Related Experiment Video
Updated: Aug 14, 2026
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024
Development and validation of a nomogram for predicting chemotherapy-induced liver injury in breast cancer patients
Meizhen Liang1, Dixin Xue1, Rusi Su1
1Department of Thyroid and Breast Surgery, The Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
Background:
Chemotherapy‑induced liver injury (CILI) is a common complication in breast cancer patients, which may lead to treatment interruption and poor prognosis. An effective tool for individualized risk prediction is lacking. This study aimed to develop and validate a nomogram for predicting CILI risk in breast cancer patients undergoing chemotherapy.
Methods:
A retrospective cohort of breast cancer patients receiving chemotherapy between May 2022 and May 2025 in The Third Affiliated Hospital of Wenzhou Medical University was enrolled. Demographic, clinical, tumor‑related, treatment, and laboratory data were collected. An increase in alanine aminotransferase (ALT) or aspartate aminotransferase (AST) exceeding the normal upper limit is defined as liver dysfunction. Logistic regression with least absolute shrinkage and selection operator (LASSO) variable selection was used to identify independent predictors. A nomogram was constructed. Model performance was assessed by the concordance index (C‑index), calibration curve, decision curve analysis (DCA), and clinical impact curve (CIC). Internal validation was performed using 1,000‑bootstrap resampling.
Results:
A total of 422 patients were included. Age and chemotherapy regimen (neoadjuvant vs. adjuvant) were identified as independent predictors for CILI. The nomogram incorporating these two variables achieved a C‑index of 0.75 [95% confidence interval (CI): 0.70-0.80]. Calibration curves showed good agreement between predicted and observed probabilities [mean absolute error (MAE) =0.024]. DCA and CIC demonstrated favorable clinical utility across a wide range of risk thresholds.
Conclusions:
The proposed nomogram provides an individualized, visual tool for predicting CILI risk in breast cancer patients undergoing chemotherapy. It may assist clinicians in early identification of high‑risk patients, optimizing chemotherapy regimens, and implementing timely liver function protective strategies.
