Abstract
Background: Breast cancer remains a leading cause of cancer-related morbidity and mortality in women worldwide. Traditional methods for predicting metastasis in breast cancer rely primarily on tumor pathology characteristics, such as tumor size, TNM grade, and receptor status. However, these methods do not fully account for patient-centered health factors, which could also play a role in metastasis risk. Factors such as a patient’s overall physiological health, history of anti-neoplastic treatments, and personal and family history of cancer may also significantly impact the likelihood of developing distant metastasis in breast cancer. This study aims to develop a predictive model for distant metastasis in breast cancer that incorporates these broader, patient-centered factors for a more comprehensive risk assessment.
Methods: This study analyzed all 4296 female breast cancer cases from the 2021 NIS, assessing 130 variables. Among these cases, 1691 (39.36%) had distant metastasis, while 2605 (60.64%) did not. For metastasis prediction, 21 key variables were selected, including age, race, anti-neoplastic treatment, presence of other cancers, cancer history, smoking, depression/anxiety, elective admission, All Patient Refined DRG Severity of Illness Subclass (APRDRG Severity), and various comorbidities. A binary logistic regression model was developed to build the predictive model for distant metastasis in breast cancer, and refined through backward elimination with cross-validation used for validation. Additionally, eight additional variables, such as morbidity, length of stay, and total charges were analyzed for comparison but were not included in the predictive model. Statistical comparisons between metastatic and non-metastatic groups were conducted, with continuous variables assessed using the Mann-Whitney U test and categorical variables using the Chi-Square test or Fisher’s Exact test. The significance level (a) was set at 0.05. All analyses were performed in RStudio.
Results: The analysis identified several significant predictors for distant metastasis in female breast cancer. Notable risk factors included malignant pleural effusion (Odds Ratio [OR] = 1.86, p < 0.001), APRDRG severity (Moderate: OR = 1.31, Major: OR = 3.60, Extreme: OR = 5.16, p < 0.05), anti-neoplastic treatment (OR = 1.24, p < 0.05), and anemia (OR = 1.32, p < 0.05). Factors associated with reduced risk of metastasis were elective admission (OR = 0.29, p < 0.001), history of cancer (OR = 0.69, p < 0.05), and obesity (OR = 0.76, p < 0.05). The model achieved an accuracy of 0.7466, an AUC of 0.7467, high sensitivity (0.8663), and moderate specificity (0.5621), with model fit supported by McFadden R² (0.1902) and Cox & Snell R² (0.3049). Cross-validation indicated consistent performance, with standard deviations < 0.05 and narrow 95% confidence intervals, confirming model reliability. Notably, 89.77% of deceased patients had distant metastasis, compared to 22.55% of survivors. Among non-metastatic cases, only 0.28% (9 of 3268) resulted in death. Patients with metastasis had longer hospital stays (6.72 ± 7.97 days) than non-metastatic patients (2.55 ± 3.40 days). However, total charges were lower for metastatic cases ($75264 ± $71374 vs. $98632 ± $88864).
Conclusion: This study presents a patient-centric model for predicting breast cancer metastasis, integrating broader health factors and lifestyle variables beyond traditional tumor characteristics. The predictive model highlights significant predictors such as malignant pleural effusion, personal cancer history, elective admission, APRDRG severity, anti-neoplastic treatment, obesity, and anemia. With its high sensitivity and stable cross-validation results, the model proves effective for identifying high-risk cases of distant metastasis. This patient-centered model for predicting distant metastasis of breast cancer provides insights that may enhance tailored treatment strategies and improve outcomes for breast cancer patients.