Using Regression Trees to Predict the Development of Immune-Mediated Adverse Events in Patients Receiving Immune Checkpoint Inhibitor Therapy

ORIGINAL ARTICLES. C. CLINICAL RESEARCH

https://doi.org/10.37469/0507-3758-2024-70-4-677-684

Published 06.09.2024

Natalia Vladimirovna Zhukova⁺⁻
Rashida Vakhidovna Orlova⁺⁻
Polina Andreevna Naymushina⁺⁻

Natalia Vladimirovna Zhukova

Federal State Budgetary Educational Institution of Higher Professional Education "Saint-Petersburg State University"

https://orcid.org/0000-0002-0619-2205

Rashida Vakhidovna Orlova

Federal State Budgetary Educational Institution of Higher Professional Education "Saint-Petersburg State University"

https://orcid.org/0000-0002-9368-5517

Polina Andreevna Naymushina

Federal State Budgetary Educational Institution of Higher Professional Education "Saint-Petersburg State University"

https://orcid.org/0000-0003-1830-9287

pdf (Русский)

Keywords

immunotherapy
immune-related adverse events
decision tree regression

How to Cite

Zhukova, N. V., Orlova, R. V., & Naymushina, P. A. (2024). Using Regression Trees to Predict the Development of Immune-Mediated Adverse Events in Patients Receiving Immune Checkpoint Inhibitor Therapy. Voprosy Onkologii, 70(4), 677–684. https://doi.org/10.37469/0507-3758-2024-70-4-677-684

Abstract

Introduction. The toxicity of immune checkpoint inhibitors can be severe and in some cases fatal.

Aim. We conducted the trial to find predictive markers for the toxicity of immune therapy.

Materials and methods. In this paper, we analyzed data from 60 patients with solid tumors who received therapy with immune checkpoint inhibitors at the St. Petersburg City Oncology Dispensary from 2018 to 2021. A classification tree method was used to predict immune-related adverse events (irAEs) development based on analysis of age, sex, BMI, ECOG, PD-L1 expression, type of therapy, leukocyte fractions, and concomitant diseases variables.

Results. The constructed decision tree allows for predicting the risk of irAE with a sensitivity of 93 %, specificity of 66 %, positive predictive value of 78.9 %, and negative predictive value of 73.3 %. The most significant parameters were found to be PD-L1 expression (on immune and tumor cells) and age.

Conclusion. PD-L1 expression and age may have predictive value in forecasting the risk of irAE in patients receiving immune checkpoint inhibitor therapy.

https://doi.org/10.37469/0507-3758-2024-70-4-677-684

pdf (Русский)

References

Costa R., Carneiro B., Agulnik M., et al. Toxicity profile of approved anti-PD-1 monoclonal antibodies in solid tumors: a systematic review and meta-analysis of randomized clinical trials. Oncotarget. 2016; 8(5): 8910-8920.-DOI: https://doi.org/10.18632/oncotarget.13315.

Puzanov I., Diab А., Abdallah К., et al. Managing toxicities associated with immune checkpoint inhibitors: consensus recommendations from the Society for Immunotherapy of Cancer (SITC) Toxicity Management Working Group. J Immunother Cancer. 2017; 5(1): 95.-DOI: https://doi.org/10.1186/s40425-017-0300-z.

Haanen J.B., Obeid М., Spain L., et al. Management of toxicities from immunotherapy: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol Elsevier. 2017; 28: iv119-iv142.-DOI: https://doi.org/10.1093/annonc/mdx225.

Hussaini S., Chehade R., Boldt R., et al. Association between immune-related side effects and efficacy and benefit of immune checkpoint inhibitors – A systematic review and meta-analysis. Cancer Treat Rev Elsevier. 2021; 92.-DOI: https://doi.org/10.1016/j.ctrv.2020.102134.

Трякин А.А., Бесова Н.С., Волков Н.М., et al. Общие принципы проведения противоопухолевой лекарственной терапии. Практические рекомендации RUSSCO, часть 1. Злокачественные опухоли. 2023; 13: 28-41.-DOI: https://doi.org/10.18027/2224-5057-2023-13-3s2-1-28-41. [Tryakin A.A., Besova N.S., Volkov N.M., et al. General principles of anti-tumour drug therapy. RUSSCO Practice Guidelines, Part 1. Malignant Tumours. 2023; 13: 28-41.-DOI: https://doi.org/10.18027/2224-5057-2023-13-3s2-1-28-41. (in Rus)].

Xu Y., Fu Y., Zhu B., et al. Predictive Biomarkers of Immune Checkpoint Inhibitors-Related Toxicities. Front Immunol. 2020; 11: 2023.-DOI: https://doi.org/10.3389/fimmu.2020.02023.

Valpione S., Pasquali S., Campama L., et al. Sex and interleukin-6 are prognostic factors for autoimmune toxicity following treatment with anti-CTLA4 blockade. J Transl Med. 2018; 16(1): 94.-DOI: https://doi.org/10.1186/s12967-018-1467-x.

Fujisawa Y., Yoshino K., Otsuka A., et al. Fluctuations in routine blood count might signal severe immune-related adverse events in melanoma patients treated with nivolumab. J Dermatol Sci. 2017; 88(2): 225-231.-DOI: https://doi.org/10.1016/j.jdermsci.2017.07.007.

Жукова Н., Орлова Р., Малкова А., et al. Предиктивные маркёры развития иммуноопосредованных нежелательных явлений. Вопросы Онкологии. 2022; 68(1): 29-33.-EDN: SQLIZN.-DOI: https://doi.org/10.37469/0507-3758-2022-68-1-29-33.-URL: https://voprosyonkologii.ru/index.php/journal/article/view/1335. [Zhukova N.V., Orlova R.V., Malkova A.M., et al. Predictive biomarkers of immune-related adverse events. Voprosy Onkologii = Problems in Oncology. 2022; 68(1): 29-33.-EDN: SQLIZN.-DOI: https://doi.org/10.37469/0507-3758-2022-68-1-29-33.-URL: https://voprosyonkologii.ru/index.php/journal/article/view/1335. (in Rus)].

Duma N., Abdel-Ghani A., Yadav S., et al. Sex differences in tolerability to anti-programmed cell death protein 1 therapy in patients with metastatic melanoma and non-small cell lung cancer: are we all equal? The Oncologist. 2019; 24(11): e1148-e1155.-DOI: https://doi.org/10.1634/theoncologist.2019-0094.

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.