Haoyang Wang

This study investigates the dynamics of scientific attention within author citation networks, utilizing the Microsoft Academic Graph dataset. Three author citation networks were constructed within the domains of nanoscience, chemical physics, and human-computer interaction. We apply analytical measurements to reveal core-periphery structures, indicating a growing disparity in scientific interactions. Our analysis highlights a concerning trend: while connections among prominent authors are strengthening, interactions among “ordinary” scientists remain relatively weak. This trend is further corroborated by the application of the network percolation method. After removing the prominent authors in the citation networks, multilayered and complex relationships among authors are revealed. We observe a decreasing trend of connection strength among relatively “ordinary” authors. The observed inequality of attention raises significant concerns about neglecting diverse voices within the scientific community. In response to these phenomena, our research emphasizes the importance of cultivating an inclusive scientific environment for early-career and underrepresented scholars, aiming for long-term sustainability in the scientific community.

Extracting social determinants of health (SDoHs) from medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. Here, we introduce SDoH-GPT, a novel framework leveraging few-shot learning large language models (LLMs) to automate the extraction of SDoH from unstructured text, aiming to improve both efficiency and generalizability.SDoH-GPT is a framework including the few-shot learning LLM methods to extract the SDoH from medical notes and the XGBoost classifiers which continue to classify SDoH using the annotations generated by the few-shot learning LLM methods as training datasets. The unique combination of the few-shot learning LLM methods with XGBoost utilizes the strength of LLMs as great few shot learners and the efficiency of XGBoost when the training dataset is sufficient. Therefore, SDoH-GPT can extract SDoH without relying on extensive medical annotations or costly human intervention.Our approach achieved tenfold and twentyfold reductions in time and cost, respectively, and superior consistency with human annotators measured by Cohen’s kappa of up to 0.92. The innovative combination of LLM and XGBoost can ensure high accuracy and computational efficiency while consistently maintaining 0.90+ AUROC scores.This study has verified SDoH-GPT on three datasets and highlights the potential of leveraging LLM and XGBoost to revolutionize medical note classification, demonstrating its capability to achieve highly accurate classifications with significantly reduced time and cost.The key contribution of this study is the integration of LLM with XGBoost, which enables cost-effective and high quality annotations of SDoH. This research sets the stage for SDoH can be more accessible, scalable, and impactful in driving future healthcare solutions.