A meta-learning approach for genomic survival analysis

Abstract

RNA sequencing has emerged as a promising approach in cancer prognosis as sequencing data becomes more easily and affordably accessible. However, it remains challenging to build good predictive models especially when the sample size is limited and the number of features is high, which is a common situation in biomedical settings. To address these limitations, we propose a meta-learning framework based on neural networks for survival analysis and evaluate it in a genomic cancer research setting. We demonstrate that, compared to regular transferlearning, meta-learning is a significantly more effective paradigm to leverage high-dimensional data that is relevant but not directly related to the problem of interest. Specifically, meta-learning explicitly constructs a model, from abundant data of relevant tasks, to learn a new task with few samples effectively. For the application of predicting cancer survival outcome, we also show that the metalearning framework with a few samples is able to achieve competitive performance with learning from scratch with a significantly larger number of samples. Finally, we demonstrate that the meta-learning model implicitly prioritizes genes based on their contribution to survival prediction and allows us to identify important pathways in cancer.

Forecasting adverse surgical events using self-supervised transfer learning for physiological signals

“…To better investigate our results, we report the average precision stratified by the top ten diagnoses for each target OR dataset and by the ASA physical statuses in Supplementary Discussion section “Evaluating by ASA physical status and diagnosis”. Finally, embedding models are frequently used to improve predictions in smaller target datasets as in [ 51 ]. We include an evaluation of PHASE in this setting in Supplementary Discussion section “Evaluating next models in a smaller target dataset”.…”

Artificial intelligence in cancer research: learning at different levels of data granularity

“…Meta-learning learns from the meta-data of previously experienced tasks, including model configurations (e.g., hyperparameter settings), evaluations (e.g., accuracies), and other measurable properties, enabling the search of an optimal model, or combinations of models, for a new task [89]. Recently, meta-learning has been applied to the prediction of cancer survival [90]. Despite the high adaptability of meta-learning, this study shows how the related tasks used for training should contain a reasonable amount of transferable information to achieve a significant improvement in performance compared to other learning strategies.…”

Transfer learning for non-image data in clinical research: a scoping review

“…Tabular data is probably the most used data type within clinical research. However, we only identified 15 studies using transfer learning on tabular data covering very different fields in medicine: two-thirds of them were from genetics [98][99][100][101][102], pathology [103][104][105], and intensive care [18,106], while the remaining five were from surgery [17], neonatology [107], infectious disease [108], pulmonology [109], and pharmacology [110]. Oncological applications like classification of cancer and prediction of cancer survival were common among the studies in genetics or pathology.…”