Deep learning with limited data: a transfer learning approach for transcriptomic survival prediction

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: Transfer learning outperformed tumor-specific baselines in 24 of 27 tumor types

• Primary Outcome: Disease-free survival prediction using concordance index

• Nnt Or Sensitivity: Concordance index values not specified, greatest improvements noted in smaller cohorts

• Confidence Interval: Not reported in abstract

Clinical Application

Limited by requirement for RNA-seq data and computational infrastructure; not readily applicable in routine clinical practice Relevant to Australian cancer genomics initiatives and precision oncology programs, though implementation would require significant bioinformatics infrastructure and validation in local populations Cancer patients with available transcriptomic data, particularly those with rare tumor types or limited cohort sizes

Abstract

BACKGROUND: Deep neural networks (DNNs) are promising for analyzing high-dimensional transcriptomic data in cancer research but are limited by data scarcity and heterogeneity. Transfer learning (TL), which leverages large datasets to improve performance on smaller ones, has been widely applied in classification and clustering, yet its use in survival prediction remains underexplored. METHODS: We evaluated transfer learning for disease-free survival prediction using RNA-seq data from 7509 patients across 27 tumor types from The Cancer Genome Atlas. A pan-cancer DNN was optimized via random search across 750 configurations. Tumor-specific baseline models were trained independently, while transfer learning models were built with a leave-one-out pre-training strategy followed by fine-tuning on the target tumor. Performance was assessed with the concordance index. Biological relevance was evaluated through a LIME-like interpretability approach and gene-set enrichment analysis. RESULTS: Transfer learning outperformed tumor-specific baselines in 24 of 27 tumor types, with the greatest improvements in smaller cohorts. Fine-tuning consistently enhanced predictions by adapting pan-cancer features to tumor-specific data. Enrichment analysis confirmed that the models captured both general oncogenic mechanisms and tumor-specific pathways. CONCLUSIONS: Transfer learning improves survival prediction from transcriptomic data, especially in small cohorts, by exploiting molecular patterns shared across cancers. These findings support transfer learning as a robust strategy for survival modeling and a step toward foundation models in molecular oncology.