Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Variational Disentanglement for Rare Event Modeling
Authors: Zidi Xiu, Chenyang Tao, Michael Gao, Connor Davis, Benjamin A. Goldstein, Ricardo Henao10469-10477
AAAI 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Results on synthetic studies and diverse real-world datasets, including mortality prediction on a COVID-19 cohort, demonstrate that the proposed approach outperforms existing alternatives. |
| Researcher Affiliation | Academia | 1 Duke University 2 Duke Institute for Health Innovation EMAIL, EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1: Variational Inference with Extremals. |
| Open Source Code | Yes | Our implementation is based on Py Torch, and code to replicate our experiments are available from https://github.com/Zidi Xiu/VIE/. |
| Open Datasets | Yes | To this end, we synthesize a semi-synthetic dataset based on the Framingham study (Mitchell et al. 2010), a long-term cardiovascular survival cohort study... (ii) In P (O Brien et al. 2020): An in-patient data from DUHS... (iii) SEER (Ries et al. 2007): A public dataset studying cancer survival among adults curated by the U.S. Surveillance, Epidemiology, and End Results (SEER) Program... |
| Dataset Splits | Yes | Datasets have been randomly split into training, validation, and testing datasets with ratio 6:2:2. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments, such as CPU or GPU models, memory, or cloud instance types. |
| Software Dependencies | No | The paper states, "Our implementation is based on Py Torch," but does not specify its version number or any other software dependencies with their respective versions. |
| Experiment Setup | Yes | Datasets have been randomly split into training, validation, and testing datasets with ratio 6:2:2... In simulation studies, we repeat simulation ten times to obtain empirical AUC and AUPRC confidence intervals. For real world datasets, we applied bootstrapping to estimate the confidence intervals... For detailed settings please refer to the SM. |