# MiGHT-EHR: A Multi-task Graph Transformer for Heterogeneous Temporal Electronic Health Records

arXiv: https://arxiv.org/abs/2608.06430 · HTML: https://mlsanity.com/paper/2608.06430/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 5 Aug 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction](https://mlsanity.com/paper/2005.12833/) (2020)
- [Doctor AI: Predicting Clinical Events via Recurrent Neural Networks](https://mlsanity.com/paper/1511.05942/) (2015)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [GRAM: Graph-based Attention Model for Healthcare Representation Learning](https://mlsanity.com/paper/1611.07012/) (2016)
- [Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis](https://mlsanity.com/paper/1706.03446/) (2017)
- [Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks](https://mlsanity.com/paper/1706.05764/) (2017)
- [Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer](https://mlsanity.com/paper/1906.04716/) (2019)
- [Deepr: A Convolutional Net for Medical Records](https://mlsanity.com/paper/1607.07519/) (2016)
- [ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context](https://mlsanity.com/paper/1911.12216/) (2019)
- [SafeDrug: Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinations](https://mlsanity.com/paper/2105.02711/) (2021)
- [AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration](https://mlsanity.com/paper/1911.12205/) (2019)
- [StageNet: Stage-Aware Neural Networks for Health Risk Prediction](https://mlsanity.com/paper/2001.10054/) (2020)
- [Change Matters: Medication Change Prediction with Recurrent Residual Networks](https://mlsanity.com/paper/2105.01876/) (2021)
- [GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source Learning](https://mlsanity.com/paper/2207.09858/) (2022)
- [Heterogeneous Similarity Graph Neural Network on Electronic Health Records](https://mlsanity.com/paper/2101.06800/) (2021)
- [PyHealth: A Python Library for Health Predictive Models](https://mlsanity.com/paper/2101.04209/) (2021)
- [Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records](https://mlsanity.com/paper/2403.04086/) (2024)
- [Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax](https://mlsanity.com/paper/2209.00655/) (2022)

## Abstract (arXiv)

Learning from Electronic Health Records (EHRs) has gained significant attention due to its potential to improve clinical prediction. However, effective learning remains challenging because EHRs encode heterogeneous, temporally ordered clinical interactions. In particular, EHRs contain: (i) heterogeneous clinical entities, including patients, visits, diagnoses, prescriptions, and procedures, together with their heterogeneous interactions, (ii) longitudinal patient trajectories across hospital visits and (iii) shared statistical dependencies across related clinical prediction tasks. Existing EHR learning methods capture only a subset of these properties. To bridge this gap, we propose Multi-task Graph transformer for Heterogeneous Temporal EHRs (MiGHT-EHR), which jointly models all three within a unified representation learning method. MiGHT-EHR constructs a heterogeneous graph from EHRs in which nodes represent clinical entities and edges connect statistically associated entities identified via normalized point-wise mutual information. Across MIMIC-III and MIMIC-IV datasets, MiGHT-EHR outperforms state-of-the-art methods on average across four tasks: drug recommendation, prediction of length-of-stay, mortality, and readmission, with particularly strong improvements in mortality and readmission prediction. Furthermore, a post-hoc analysis of the learned representations reveals that patient neighborhoods are organized by clinical outcomes, salient medical concepts are recoverable as linear directions in the representation space, and task probabilities are well calibrated. Collectively, these findings demonstrate that MiGHT-EHR representations support diverse prediction tasks while preserving clinically interpretable structure.