Abstract
While recent studies, such as Wang et al. have explored immunotherapy trends in thyroid cancer, methodological limitations in data retrieval persist. To address this, we implemented a refined search strategy using the Web of Science Core Collection, targeting critical fields (title, abstract, author keywords) with enhanced terminology. This approach yielded 578 publications-41% more than prior studies (e.g. 409 in Wang et al.) - demonstrating the profound impact of search precision on bibliometric outcomes. Key findings revealed a surge in publications post-2017, global collaboration patterns, and high-impact research clusters. Our study uniquely integrates bibliometric analysis with machine learning to map the evolution of thyroid cancer immunotherapy, emphasizing predictive modeling of emerging therapies and clinical translation. We further provide an open-access analytics platform to streamline data reuse, enabling researchers to identify knowledge gaps and prioritize future investigations. By enhancing methodological rigor and fostering data-driven insights, this work accelerates the translation of immunotherapy advances into clinical practice.