mlsanityData to 7 Oct 2026

sEHR-CE: Language modelling of structured EHR data for efficient and generalizable patient cohort expansion

arXiv 2211.17121 ↗First posted 30 Nov 2022cs.CL cs.LG stat.APcited by 3

Not on the map. Why?

Abstract (arXiv)

Electronic health records (EHR) offer unprecedented opportunities for in-depth clinical phenotyping and prediction of clinical outcomes. Combining multiple data sources is crucial to generate a complete picture of disease prevalence, incidence and trajectories. The standard approach to combining clinical data involves collating clinical terms across different terminology systems using curated maps, which are often inaccurate and/or incomplete. Here, we propose sEHR-CE, a novel framework based on transformers to enable integrated phenotyping and analyses of heterogeneous clinical datasets without relying on these mappings. We unify clinical terminologies using textual descriptors of concepts, and represent individuals' EHR as sections of text. We then fine-tune pre-trained language models to predict disease phenotypes more accurately than non-text and single terminology approaches. We validate our approach using primary and secondary care data from the UK Biobank, a large-scale research study. Finally, we illustrate in a type 2 diabetes use case how sEHR-CE identifies individuals without diagnosis that share clinical characteristics with patients.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 33 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

19 of 33 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Longformer: The Long-Document Transformercited by 3,362
  3. 2020Reformer: The Efficient Transformercited by 1,658
  4. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  5. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 996
  6. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  7. 2019BEHRT: Transformer for Electronic Health Recordscited by 258
  8. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 234
  9. 2019Time2Vec: Learning a Vector Representation of Timecited by 208
  10. 2015Doctor AI: Predicting Clinical Events via Recurrent Neural Networkscited by 205
  11. 2020Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Datacited by 85
  12. 2016Multi-layer Representation Learning for Medical Conceptscited by 68
7 more
  1. 2016Deepr: A Convolutional Net for Medical Recordscited by 59
  2. 2016DeepCare: A Deep Dynamic Memory Model for Predictive Medicinecited by 32
  3. 2021Unifying Heterogeneous Electronic Health Records Systems via Text-Based Code Embeddingcited by 24
  4. 2019TAPER: Time-Aware Patient EHR Representationcited by 22
  5. 2018Medical Concept Embedding with Time-Aware Attentioncited by 11
  6. 2019Learning Multimorbidity Patterns from Electronic Health Records Using Non-negative Matrix Factorisationcited by 7
  7. 2018Application of Clinical Concept Embeddings for Heart Failure Prediction in UK EHR datacited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Modelscited by 101
  2. 2023Interpreting deep embeddings for disease progression clusteringcited by 1
  3. 2024Exploring Long-Term Prediction of Type 2 Diabetes Microvascular Complicationscited by 0