Scholarlink

<p>This systematic review evaluates how decentralized learning (DL) approaches—e.g., federated learning, swarm learning, ensemble–compare with traditional models in healthcare applications. We searched eight databases (01/2012 to 03/2024), screening 165,010 studies with two independent reviewers. Analysis included 160 articles comprising 710 DL models and 8149 performance comparisons across clinical domains, predominantly in oncology, COVID-19, and neurological diagnostics. In paired comparisons, centralized learning (CL) demonstrated advantages in threshold-dependent metrics (78% favourability for accuracy and Dice score with large effect sizes), while DL achieved comparable performance in ranking metrics (51% centralized favourability for AUROC with small effect size). DL consistently outperformed local learning (LL) across all metrics, particularly precision (86% favourability) and accuracy (83% favourability). Clinical threshold analysis (≥0.80 performance) revealed that CL rescued DL viability in up to 18% of comparisons, though when both achieved clinical viability, improvements typically represented “excellent versus acceptable” performance (median difference of 0.7–1.5pp) rather than “acceptable versus inadequate.” DL rescued LL viability with substantial improvements (median difference of 7.6–27pp). These findings demonstrate DL offers clinically acceptable alternatives for privacy-constrained contexts, with implementation decisions balancing marginal performance trade-offs against regulation (e.g., GDPR, AI Act) and application. Future research requires standardized privacy-performance reporting.</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

Comparing decentralized machine learning and AI clinical models to local and centralized alternatives: a systematic review

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月14日

查看全文
  • José Miguel Diniz,
  • Henrique Vasconcelos,
  • Rita Rb-Silva,
  • Carolina Ameijeiras-Rodriguez,
  • Daniel Rodrigues,
  • Pedro Ramos,
  • António Tomás,
  • Yu Gao,
  • Júlio Souza,
  • Alberto Freitas

摘要

This systematic review evaluates how decentralized learning (DL) approaches—e.g., federated learning, swarm learning, ensemble–compare with traditional models in healthcare applications. We searched eight databases (01/2012 to 03/2024), screening 165,010 studies with two independent reviewers. Analysis included 160 articles comprising 710 DL models and 8149 performance comparisons across clinical domains, predominantly in oncology, COVID-19, and neurological diagnostics. In paired comparisons, centralized learning (CL) demonstrated advantages in threshold-dependent metrics (78% favourability for accuracy and Dice score with large effect sizes), while DL achieved comparable performance in ranking metrics (51% centralized favourability for AUROC with small effect size). DL consistently outperformed local learning (LL) across all metrics, particularly precision (86% favourability) and accuracy (83% favourability). Clinical threshold analysis (≥0.80 performance) revealed that CL rescued DL viability in up to 18% of comparisons, though when both achieved clinical viability, improvements typically represented “excellent versus acceptable” performance (median difference of 0.7–1.5pp) rather than “acceptable versus inadequate.” DL rescued LL viability with substantial improvements (median difference of 7.6–27pp). These findings demonstrate DL offers clinically acceptable alternatives for privacy-constrained contexts, with implementation decisions balancing marginal performance trade-offs against regulation (e.g., GDPR, AI Act) and application. Future research requires standardized privacy-performance reporting.