IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers

Authors: Jingge Xiao, Leonie Basso, Wolfgang Nejdl, Niloy Ganguly, Sandipan Sikdar

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on three real-world datasets show that the proposed method can systematically outperform its predecessors, achieve state-of-the-art results, and have significant advantages in terms of data efficiency.
Researcher Affiliation Academia 1L3S Research Center, Leibniz Universit at Hannover 2Indian Institute of Technology Kharagpur
Pseudocode Yes Algorithm 1: IVP-VAE. The same IVP solver works for both encoder and decoder by solving IVPs in opposite directions.
Open Source Code Yes Source code is at https://github.com/jingge326/ivpvae.
Open Datasets Yes We evaluate our model on three real-world public EHR datasets from the Physio Net platform (Goldberger et al. 2000): MIMIC-IV (Johnson et al. 2020, 2023), Physio Net 2012 (Silva et al. 2012) and e ICU (Pollard et al. 2018, 2019).
Dataset Splits Yes Each dataset is randomly split into 80% for training, 10% for validation and 10% for testing.
Hardware Specification Yes All models were tested in the same computing environment with NVIDIA Tesla V100 GPUs.
Software Dependencies No The paper does not explicitly list key software components with specific version numbers for reproducibility (e.g., Python, PyTorch versions).
Experiment Setup Yes Hyperparameter settings are described in Appendix A.2.