# Natural Language Processing in Electronic Health Records in Relation to Healthcare Decision-making: A Systematic Review

arXiv: https://arxiv.org/abs/2306.12834 · HTML: https://mlsanity.com/paper/2306.12834/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 157 references that are in the map.
- First posted on arXiv 22 Jun 2023.

## Builds on (most cited first, 23 of 23)

- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://mlsanity.com/paper/2004.09167/) (2020)
- [BEHRT: Transformer for Electronic Health Records](https://mlsanity.com/paper/1907.09538/) (2019)
- [Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data](https://mlsanity.com/paper/2001.05295/) (2020)
- [Learning to Summarize Radiology Findings](https://mlsanity.com/paper/1809.04698/) (2018)
- [AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning](https://mlsanity.com/paper/1802.07207/) (2018)
- [Natural Language Processing for EHR-Based Computational Phenotyping](https://mlsanity.com/paper/1806.04820/) (2018)
- [MT-Clinical BERT: Scaling Clinical Information Extraction with Multitask Learning](https://mlsanity.com/paper/2004.10220/) (2020)
- [Med7: a transferable clinical natural language processing model for electronic health records](https://mlsanity.com/paper/2003.01271/) (2020)
- [Generation of Synthetic Electronic Medical Record Text](https://mlsanity.com/paper/1812.02793/) (2018)
- [Augmenting Generative Adversarial Networks for Speech Emotion Recognition](https://mlsanity.com/paper/2005.08447/) (2020)
- [Multitask Learning from Augmented Auxiliary Data for Improving Speech Emotion Recognition](https://mlsanity.com/paper/2207.05298/) (2022)
- [Named Entity Recognition in Electronic Health Records Using Transfer Learning Bootstrapped Neural Networks](https://mlsanity.com/paper/1901.01592/) (2019)
- [Query Focused Multi-document Summarisation of Biomedical Texts](https://mlsanity.com/paper/2008.11986/) (2020)
- [Learning the Joint Representation of Heterogeneous Temporal Events for Clinical Endpoint Prediction](https://mlsanity.com/paper/1803.04837/) (2018)
- [Unsupervised Clinical Language Translation](https://mlsanity.com/paper/1902.01177/) (2019)
- [Query-Focused EHR Summarization to Aid Imaging Diagnosis](https://mlsanity.com/paper/2004.04645/) (2020)
- [Multiple Sclerosis Severity Classification From Clinical Text](https://mlsanity.com/paper/2010.15316/) (2020)
- [Image denoising and restoration with CNN-LSTM Encoder Decoder with Direct Attention](https://mlsanity.com/paper/1801.05141/) (2018)
- [Small-world networks for summarization of biomedical articles](https://mlsanity.com/paper/1903.02861/) (2019)
- [Natural language processing to identify lupus nephritis phenotype in electronic health records](https://mlsanity.com/paper/2112.10821/) (2021)

## Built on by (most cited first, 25 of 25)

- [A Comprehensive Evaluation of Large Language Models on Benchmark Biomedical Text Processing Tasks](https://mlsanity.com/paper/2310.04270/) (2023)
- [Clinical NLP with Attention-Based Deep Learning for Multi-Disease Prediction](https://mlsanity.com/paper/2507.01437/) (2025)
- [TA-RNN: an Attention-based Time-aware Recurrent Neural Network Architecture for Electronic Health Records](https://mlsanity.com/paper/2401.14694/) (2024)
- [PromptMind Team at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles](https://mlsanity.com/paper/2405.08373/) (2024)
- [Large Language Models for Healthcare Text Classification: A Systematic Review](https://mlsanity.com/paper/2503.01159/) (2025)
- [ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs](https://mlsanity.com/paper/2504.16394/) (2025)
- [Question-Answering Based Summarization of Electronic Health Records using Retrieval Augmented Generation](https://mlsanity.com/paper/2401.01469/) (2024)
- [LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding](https://mlsanity.com/paper/2507.02843/) (2025)
- [Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs](https://mlsanity.com/paper/2507.03001/) (2025)
- [Automatic identification of diagnosis from hospital discharge letters via weakly supervised Natural Language Processing](https://mlsanity.com/paper/2410.15051/) (2024)
- [PROMISE: A Framework for Developing Complex Conversational Interactions (Technical Report)](https://mlsanity.com/paper/2312.03699/) (2023)
- [Large language models for crowd decision making based on prompt design strategies using ChatGPT: models, analysis and challenges](https://mlsanity.com/paper/2403.15587/) (2024)
- [Use of natural language processing to extract and classify papillary thyroid cancer features from surgical pathology reports](https://mlsanity.com/paper/2406.00015/) (2024)
- [Named Clinical Entity Recognition Benchmark](https://mlsanity.com/paper/2410.05046/) (2024)
- [AI-assisted summary of suicide risk Formulation](https://mlsanity.com/paper/2412.10388/) (2024)
- [CAAT-EHR: Cross-Attentional Autoregressive Transformer for Multimodal Electronic Health Record Embeddings](https://mlsanity.com/paper/2501.18891/) (2025)
- [LLM-Driven Medical Document Analysis: Enhancing Trustworthy Pathology and Differential Diagnosis](https://mlsanity.com/paper/2506.19702/) (2025)
- [The Impact of Foundational Models on Patient-Centric e-Health Systems](https://mlsanity.com/paper/2507.21882/) (2025)
- [Weakly Supervised Fine-grained Span-Level Framework for Chinese Radiology Report Quality Assurance](https://mlsanity.com/paper/2508.08876/) (2025)
- [The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities](https://mlsanity.com/paper/2508.14032/) (2025)
- [From Staff Messages to Actionable Insights: A Multi-Stage LLM Classification Framework for Healthcare Analytics](https://mlsanity.com/paper/2509.05484/) (2025)
- [Benchmarking LLMs for Predictive Applications in the Intensive Care Units](https://mlsanity.com/paper/2512.20520/) (2025)
- [Structured Insight from Unstructured Data: Large Language Models for SDOH-Driven Diabetes Risk Prediction](https://mlsanity.com/paper/2601.13388/) (2026)
- [Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs](https://mlsanity.com/paper/2604.12049/) (2026)
- [Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports](https://mlsanity.com/paper/2605.09440/) (2026)

## Abstract (arXiv)

Background: Natural Language Processing (NLP) is widely used to extract clinical insights from Electronic Health Records (EHRs). However, the lack of annotated data, automated tools, and other challenges hinder the full utilisation of NLP for EHRs. Various Machine Learning (ML), Deep Learning (DL) and NLP techniques are studied and compared to understand the limitations and opportunities in this space comprehensively. Methodology: After screening 261 articles from 11 databases, we included 127 papers for full-text review covering seven categories of articles: 1) medical note classification, 2) clinical entity recognition, 3) text summarisation, 4) deep learning (DL) and transfer learning architecture, 5) information extraction, 6) Medical language translation and 7) other NLP applications. This study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Result and Discussion: EHR was the most commonly used data type among the selected articles, and the datasets were primarily unstructured. Various ML and DL methods were used, with prediction or classification being the most common application of ML or DL. The most common use cases were: the International Classification of Diseases, Ninth Revision (ICD-9) classification, clinical note analysis, and named entity recognition (NER) for clinical descriptions and research on psychiatric disorders. Conclusion: We find that the adopted ML models were not adequately assessed. In addition, the data imbalance problem is quite important, yet we must find techniques to address this underlining problem. Future studies should address key limitations in studies, primarily identifying Lupus Nephritis, Suicide Attempts, perinatal self-harmed and ICD-9 classification.