Summary of Esurvfusion: An Evidential Multimodal Survival Fusion Model Based on Gaussian Random Fuzzy Numbers, by Ling Huang et al.
EsurvFusion: An evidential multimodal survival fusion model based on Gaussian random fuzzy numbers
by Ling Huang, Yucheng Xing, Qika Lin, Su Ruan, Mengling Feng
First submitted to arxiv on: 2 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed EsurvFusion model aims to improve prediction quality for survival outcomes by combining heterogeneous data sources, such as clinical, imaging, text, and genomics. This task is challenging due to high heterogeneity and noise across data sources, which vary in structure, distribution, and context. The model incorporates modality-level reliability, estimates aleatoric and epistemic uncertainties, and combines predictions through an evidence-based decision fusion layer. This approach addresses data and model uncertainty, allowing for interpretable multimodal survival analysis. Experimental results on four datasets demonstrate the effectiveness of EsurvFusion in handling high heterogeneity data, achieving new state-of-the-art performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Multimodal survival analysis tries to predict how long people will live based on different types of data like medical records, images, text, and genes. The problem is tricky because this data can be very different and noisy. This paper proposes a new way to combine all these different data sources called EsurvFusion. It uses special math tools to handle uncertainty and reliability in the predictions. This allows for better survival analysis that shows how each type of data affects the results. |
