Natural Language Processing in Electronic Health Records in relation to healthcare decision-making: A systematic review. (March 2023)

• Record Type: Journal Article
• Authors: Hossain, Elias; Rana, Rajib; Higgins, Niall; Soar, Jeffrey; Barua, Prabal Datta; Pisani, Anthony R.; Turner, Kathryn
• Is Part Of: Computers in biology and medicine. Volume 155(2023)
• Publication Date: 2023-03
• Subjects: Machine learning -- Electronic Health Records -- Medical natural language processing -- Artificial intelligence in medicine -- Automated tools -- State-of-the-art deep learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2023.106649
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: 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. Highlights: Physiological disorders, such as dementia and geriatric mental health, have been identified as promising research areas. SVM, boosting techniques, LR, LSTM, RNN, and CNNs are appropriate for analysing unstructured free text data for downstream EHRs applications. We find that while deep learning algorithms have achieved great success in the NLP sector, their application in the biological realm remains difficult. Transformer-based models for free text analysis, are yet to be used extensively, and conventional methods are currently preferred.