A bibliometric analysis of 16,826 triple-negative breast cancer publications using multiple machine learning algorithms: Progress in the past 17 years.

Background: Triple-negative breast cancer (TNBC) is proposed at the beginning of this century, which is still the most challenging breast cancer subtype due to its aggressive behavior, including early relapse, metastatic spread, and poor survival. This study uses machine learning methods to explore the current research status and deficiencies from a macro perspective on TNBC publications. Methods: PubMed publications under "triple-negative breast cancer" were searched and downloaded between January 2005 and 2022. R and Python extracted MeSH terms, geographic information, and other abstracts from metadata. The Latent Dirichlet Allocation (LDA) algorithm was applied to identify specific research topics. The Louvain algorithm established a topic network, identifying the topic's relationship. Results: A total of 16,826 publications were identified, with an average annual growth rate of 74.7%. Ninety-eight countries and regions in the world participated in TNBC research. Molecular pathogenesis and medication are most studied in TNBC research. The publications mainly focused on three aspects: Therapeutic target research, Prognostic research, and Mechanism research. The algorithm and citation suggested that TNBC research is based on technology that advances TNBC subtyping, new drug development, and clinical trials. Conclusion: This study quantitatively analyzes the current status of TNBC research from a macro perspective and will aid in redirecting basic and clinical research toward a better outcome for TNBC. Therapeutic target research and Nanoparticle research are the present research focus. There may be a lack of research on TNBC from a patient perspective, health economics, and end-of-life care perspectives. The research direction of TNBC may require the intervention of new technologies.