Predicting Patterns of Distant Metastasis in Breast Cancer Patients following Local Regional Therapy Using Machine Learning

Abstract

Up to 30% of breast cancer (BC) patients will develop distant metastases (DM), for which there is no cure. Here, statistical and machine learning (ML) models were developed to estimate the risk of site-specific DM following local-regional therapy. This retrospective study cohort included 175 patients diagnosed with invasive BC who later developed DM. Clinicopathological information was collected for analysis. Outcome variables were the first site of metastasis (brain, bone or visceral) and the time interval (months) to developing DM. Multivariate statistical analysis and ML-based multivariable gradient boosting machines identified factors associated with these outcomes. Machine learning models predicted the site of DM, demonstrating an area under the curve of 0.74, 0.75, and 0.73 for brain, bone and visceral sites, respectively. Overall, most patients (57%) developed bone metastases, with increased odds associated with estrogen receptor (ER) positivity. Human epidermal growth factor receptor-2 (HER2) positivity and non-anthracycline chemotherapy regimens were associated with a decreased risk of bone DM, while brain metastasis was associated with ER-negativity. Furthermore, non-anthracycline chemotherapy alone was a significant predictor of visceral metastasis. Here, clinicopathologic and treatment variables used in ML prediction models predict the first site of metastasis in BC. Further validation may guide focused patient-specific surveillance practices.

Keywords: breast cancer metastasis; machine learning; metastatic patterns; prediction models.

Figure 1

Flow chart displaying patient inclusion/exclusion criteria. Once patients with missing data were removed from the original cohort (n = 416), the remaining patients were excluded in order of clinical, treatment and pathological data. The final cohort for our study consisted of 175 patients. Abbreviations: chemo—chemotherapy; IDC—intraductal carcinoma.

Figure 2

Odds ratios (OR) for bone, brain or visceral metastases according to clinicopathological characteristics. Multivariate analyses were conducted to determine the ORs for developing bone (a) or brain (b) metastasis according to clinicopathological characteristics. ER+ and N1 vs. N0 stage were significantly associated with an increased risk of bone metastasis, whereas HER2+ and “other chemo” were significantly associated with a decreased risk. ER+ was significantly associated with a decreased risk of brain metastasis. (c) ORs for developing visceral metastasis were analyzed using bivariate analysis, and no characteristics were significant. Abbreviations: chemo—chemotherapy; N0—nodal status 0 (0 positive nodes); N1—nodal status 1 (1–3 positive nodes); N2—nodal status 2 (4–9 positive nodes); N3—nodal status 3 (greater than 10 positive nodes); HER2—human epidermal growth factor 2; ER+—estrogen receptor-positive. (* indicates statistically significant, p = 0.05).