Bayesian Counterfactual Machine Learning Individualizes Radiation Modality Selection to Mitigate Immunosuppression. JCO Clin Cancer Inform 2025 Aug;9:e2500058
Date
09/08/2025Pubmed ID
40920994Pubmed Central ID
PMC12419026DOI
10.1200/CCI-25-00058Scopus ID
2-s2.0-105015371000 (requires institutional sign-in at Scopus site)Abstract
PURPOSE: Lymphocytes play critical roles in cancer immunity and tumor surveillance. Radiation-induced lymphopenia (RIL) is a common side effect observed in patients with cancer undergoing chemoradiation therapy (CRT), leading to impaired immunity and worse clinical outcomes. Although proton beam therapy (PBT) has been suggested to reduce RIL risk compared with intensity-modulated radiation therapy (IMRT), this study used Bayesian counterfactual machine learning to identify distinct patient profiles and inform personalized radiation modality choice.
METHODS: A novel Bayesian causal inferential technique is introduced and applied to a matched retrospective cohort of 510 patients with esophageal cancer undergoing CRT to identify patient profiles for which immunosuppression could have been mitigated from radiation modality selection.
RESULTS: BMI, age, baseline absolute lymphocyte count (ALC), and planning target volume determined the extent to which reductions in ALCs varied by radiation modality. Five patient profiles were identified. Significant variation in ALC nadir between PBT and IMRT was observed in three of the patient subtypes. Notably, older patients (age >69 years) with normal weight experienced a two-fold reduction in mean ALC nadir when treated with IMRT versus PBT. Mean ALC nadir was reduced significantly for IMRT patients with lower ALC at baseline (<1.6 k/µL) who were overweight or obese when compared with PBT, whereas overweight patients with higher baseline ALC showed clinical equipoise between modalities.
CONCLUSION: Individualized radiation therapy selection can be an important tool to minimize immunosuppression for high-risk patients. The Bayesian counterfactual modeling techniques presented in this article are flexible enough to capture complex, nonlinear patterns while estimating interpretable patient profiles for translation into clinical protocols.
Author List
Yu D, Kane MJ, Chen Y, Lin SH, Mohan R, Hobbs BPAuthor
Duo Yu PhD Assistant Professor in the Data Science Institute department at Medical College of WisconsinMESH terms used to index this publication - Major topics in bold
AdultAged
Aged, 80 and over
Bayes Theorem
Chemoradiotherapy
Esophageal Neoplasms
Female
Humans
Immune Tolerance
Lymphopenia
Machine Learning
Male
Middle Aged
Precision Medicine
Proton Therapy
Radiotherapy, Intensity-Modulated
Retrospective Studies
