Scholarlink

Background <p>Deep learning (DL) is revolutionizing high-dimensional analysis for clinical applications, with multimodal approaches showing promise in integrating diverse datasets and improving predictive accuracy. However, its use in prognostic assessment, particularly for non-small-cell lung cancer (NSCLC), remains limited.</p> Methods <p>Whole-slide imaging (WSI), next-generation sequencing (NGS), and clinical features from 2,366 NSCLC patients sourced from various databases were analyzed. A Sequential-Adapted Attention (SeAttn) model was developed to process WSI, while multiple DL models analyzed genetic and clinical data. Multimodal features were combined using a COX-based DL approach to predict long-term prognosis. Validation (<i>N</i> = 100) and test (<i>N</i> = 101) cohorts were used to confirm model performance.</p> Results <p>The SeAttn model achieved an area under the curve (AUC) of 0.98 for NSCLC histologic subtype prediction in the test cohort (<i>P</i> &lt; 0.0001). Individually, WSI, clinical, and genetic features predicted prognosis with concordance indices (C-indices) of 0.55–0.67 using the test cohort. Combined multimodal features improved the test cohort C-index to 0.71 (<i>P</i> = 0.002). The model accurately predicted prognosis up to 5 years post-diagnosis (<i>P</i> &lt; 0.05 for all time-dependent AUCs) and stratified patients by overall survival (<i>P</i> = 0.012). SeAttn demonstrated attention shifts when comparing subtyping and prognosis models and revealed immuno-hot and immuno-cold stroma enrichment underlying survival differences. Novel prognostic markers, including <i>TPTE</i> mutation, microRNA cluster amplification, and <i>RIPK4</i>-<i>IL10RB</i> co-deletion, were identified and validated.</p> Conclusions <p>This multimodal DL framework demonstrates robust prognostic capabilities for NSCLC, integrating clinical, genetic, and imaging data to yield accurate survival estimates and identify biomarkers. These findings highlight the scalability of multimodal DL for broader cancer 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

Multimodal deep learning for survival prediction and biomarker discovery in non-small cell lung cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月17日

查看全文
  • Yiqing Wang,
  • Pinghui Xia,
  • Yang Xu,
  • Jianxin Xu,
  • Wenzhen Xu,
  • Wang Lv,
  • Junrong Yan,
  • Qiuxiang Ou,
  • Hua Bao,
  • Luming Wang,
  • Jian Hu

摘要

Background

Deep learning (DL) is revolutionizing high-dimensional analysis for clinical applications, with multimodal approaches showing promise in integrating diverse datasets and improving predictive accuracy. However, its use in prognostic assessment, particularly for non-small-cell lung cancer (NSCLC), remains limited.

Methods

Whole-slide imaging (WSI), next-generation sequencing (NGS), and clinical features from 2,366 NSCLC patients sourced from various databases were analyzed. A Sequential-Adapted Attention (SeAttn) model was developed to process WSI, while multiple DL models analyzed genetic and clinical data. Multimodal features were combined using a COX-based DL approach to predict long-term prognosis. Validation (N = 100) and test (N = 101) cohorts were used to confirm model performance.

Results

The SeAttn model achieved an area under the curve (AUC) of 0.98 for NSCLC histologic subtype prediction in the test cohort (P < 0.0001). Individually, WSI, clinical, and genetic features predicted prognosis with concordance indices (C-indices) of 0.55–0.67 using the test cohort. Combined multimodal features improved the test cohort C-index to 0.71 (P = 0.002). The model accurately predicted prognosis up to 5 years post-diagnosis (P < 0.05 for all time-dependent AUCs) and stratified patients by overall survival (P = 0.012). SeAttn demonstrated attention shifts when comparing subtyping and prognosis models and revealed immuno-hot and immuno-cold stroma enrichment underlying survival differences. Novel prognostic markers, including TPTE mutation, microRNA cluster amplification, and RIPK4-IL10RB co-deletion, were identified and validated.

Conclusions

This multimodal DL framework demonstrates robust prognostic capabilities for NSCLC, integrating clinical, genetic, and imaging data to yield accurate survival estimates and identify biomarkers. These findings highlight the scalability of multimodal DL for broader cancer applications.