<![CDATA[Pain assessment is a critical aspect of healthcare delivery, particularly for patients with Coronary Artery Disease (CAD), who often experience communication difficulties during acute episodes. This study aims to analyze the current state of research on facial expression-based pain detection through a Systematic Literature Review (SLR) conducted in accordance with the PRISMA guidelines. A total of 86 articles published between 2020 and 2025 were retrieved from the Google Scholar database and systematically reviewed. The critical synthesis reveals that studies specifically investigating facial expressions for pain assessment in patients with coronary artery disease remain highly limited. Existing research is predominantly focused on the development of pain detection technologies for general clinical settings, including the use of physiological indicators, experimental datasets such as the BioVid Heat Pain Database, and the application of generic machine learning algorithms. The primary scientific contribution of this review is the identification of a substantial methodological gap within the current literature. Existing studies are largely characterized by descriptive qualitative research designs and a strong reliance on secondary laboratory datasets rather than real-world clinical data collected from patients. The novelty of this study lies in its comprehensive mapping of the existing literature and its proposal to adapt generic pain detection models to the specific characteristics of chest pain (angina pectoris) experienced by patients with coronary artery disease. The findings highlight the need for future research to shift toward integrating computational methods with real-world clinical data from cardiology patients in order to improve the external validity and practical applicability of pain detection systems within actual healthcare environments.]]>
