Systematic comparison of multi-omics survival models reveals a widespread lack of noise resistance

As observed in several previous studies, integrating more molecular modalities in multi-omics cancer survival models may not always improve model accuracy. In this study, we compared eight deep learning and four statistical integration techniques for survival prediction on 17 multi-omics datasets, examining model performance in terms of overall accuracy and noise resistance. We found that one deep learning method, mean late fusion, and two statistical methods, PriorityLasso and BlockForest, performed best in terms of both noise resistance and overall discriminative and calibration performance. Nevertheless, all methods struggled to adequately handle noise when too many modalities were added. In summary, we confirmed that current multi-omics survival methods are not sufficiently noise resistant. We recommend relying on only modalities for which there is known predictive value for a particular cancer type until models that have stronger noise-resistance properties are developed. [Display omitted] •Multi-omics survival models are compared across The Cancer Genome Atlas (TCGA) datasets•Only one model performs better than a model trained using clinical data alone•PriorityLasso is recommended when the informativeness of modalities is uncertain With decreasing costs of high-throughput sequencing, more and more studies have started to provide multi-omics molecular profiles of patients with cancer. This has led to various developments of novel survival analysis approaches integrating these heterogeneous molecular and clinical groups of variables. Although some of these methods have reached state-of-the-art results in cancer survival prediction, many have demonstrated a decay in performance when integrating larger numbers of omics modalities. Wissel et al. perform an empirical comparison of 12 models for predicting survival from multi-omics data on 17 datasets from The Cancer Genome Atlas (TCGA). The authors show that all considered methods suffer from a lack of noise resistance. The study emphasizes the need for more noise-resistant multi-omics survival methods.