A generalized non-linear model predicting efficacy of neoadjuvant therapy in HER2+ breast cancer

Yusong Wang; Xiaoyan Liu; Keda Yu; Shouping Xu; Pengfei Qiu; Xinwen Zhang; Mozhi Wang; Yingying Xu

doi:10.1016/j.isci.2023.106330

A generalized non-linear model predicting efficacy of neoadjuvant therapy in HER2+ breast cancer

iScience. 2023 Mar 2;26(4):106330. doi: 10.1016/j.isci.2023.106330. eCollection 2023 Apr 21.

Authors

Yusong Wang¹, Xiaoyan Liu², Keda Yu³, Shouping Xu⁴, Pengfei Qiu⁵, Xinwen Zhang⁶, Mozhi Wang¹, Yingying Xu¹

Affiliations

¹ Department of Breast Surgery, The First Hospital of China Medical University, Shenyang, Liaoning Province 110001, China.
² Department of Breast Surgery, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, Liaoning Province 110801, China.
³ Department of Breast Surgery, Fudan University Shanghai Cancer Center and Cancer Institute, Shanghai 200032, China.
⁴ Department of Breast Surgery, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang Province 150081, China.
⁵ Breast Cancer Center, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Science, Jinan, Shandong Province 250117, China.
⁶ Center of Implant Dentistry, School and Hospital of Stomatology, China Medical University, Liaoning Provincial Key Laboratory of Oral Disease, Shenyang, Liaoning Province 110001, China.

Abstract

Neoadjuvant therapy (NAT) is currently recommended to patients with human epidermal growth factor receptor 2-positive breast cancer (HER2+ BC) that typically exhibit a poor prognosis. The tumor immune microenvironment profoundly affects the efficacy of NAT. However, the correlation between tumor-infiltrating lymphocytes or their specific subpopulations and the response to NAT in HER2+ BC remains largely unknown. In our study, the immune infiltration status of 295 patients was classified as "immune-rich" or "immune-poor" phenotypes. The "immune-rich" phenotype was significantly positively related to pathological complete response (pCR). Ten genes were correlated with both pCR and the immune phenotype based on the results of spline and logistic regression. We constructed a generalized non-linear model combining linear and non-linear gene effects and successfully validated its predictive power using an internal and external validation set (AUC = 0.819, 0.797; respectively) and a clinical set (accuracy = 0.75).

Keywords: Cancer; Systems biology.