AUTHOR=Zhou Jian-Guo , Wong Ada Hang-Heng , Wang Haitao , Tan Fangya , Chen Xiaofei , Jin Su-Han , He Si-Si , Shen Gang , Wang Yun-Jia , Frey Benjamin , Fietkau Rainer , Hecht Markus , Ma Hu , Gaipl Udo S. 

TITLE=Elucidation of the Application of Blood Test Biomarkers to Predict Immune-Related Adverse Events in Atezolizumab-Treated NSCLC Patients Using Machine Learning Methods

JOURNAL=Frontiers in Immunology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2022.862752

DOI=10.3389/fimmu.2022.862752

ISSN=1664-3224

ABSTRACT=Background: Development of severe immune-related adverse events (irAEs) is a major predicament to stop treatment with immune checkpoint inhibitors, even though tumor progression is suppressed. However, no effective early phase biomarker has been established to predict irAE until now.
Method: This study retrospectively used the data of four international, multi-center clinical trials to investigate the application of blood test biomarkers to predict irAEs in atezolizumab-treated advanced non-small cell lung cancer (NSCLC) patients. 7 machine learning methods were exploited to dissect the importance score of 21 blood test biomarkers after 1,000 simulations by the training cohort consisting of 80%, 70% and 60% of the combined cohort with 1,320 eligible patients.
Results: XGBoost and LASSO exhibited the best performance in this study with relatively higher consistency between the training and test cohorts. The best area-under-curve (AUC) was obtained by a 10-biomarkers panel using the XGBoost method for the 8:2 training:test cohort ratio (training cohort AUC = 0.692, test cohort AUC = 0.681). This panel could be further narrowed down to a 3-biomarkers panel consisting of C-reactive protein (CRP), platelet-to-lymphocyte ratio (PLR), and thyroid stimulating hormone (TSH) with a small median AUC difference using the XGBoost method (for the 8:2 training:test cohort ratio, training cohort AUC difference = -0.035 (p < 0.0001), test cohort AUC difference = 0.001 (p=0.965)).
Conclusion: Blood test biomarkers do currently not have sufficient predictive power to predict irAE development in atezolizumab-treated advanced NSCLC patients. Nevertheless, biomarkers related to adaptive immunity and liver or thyroid dysfunction warrant further investigation.