<![CDATA[Patient-Centered Care (PCC) faces critical challenges such as fragmented communication, limited interpretation of patient narratives, and underutilization of real-time feedback. Natural Language Processing (NLP) offers promising solutions by enabling the structured analysis of unstructured data like Electronic Health Records (EHRs), social media content, and patient feedback. This study aims to systematically map the scholarly landscape of NLP applications in PCC between 2015 and 2025, identifying key trends, dominant research themes, and knowledge gaps. A bibliometric analysis was conducted using the Scopus database, with inclusion criteria focused on peer-reviewed, English-language articles in relevant health and technology fields. From an initial set of 645 records, 254 publications met the eligibility requirements. Data cleaning and network analysis were performed using OpenRefine, MS Excel, and VOSviewer, focusing on co-authorship, keyword co-occurrence, and citation density. Results indicate an exponential increase in research output, rising from five publications in 2015 to eighty-one in 2024, largely driven by high-income countries with advanced digital infrastructure. Five thematic clusters emerged: (1) Social Media–Based Patient Communication, (2) Sentiment Analysis for Care Feedback, (3) Clinical Decision Support via NLP, (4) AI-Powered Patient Empowerment, and (5) Modeling Perceived Quality of Care. Implications include the development of real-time, AI-driven feedback loops, multimodal data integration, and culturally responsive chatbot systems. This study also highlights urgent directions for future research, such as building explainable and ethical AI models, integrating diverse data sources, and designing adaptive NLP applications that support longitudinal patient engagement. It offers foundational insights into the evolving role of NLP in enhancing personalized, responsive, and ethically sound PCC.]]>
