Deep Extended Hazard Models for Survival Analysis
Authors: Qixian Zhong, Jonas W. Mueller, Jane-Ling Wang
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Numerical experiments also provide evidence that the proposed methods outperform existing statistical and deep learning approaches to survival analysis. |
| Researcher Affiliation | Collaboration | Qixian Zhong Department of Statistics and Data Science School of Economics and Wang Yanan Institute for Studies in Economics (WISE) Xiamen University qxzhong@xmu.edu.cn Jonas Mueller Amazon Web Services jonasmue@amazon.com Jane-Ling Wang Department of Statistics UC Davis janelwang@ucdavis.edu |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete access information (e.g., repository link, explicit statement of code release) for its methodology. |
| Open Datasets | Yes | COLON was collected from a sample of 929 subjects to evaluate the effects of the drugs levamisole and fluorouracil on resected colon carcinoma [45]. METABRIC includes paired DNA-RNA profiles and clinical information of 1,980 breast cancer patients, among which 57.7 percent are recorded to die from the cancer [16]. Rot GBSG is the breast cancer data extracted from the Rotterdam tumor bank [21] and the German Breast Cancer Study Group [54]. WHAS is a data set of 1,638 subjects for studying the factors of acute myocardial infarction [30]. |
| Dataset Splits | Yes | The evaluation for each dataset is done via 5-fold cross-validation, where we randomly split each dataset into 5 equal folds that correspond to different train/test sets. Within each fold, 20% of the training data is reserved as a validation set. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions a 'Gaussian kernel' and 'L2 regularization' but does not provide specific software names with version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | No | The paper mentions the use of neural networks and L2 regularization, and that the Appendix contains implementation details. However, it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed training configurations in the main text. |