Pathology data of the human breast cancer specimens tested.

Information includes the age of the patient, the size of the tumor (mm), the expression percentage of estrogen receptor (ER), progesterone receptor (PR) and HER2, and the metastasis to the lymph node. Lymph node status is indicated as (+) or (−); HER2 expression levels are grouped into four categories according to the pathological data: 3, high or overexpression (H) of HER2; 1–2, medium (M) expression; 1, low (L) expression, and 0 indicates that the expression was not detectable (ND).