Scholarlink

<p>The widespread adoption of real-world data has given rise to numerous healthcare-distributed research networks, but multi-site analyses still face administrative burdens and data privacy challenges. In response, we developed a Collaborative One-shot Lossless Algorithm for Generalized Linear Mixed Models (COLA-GLMM), the first-ever algorithm that achieves both <i>lossless</i> and <i>one-shot</i> properties. COLA-GLMM ensures accuracy against the gold standard of pooled data while requiring only summary statistics and completes within a single communication round, eliminating the usual back-and-forth overhead. We further introduced an enhanced version that employs homomorphic encryption to reduce the risks of summary statistics misuse at the coordinating center. The simulation studies showed near-exact agreement with the gold standard in parameter estimation, with relative differences of 7.8 × 10<sup>−6</sup>%–3.0% under various cell suppression settings. We also validated COLA‑GLMM on eight international decentralized databases to identify risk factors for COVID‑19 mortality. Together, these results show that COLA‑GLMM enables accurate, low‑burden, and privacy-preserving multi‑site research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Unlocking efficiency in real-world collaborative studies: a multi-site international study with one-shot lossless GLMM algorithm

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月19日

查看全文
  • Jiayi Tong,
  • Jenna M. Reps,
  • Chongliang Luo,
  • Yiwen Lu,
  • Lu Li,
  • Juan Manuel Ramirez-Anguita,
  • Milou T. Brand,
  • Scott L. DuVall,
  • Thomas Falconer,
  • Alex Mayer Fuentes,
  • Xing He,
  • Michael E. Matheny,
  • Miguel A. Mayer,
  • Bhavnisha K. Patel,
  • Katherine R. Simon,
  • Marc A. Suchard,
  • Guojun Tang,
  • Benjamin Viernes,
  • Ross D. Williams,
  • Mui van Zandt,
  • Fei Wang,
  • Jiang Bian,
  • Jiayu Zhou,
  • David A. Asch,
  • Yong Chen

摘要

The widespread adoption of real-world data has given rise to numerous healthcare-distributed research networks, but multi-site analyses still face administrative burdens and data privacy challenges. In response, we developed a Collaborative One-shot Lossless Algorithm for Generalized Linear Mixed Models (COLA-GLMM), the first-ever algorithm that achieves both lossless and one-shot properties. COLA-GLMM ensures accuracy against the gold standard of pooled data while requiring only summary statistics and completes within a single communication round, eliminating the usual back-and-forth overhead. We further introduced an enhanced version that employs homomorphic encryption to reduce the risks of summary statistics misuse at the coordinating center. The simulation studies showed near-exact agreement with the gold standard in parameter estimation, with relative differences of 7.8 × 10−6%–3.0% under various cell suppression settings. We also validated COLA‑GLMM on eight international decentralized databases to identify risk factors for COVID‑19 mortality. Together, these results show that COLA‑GLMM enables accurate, low‑burden, and privacy-preserving multi‑site research.