Neural Temporal Point Processes For Modelling Electronic Health Records
arXiv:2007.13794
Abstract
The modelling of Electronic Health Records (EHRs) has the potential to drive more efficient allocation of healthcare resources, enabling early intervention strategies and advancing personalised healthcare. However, EHRs are challenging to model due to their realisation as noisy, multi-modal data occurring at irregular time intervals. To address their temporal nature, we treat EHRs as samples generated by a Temporal Point Process (TPP), enabling us to model what happened in an event with when it happened in a principled way. We gather and propose neural network parameterisations of TPPs, collectively referred to as Neural TPPs. We perform evaluations on synthetic EHRs as well as on a set of established benchmarks. We show that TPPs significantly outperform their non-TPP counterparts on EHRs. We also show that an assumption of many Neural TPPs, that the class distribution is conditionally independent of time, reduces performance on EHRs. Finally, our proposed attention-based Neural TPP performs favourably compared to existing models, whilst aligning with real world interpretability requirements, an important step towards a component of clinical decision support systems.
arXiv commentVersion accepted to Machine Learning for Health (ML4H) workshop at NeurIPS 2020. 10 pages, 5 figures, 3 tables. Code, pre-trained models and datasets available at https://github.com/babylonhealth/neuralTPPs
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis
- What do we need to build explainable AI systems for the medical domain?
- Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
- A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
- Fully Neural Network based Model for General Temporal Point Processes
- Generating Wikipedia by Summarizing Long Sequences
- Intensity-Free Learning of Temporal Point Processes
- BEHRT: Transformer for Electronic Health Records
- Learning Multivariate Hawkes Processes at Scale
- Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages
- Patient trajectory prediction in the Mimic-III dataset, challenges and pitfalls
- Unsupervised Representation for EHR Signals and Codes as Patient Status Vector
- Deep Fourier Kernel for Self-Attentive Point Processes