Establishment of prognostic model for postoperative patients with metaplastic breast cancer: Based on a retrospective large data analysis and Chinese multicenter study

Machine Learning-Based Predictive Model for Mortality in Female Breast Cancer Patients Considering Lifestyle Factors

Purpose

To construct a free and accurate breast cancer mortality prediction tool by incorporating lifestyle factors, aiming to assist healthcare professionals in making informed decisions.

Patients and Methods

In this retrospective study, we utilized a ten-year follow-up dataset of female breast cancer patients from a major Chinese hospital and included 1,390 female breast cancer patients with a 7% (96) mortality rate. We employed six machine learning algorithms (ridge regression, k-nearest neighbors, neural network, random forest, support vector machine, and extreme gradient boosting) to construct a mortality prediction model for breast cancer.

Results

This model incorporated significant lifestyle factors, such as postsurgery sexual activity, use of totally implantable venous access ports, and prosthetic breast wear, which were identified as independent protective factors. Meanwhile, ten-fold cross-validation demonstrated the superiority of the random forest model (average AUC = 0.918; 1-year AUC = 0.914, 2-year AUC = 0.867, 3-year AUC = 0.883). External validation further supported the model's robustness (average AUC = 0.782; 1-year AUC = 0.809, 2-year AUC = 0.785, 3-year AUC = 0.893). Additionally, a free and user-friendly web tool was developed using the Shiny framework to facilitate easy access to the model.

Conclusion

Our breast cancer mortality prediction model is free and accurate, providing healthcare professionals with valuable information to support their clinical decisions and potentially promoting healthier lifestyles for breast cancer patients.

Chemotherapy is of prognostic significance to metaplastic breast cancer

This study aimed to evaluate the significance of chemotherapy (CT) among metaplastic breast cancer (MpBC), and to compare the survival outcomes between triple negative MpBC (MpBC-TNBC) and triple negative invasive ductal carcinoma (IDC-TNBC). SEER database was indexed to identify female unilateral primary MpBC diagnosed from 2010 to 2017. Patients were classified into neoadjuvant chemotherapy (NAC) with response (NAC-response), NAC-no response, adjuvant chemotherapy, and no CT. Breast cancer-specific survival (BCSS) and overall survival (OS) was estimated using the Kaplan-Meier method and compared by log-rank test. Cox regression was used to evaluate the independent prognostic factors. A 1:4 propensity score matching method was adopted to balance baseline differences. Altogether 1186 MpBC patients were enrolled, among them 181 received NAC, 647 received adjuvant CT and 358 did not receive any CT. Chemotherapy was an independent favorable prognostic factor. NAC-response and adjuvant CT had a significant or an obvious trend of survival improvement compared with NAC-no response or no CT. MpBC-TNBC was an independent unfavorable prognostic factor compared with IDC-TNBC. Among them, there was significant or trend of survival improvement among all TNBCs receiving NAC or adjuvant CT compared with no CT. Chemotherapy was of important significance to MpBC prognosis and should be integrated in comprehensive treatment for MpBC.

Metaplastic breast cancer: an all-round multidisciplinary consensus

Metaplastic breast cancer (MpBC) is a rare and aggressive histologic subtype of breast cancer (BC) characterized by the presence of at least two cellular types, commonly epithelial and mesenchymal components. Despite growing evidence that MpBC is a unique entity, it has long been treated as a variant of nonspecial type (NST) BC. MpBC typically shows the phenotype of triple-negative breast cancer (TNBC), but compared to NST-TNBC, it is a relatively chemorefractory tumor associated with worse outcomes. Therefore, there is an urgent need to develop management guidelines specifically for MpBC to improve the prognosis of patients with early MpBC. This expert consensus aims to guide diagnosis and standardize clinical management of early MpBC among treating physicians. We provide guidance on the challenging radiological and pathological diagnosis of MpBC. Evidence on the involvement of genetic predisposition in the development of MpBC is also explored. We emphasize the importance of a multidisciplinary approach for the treatment of patients with early MpBC. The optimal surgery and radiotherapy approach is presented, as well as the opportunity offered by novel therapeutic approaches to increase treatment response in this chemoresistant subtype. Appropriate management of patients with MpBC is critical to reduce the high risk of local and distant recurrence that characterizes this disease.