# ICE-NODE: Integration of Clinical Embeddings with Neural Ordinary Differential Equations

arXiv: https://arxiv.org/abs/2207.01873 · HTML: https://mlsanity.com/paper/2207.01873/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 5 Jul 2022.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Automatic differentiation in machine learning: a survey](https://mlsanity.com/paper/1502.05767/) (2015)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series](https://mlsanity.com/paper/1905.12374/) (2019)
- [GRAM: Graph-based Attention Model for Healthcare Representation Learning](https://mlsanity.com/paper/1611.07012/) (2016)
- [Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer](https://mlsanity.com/paper/1906.04716/) (2019)
- [Learning Differential Equations that are Easy to Solve](https://mlsanity.com/paper/2007.04504/) (2020)
- [MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare](https://mlsanity.com/paper/1810.09593/) (2018)
- [Multi-layer Representation Learning for Medical Concepts](https://mlsanity.com/paper/1602.05568/) (2016)
- [Minimal Gated Unit for Recurrent Neural Networks](https://mlsanity.com/paper/1603.09420/) (2016)
- [Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record](https://mlsanity.com/paper/1810.04793/) (2018)
- [Sequential Diagnosis Prediction with Transformer and Ontological Representation](https://mlsanity.com/paper/2109.03069/) (2021)
- [Medical Concept Embedding with Time-Aware Attention](https://mlsanity.com/paper/1806.02873/) (2018)
- [Temporal Self-Attention Network for Medical Concept Embedding](https://mlsanity.com/paper/1909.06886/) (2019)
- [Inpatient2Vec: Medical Representation Learning for Inpatients](https://mlsanity.com/paper/1904.08558/) (2019)

## Built on by (most cited first, 5 of 5)

- [CTP:A Causal Interpretable Model for Non-Communicable Disease Progression Prediction](https://mlsanity.com/paper/2308.09735/) (2023)
- [Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction](https://mlsanity.com/paper/2510.10454/) (2025)
- [Mixture of Coupled HMMs for Robust Modeling of Multivariate Healthcare Time Series](https://mlsanity.com/paper/2311.07867/) (2023)
- [Using latent representations to link disjoint longitudinal data for mixed-effects regression](https://mlsanity.com/paper/2510.25531/) (2025)
- [Embedding interpretable ℓ1-regression into neural networks for uncovering temporal structure in cell imaging](https://mlsanity.com/paper/2603.02899/) (2026)

## Abstract (arXiv)

Early diagnosis of disease can lead to improved health outcomes, including higher survival rates and lower treatment costs. With the massive amount of information available in electronic health records (EHRs), there is great potential to use machine learning (ML) methods to model disease progression aimed at early prediction of disease onset and other outcomes. In this work, we employ recent innovations in neural ODEs combined with rich semantic embeddings of clinical codes to harness the full temporal information of EHRs. We propose ICE-NODE (Integration of Clinical Embeddings with Neural Ordinary Differential Equations), an architecture that temporally integrates embeddings of clinical codes and neural ODEs to learn and predict patient trajectories in EHRs. We apply our method to the publicly available MIMIC-III and MIMIC-IV datasets, and we find improved prediction results compared to state-of-the-art methods, specifically for clinical codes that are not frequently observed in EHRs. We also show that ICE-NODE is more competent at predicting certain medical conditions, like acute renal failure, pulmonary heart disease and birth-related problems, where the full temporal information could provide important information. Furthermore, ICE-NODE is also able to produce patient risk trajectories over time that can be exploited for further detailed predictions of disease evolution.