Clinical Decision Support Systems in Breast Cancer: A Systematic Review

Abstract

Breast cancer is the most frequently diagnosed cancer in women, with more than 2.1 million new diagnoses worldwide every year. Personalised treatment is critical to optimising outcomes for patients with breast cancer. A major advance in medical practice is the incorporation of Clinical Decision Support Systems (CDSSs) to assist and support healthcare staff in clinical decision-making, thus improving the quality of decisions and overall patient care whilst minimising costs. The usage and availability of CDSSs in breast cancer care in healthcare settings is increasing. However, there may be differences in how particular CDSSs are developed, the information they include, the decisions they recommend, and how they are used in practice. This systematic review examines various CDSSs to determine their availability, intended use, medical characteristics, and expected outputs concerning breast cancer therapeutic decisions, an area that is known to have varying degrees of subjectivity in clinical practice. Utilising the methodology of Kitchenham and Charter, a systematic search of the literature was performed in Springer, Science Direct, Google Scholar, PubMed, ACM, IEEE, and Scopus. An overview of CDSS which supports decision-making in breast cancer treatment is provided along with a critical appraisal of their benefits, limitations, and opportunities for improvement.

Keywords: breast cancer; breast cancer treatment; clinical decision support system (CDSS); decision support system (DSS); systematic review.

Figure 1

General diagram of a CDSS. (1) User (healthcare or patient) who provides information; (2) CDSS that uses Artificial Intelligence (AI) techniques to analyse data to help healthcare providers make decisions and improve patient care; (3) patient’s clinical data which may include several types of patient information such as personal details, medical tests, family history, environmental factors, amongst others; (4) domain knowledge is included in CDSS logic; (5) output of CDSS that could provide information about risk, treatment or follow-up.

Figure 2

Flow diagram summarising the literature search, inclusion, and exclusion process. Red dotted squares correspond to excluded paper; green continuous squares correspond to selected papers.