Whether peripheral immune cell subsets can predict pathological complete response (pCR) in breast cancer patients remains to be elucidated. We aimed to dissect the relationship between peripheral immune cell subsets and pCR.Two hundred and twenty-six eligible patients from two prospective clinical trials (SHPD001 and SHPD002) in China were randomly divided into a training cohort and a validation cohort. The breast cancer subtypes in this study included hormone receptor (HR)-positive/human epidermal growth factor receptor 2 (HER2)-negative (n = 95), HER2-positive (n = 100), and triple negative (n = 31) breast cancer. We defined the "Neo-Peripheral Adaptive Immune Score" for neoadjuvant chemotherapy (neoPAI Score) based on the percentages of CD4 + T cells, CD8 + T cells, B cells, and the CD4 + /CD8 + ratio in peripheral blood. We also evaluated the ability of the neoPAI Score derived from tumor-infiltrating immune cells (TIICs) to predict survival by employing The Cancer Genome Atlas-Breast Cancer (TCGA-BRCA) database.In the training cohort, multivariate analysis showed that HR status [odds ratio (OR) 0.325; 95% confidence interval (CI) 0.135-0.761; P = 0.010], HER2 status (OR 2.657; 95% CI 1.266-5.730; P = 0.011), Ki67 index (OR 3.191; 95% CI 1.509-6.956; P = 0.003), histological grade (OR 2.297; 95% CI 1.031-5.290; P = 0.045) and neoPAI Score (OR 4.451; 95% CI 1.608-13.068; P = 0.005) were independent predictors of pCR. In the validation cohort, histological grade (OR 3.779; 95% CI 3.793-1.136 × 103; P = 0.008) and neoPAI Score (OR 90.828; 95% CI 3.827-9.843 × 103; P = 0.019) were independent predictors of pCR. The Immune Model that integrated the neoPAI Score was more accurate in predicting pCR than the Clinical Model that exclusively contained clinicopathological parameters in both cohorts. In TCGA-BRCA database, the neoPAI Score constructed from TIICs can predict the progression-free interval (P = 0.048) of breast cancer.The neoPAI Score defined by the percentages of peripheral immune cell subsets could be used as a potential biomarker for neoadjuvant chemotherapy efficacy.© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.