Summary of Survival Modeling Using Deep Learning, Machine Learning and Statistical Methods: a Comparative Analysis For Predicting Mortality After Hospital Admission, by Ziwen Wang et al.
Survival modeling using deep learning, machine learning and statistical methods: A comparative analysis for predicting mortality after hospital admission
by Ziwen Wang, Jin Wee Lee, Tanujit Chakraborty, Yilin Ning, Mingxuan Liu, Feng Xie, Marcus Eng Hock Ong, Nan Liu
First submitted to arxiv on: 4 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
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 This comparative study evaluates the performance of various survival analysis methods for predicting time-to-event outcomes in healthcare settings. The investigated techniques include traditional statistical models, state-of-the-art machine learning algorithms, and hybrid approaches. The evaluation metrics used were the concordance index (C-index) for model goodness-of-fit and integral Brier scores (IBS) for calibration. The results showed that deep learning models achieved comparable performance, with DeepSurv producing the best discrimination. Additionally, AutoScore-Survival offers a more parsimonious model with excellent interpretability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper compares different survival analysis methods to predict when an event will happen. They tested many approaches, including old statistical ones and new machine learning algorithms. The results show that some deep learning models do just as well, if not better, than others. One model called DeepSurv does the best job of predicting when something will happen. Another model, AutoScore-Survival, is simpler to understand and still works pretty well. |
Keywords
* Artificial intelligence * Deep learning * Machine learning
