Scholarlink

Background <p>Sepsis-Induced Acute Respiratory Distress Syndrome (SI-ARDS) presents significant diagnostic and prognostic challenges due to its complex clinical manifestations and high mortality rate.</p> Methods <p>We developed a deep Knowledge-Driven multi-Modal Fusion (KDMF) framework for the accurate diagnosis and prognosis of SI-ARDS. The model leverages multi-modal data, including CT images, CT reports, and laboratory indicators, alongside a disease-specific knowledge graph.</p> Results <p>KDMF achieves superior performance in predicting SI-ARDS incidence (AUC 0.930) and time to 28-day mortality (AUC 0.843, C-index 0.833). Comprehensive error analysis and ablation studies demonstrate the critical contributions of each data modality and the integrated knowledge graph.</p> Conclusions <p>The results highlight the potential of KDMF to enhance early intervention and treatment strategies, underscoring the robustness and interpretability of the framework in clinical applications.</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

Deep knowledge-driven multi-modal fusion for diagnosis and prognosis of SI-ARDS

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月28日

查看全文
  • Hongyi Chen,
  • Yang Gu,
  • Guangwei Zhang,
  • Yan Zhang,
  • Xiaohui Duan,
  • Ziying Li,
  • Jiaqi Lin,
  • Xiaoling Yi,
  • Mansheng Chen,
  • Tianqi Yang,
  • Leqi Zheng,
  • Xuanqi Huang,
  • Guoqiong Zeng,
  • Huijun Hu,
  • Riyu Han,
  • Hao Wu,
  • Phei Er Saw,
  • Peiyuan Lai,
  • Li Li,
  • Changdong Wang,
  • Yunfang Yu,
  • Tao Yu,
  • Mohsen Guizani

摘要

Background

Sepsis-Induced Acute Respiratory Distress Syndrome (SI-ARDS) presents significant diagnostic and prognostic challenges due to its complex clinical manifestations and high mortality rate.

Methods

We developed a deep Knowledge-Driven multi-Modal Fusion (KDMF) framework for the accurate diagnosis and prognosis of SI-ARDS. The model leverages multi-modal data, including CT images, CT reports, and laboratory indicators, alongside a disease-specific knowledge graph.

Results

KDMF achieves superior performance in predicting SI-ARDS incidence (AUC 0.930) and time to 28-day mortality (AUC 0.843, C-index 0.833). Comprehensive error analysis and ablation studies demonstrate the critical contributions of each data modality and the integrated knowledge graph.

Conclusions

The results highlight the potential of KDMF to enhance early intervention and treatment strategies, underscoring the robustness and interpretability of the framework in clinical applications.