# Deep Learning with Heterogeneous Graph Embeddings for Mortality Prediction from Electronic Health Records

arXiv: https://arxiv.org/abs/2012.14065 · HTML: https://mlsanity.com/paper/2012.14065/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2020.

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

- [Federated Learning of Medical Concepts Embedding using BEHRT](https://mlsanity.com/paper/2305.13052/) (2023)
- [HealthGAT: Node Classifications in Electronic Health Records using Graph Attention Networks](https://mlsanity.com/paper/2403.18128/) (2024)
- [CATNet: Cross-event Attention-based Time-aware Network for Medical Event Prediction](https://mlsanity.com/paper/2204.13847/) (2022)
- [Exploring a Graph-based Approach to Offline Reinforcement Learning for Sepsis Treatment](https://mlsanity.com/paper/2509.03393/) (2025)
- [CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study](https://mlsanity.com/paper/2608.02663/) (2026)

## Abstract (arXiv)

Computational prediction of in-hospital mortality in the setting of an intensive care unit can help clinical practitioners to guide care and make early decisions for interventions. As clinical data are complex and varied in their structure and components, continued innovation of modeling strategies is required to identify architectures that can best model outcomes. In this work, we train a Heterogeneous Graph Model (HGM) on Electronic Health Record data and use the resulting embedding vector as additional information added to a Convolutional Neural Network (CNN) model for predicting in-hospital mortality. We show that the additional information provided by including time as a vector in the embedding captures the relationships between medical concepts, lab tests, and diagnoses, which enhances predictive performance. We find that adding HGM to a CNN model increases the mortality prediction accuracy up to 4%. This framework serves as a foundation for future experiments involving different EHR data types on important healthcare prediction tasks.