What question did this study set out to answer?

The research aims to enhance prognostic assessment for non-small cell lung cancer using multimodal deep learning techniques.

February 21, 2026Open Access

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

Key Points

The research aims to enhance prognostic assessment for non-small cell lung cancer using multimodal deep learning techniques.
Analyzed data from 2,366 NSCLC patients using whole-slide imaging, next-generation sequencing, and clinical features.
Developed a Sequential-Adapted Attention model to process imaging data.
Utilized multiple deep learning models for genetic and clinical data analysis.
Combined multimodal features with a COX-based deep learning approach for prognosis prediction.
Validated model performance using dedicated cohorts.
The SeAttn model achieved an AUC of 0.98 for NSCLC histologic subtype prediction.
Combined multimodal features improved test cohort C-index to 0.71.
Model accurately predicted prognosis up to 5 years post-diagnosis.
Identified novel prognostic markers such as TPTE mutation and microRNA cluster amplification.
Highlighted immuno-hot and immuno-cold stroma enrichment associated with survival differences.

Abstract

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. 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. 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. 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.

Mark Helpful

Bookmark

Relay

View Full Paper