Summary of Coxse: Exploring the Potential Of Self-explaining Neural Networks with Cox Proportional Hazards Model For Survival Analysis, by Abdallah Alabdallah et al.
CoxSE: Exploring the Potential of Self-Explaining Neural Networks with Cox Proportional Hazards Model for Survival Analysis
by Abdallah Alabdallah, Omar Hamed, Mattias Ohlsson, Thorsteinn Rögnvaldsson, Sepideh Pashami
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
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 CoxSE model combines self-explaining neural networks (SENN) with Cox proportional hazards modeling for survival analysis, aiming to retain explainability while increasing predictive power. The authors introduce a novel locally explainable Cox proportional hazards model that estimates a locally-linear log-hazard function using SENN. They also propose a hybrid model, CoxSENAM, which enables control over the stability and consistency of generated explanations. Compared to existing methods like DeepSurv and NAM-based models, CoxSE and CoxSENAM demonstrate improved explainability and robustness to non-informative features. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary For survival analysis, researchers are exploring ways to balance predictive power with model interpretability. The new CoxSE model, which combines self-explaining neural networks (SENN) with Cox proportional hazards modeling, aims to achieve this balance. By estimating a locally-linear log-hazard function using SENN, the model can provide more stable and consistent explanations while maintaining the same expressiveness as black-box models. |
