exposure, and patient body weight. The model demonstrated acceptable accuracy: with an overall accuracy of 94,8%, the predictive accuracy for favorable outcomes was 97,4%, and for unfavorable outcomes – 80,3%. The high performance of the model was corroborated by the results of the classification matrix and ROC analysis. This model represents the first documented application of linear discriminant analysis for blind classification of ARS clinical outcomes in humans based on clinico-radiobiological parameters, thus offering repro-ducibility, interpretability, and potential for automation in systems of medical triage, diagnosis, and emergency response during radiation incidents.

Key words
acute radiation syndrome, human radiation injury, clinical outcome of acute radiation syndrome, acute radiation syndrome outcome prediction, clinico-radiobiological parameter, discriminant analysis.

References

1. Okladnikova N.D., Pesternikova V.S., Sumina M.V., Azizova T.V. Human acute radiation syndrome: con-sequences and outcomes (results of clinical observation). Voprosy radiatsionnoy bezopasnosti – Radiation Safety Problems, 1999, no. 2, pp. 34-44. (In Russian).

2. Galstyan I.A., Bushmanov A.Yu., Torubarov F.S., Zvereva Z.F., Shcherbatykh O.V., Nugis V.Yu., Met-lyaeva N.A., Pustovoyt V.I., Umnikov A.S., Konchalovsky M.V., Aksenov A.V., Korenkov V.V., Yunanova L.A., Kashirina O.G. Possibilities of early diagnosis of acute radiation bone marrow syndrome developing with combined radiation-mechanical injuries. Meditsinskaya radiologiya i radiatsionnaya bezopasnost’ – Medical Radiology and Radiation Safety, 2025, vol. 70, no. 1, pp. 53-59. (In Russian).

3. Samoylov A.S., Solovyev V.Yu., Udalov Yu.D., Bushmanov A.Yu. Atlas of human acute radiation injuries. Vestnik Rossiyskoy voenno-meditsinskoy akademii – Bulletin of the Russian Military Medical Academy, 2018, no. S1, pp. 176-177. (In Russian).

4. Grammaticos P., Giannoula E., Fountos G.P. Acute radiation syndrome and chronic radiation syndrome. Hell. J. Nucl. Med., 2013, vol. 16, no. 1, pp. 56-59.

5. Legeza V.I., Zagorodnikov G.G., Aksenova N.V., Reznik V.M. The major results of 35-year monitoring of some indicators of the state of health of military personnel – liquidators of the consequences of the accident at the Chernobyl nuclear power plant. Voenno-meditsinskiy zhurnal – Military Medical Journal, 2023, vol. 344, no. 6, pp. 22-27. (In Russian).

6. Bolduc D.L., Blakely W.F., Olsen C.H., Agay D., Mestries J.C., Drouet M., Hérodin F. Baboon radiation quality (mixed-field neutron and gamma, gamma alone) dose-response model systems: assessment of H-ARS severity using hematologic biomarkers. Radiat. Prot. Dosim., 2019, vol. 186, no. 1, pp. 15-23.

7. MacVittie T.J., Farese A.M., Jackson W.E. A systematic review of the hematopoietic acute radiation syndrome (H-ARS) in canines and non-human primates: acute mixed neutron/gamma vs. reference quality radiations. Health Phys., 2020, vol. 119, no. 5, pp. 527-558.

8. Macià i Garau M., Lucas Calduch A., López E.C. Radiobiology of the acute radiation syndrome. Rep. Pract. Oncol. Radiother., 2011, vol. 16, no. 4, pp. 123-130.

9. Ushakov I.B., Bogomolov A.V. Digital preventive medicine. Vestnik Rossiyskoy akademii nauk – Herald of the Russian Academy of Sciences, 2024, vol. 94, no. 11, pp. 1003-1013. (In Russian).

10. Ushakov I.B., Bogomolov A.V., Kukushkin Yu.A. Methodological aspects of dynamic monitoring of the functional states of operators in high-risk professions. Mediko-biologicheskie i sotsial'no-psikhologicheskie problemy bezopasnosti v chrezvychaynykh situatsiyakh – Medico-Biological and Socio-Psychological Problems of Safety in Emergency Situations, 2010, no. 4-2, pp. 6-12. (In Russian).

11. Radiation medicine: a guide for medical researchers and public health administrators. Vol. 2. Human radiation injuries. Ed.: L.A. Ilyin. Moscow, Burnazyan FMBC, 2001. 417 p. (In Russian).

12. Medical management of radiation injuries. Safety Reports Series No. 101. Vienna, IAEA, 2020. 98 p.

13. Maksimov I.B., Stolyar V.P., Bogomolov A.V. Applied theory of information support for biomedical research. Moscow, Binom Publ., 2013. 312 p. (In Russian).

14. Starovoitov V.V., Golub Yu.I. Comparative analysis of quality assessments in binary classification. Informatika – Informatics, 2020, vol. 17, no. 1, pp. 87-101. (In Russian).

15. Shuryak I., Royba E., Repin M., Turner H.C., Garty G., Deoli N., Brenner D.J. A machine learning method for improving the accuracy of radiation biodosimetry by combining data from the dicentric chromosomes and micronucleus assays. Sci. Rep., 2022, vol. 12, no. 1, pp. 21077. DOI: 10.1038/s41598-022-25453-2.

16. Mettler F.A., Voelz G.L. Major radiation exposure – what to expect and how to respond. N. Engl. J. Med., 2002, vol. 346, no. 20, pp. 1554-1561.

17. Fliedner T.M., Friesecke I., Beyre K. Medical management of radiation accidents: manual on the acute radiation syndrome. London, British Institute of Radiology, 2001. 66 p.

18. Thompson R.F., Valdes G., Fuller C.D., Carpenter C.M., Morin O., Aneja S., Lindsay W.D., Aerts H.J.W.L., Agrimson B., Deville C., Rosenthal S.A., Yu J.B., Thomas C.R. Artificial intelligence in radiation oncology: a specialty-wide disruptive transformation? Radiother. Oncol., 2018, vol. 129, no. 3, pp. 421-426.

Full-text article (in Russian)