Radiation-induced lymphopenia (RIL) is common among patients undergoing radiotherapy (RT), and severe RIL has been linked with adverse outcomes. The severity and risk of RIL can be predicted from baseline clinical characteristics and dosimetric parameters. However, dose-volume (DV) indices are highly correlated with one another and are only weakly associated with RIL. Here we introduce the novel concept of "composite dosimetric score" (CDS) as the index that condenses the dose distribution in immune tissues of interest to study the dosimetric dependence of RIL. We derived an improved multivariate classification scheme for risk of grade 4 (G4) RIL, based on this novel RT dosimetric feature, for patients receiving chemoRT for esophageal cancer. DV indices were extracted for 734 patients who received chemoRT for biopsy-proven esophageal cancer. Non-negative matrix factorization was used to project the DV indices of lung, heart, and spleen into a single CDS; XGBoost was employed to explore significant interactions among predictors; and logistic regression was applied to combine the resultant CDS along with baseline clinical factors and interaction terms to facilitate individualized prediction of immunotoxicity. Five-fold cross-validation was applied to evaluate the model performance. The CDS for selected immune organs at risk (OARs, i.e., heart, lung, and spleen) (1.791, 95 CI [1.350,2.377]) was a statistically significant risk determinant for G4RIL. Pearson correlation coefficients for CDS vs. G4RIL risk for individual immune OARs were greater than any single DV indices. Personalized prediction of G4RIL based on CDS and 4 clinical risk factors yielded an area under the curve value of 0.78. Interaction between age and CDS revealed that G4RIL risk increased more sharply with increasing CDS for patients ≥65. Risk of immunotoxicity for patients undergoing chemoRT for esophageal cancer can be predicted by CDS. The CDS concept can be extended to immunotoxicity in other cancer types and in dose-response models currently based on DV indices. Personalized treatment planning should leverage CDS methods rather than using individual or subsets of DV indices.