Breast cancer is the most common disease among women, with over $2.1$ million new diagnoses each year worldwide. About $30\%$ of patients initially presenting with early stage disease have a recurrence of cancer within 10 years. Predicting who will have a recurrence and who will not remains challenging, with consequent implications for associated treatment. Artificial intelligence strategies that can predict the risk of recurrence of breast cancer could help breast cancer clinicians avoid ineffective overtreatment. Despite its significance, most breast cancer recurrence datasets are insufficiently large, not publicly available, or imbalanced, making these studies more difficult. This systematic review investigates the role of artificial intelligence in the prediction of breast cancer recurrence. We summarise common techniques, features, training and testing methodologies, metrics, and discuss current challenges relating to implementation in clinical practice. We systematically reviewed works published between 1 January 2011 and 1 November 2021 using the methodology of Kitchenham and Charter. We leveraged Springer, Google Scholar, PubMed, and IEEE search engines. This review found three areas that require further work. First, there is no agreement on artificial intelligence methodologies, feature predictors, or assessment metrics. Second, issues such as sampling strategies, missing data, and class imbalance problems are rarely addressed or discussed. Third, representative datasets for breast cancer recurrence are scarce, which hinders model validation and deployment. We conclude that predicting breast cancer recurrence remains an open problem despite the use of artificial intelligence.

Triple-negative breast cancer (TNBC) is an aggressive form of mammary malignancy currently without satisfactory systemic treatment options. Agents generating reactive oxygen species (ROS), such as ascorbate (Asc) and menadione (Men), especially applied in combination, have been proposed as an alternative anticancer modality. However, their effectiveness can be hampered by the cytoprotective effects of elevated antioxidant enzymes (e.g., peroxiredoxins, PRDX) in cancer. In this study, PRDX1 mRNA and protein expression were assessed in TNBC tissues by analysis of the online RNA-seq datasets and immunohistochemical staining of tissue microarray, respectively. We demonstrated that PRDX1 mRNA expression was markedly elevated in primary TNBC tumors as compared to non-malignant controls, with PRDX1 protein staining intensity correlating with favorable survival parameters. Subsequently, PRDX1 functionality in TNBC cell lines or non-malignant mammary cells was targeted by genetic silencing or chemically by auranofin (AUR). The PRDX1-knockdown or AUR treatment resulted in inhibition of the growth of TNBC cells in vitro. These cytotoxic effects were further synergistically potentiated by the incubation with a combination of the prooxidant agents, Asc and Men. In conclusion, we report that the PRDX1-related antioxidant system is essential for maintaining redox homeostasis in TNBC cells and can be an attractive therapeutic target in combination with ROS-generating agents.

Castrate-resistant prostate cancer (CRPC) is challenging to treat with the androgen receptor (AR), the main target and key focus of resistance. Understanding the mechanisms of AR interaction with co-regulators will identify new therapeutic targets to overcome AR resistance mechanisms. We previously identified the serum response factor (SRF) as a lead target in an in vitro model of CRPC and showed that SRF expression in tissues of CRPC patients was associated with shorter survival. Here, we tested SRF inhibition in vitro and in vivo to assess SRF as a potential target in CRPC. Inhibition of SRF with the small-molecule inhibitor CCG1423 resulted in enhanced response to enzalutamide in vitro and reduced tumour volume of LuCaP 35CR, a CRPC patient-derived xenograft model. Nuclear localisation of AR post-CCG1423 was significantly decreased and was associated with decreased α-tubulin acetylation in vitro and decreased prostate specific antigen (PSA) levels in vivo. SRF immunoreactivity was tested in metastatic tissues from CRPC patients to investigate its role in enzalutamide response. Kaplan–Meier curves showed that high SRF expression was associated with shorter response to enzalutamide. Our study supports the use of SRF inhibitors to improve response to enzalutamide.