<![CDATA[This study examines the application of Big Data models to optimize patient communication in the informed consent process within healthcare settings. Effective informed consent is a cornerstone of patient centered care, yet its implementation is frequently hampered by communication gaps, information overload, and insufficient personalization. This research proposes a Big Data-based framework that integrates structured and unstructured health data including electronic medical records (EMR), patient interaction logs, and demographic information to generate personalized communication strategies for informed consent. Using a mixed-methods approach combining Systematic Literature Review (SLR) and prototype system design, the study identifies key data variables influencing patient comprehension and consent quality. The proposed model leverages machine learning algorithms (Random Forest, NLP) to predict patient health literacy levels and tailor information delivery accordingly. Results from synthetic dataset simulations indicate that the Big Data framework can significantly improve patient understanding (84.6%), reduce consent-related errors by 41.7%, and enhance overall healthcare communication efficiency. The prototype system built on a Lambda Architecture with real-time personalization modules demonstrates high predictive accuracy (87.3%) and F1-score (86.8%). This study contributes to the intersection of health informatics and patient rights, offering a scalable, data-driven solution applicable across various hospital settings. Keywords: Big Data, informed consent, patient communication, electronic medical records, machine learning]]>
