Natural Language Processing for EHR-Based Computational Phenotyping

2018/06/13 by Zexian Zeng, Yu Deng, Zeng, Zexian +7 · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial intelligence #Bioinformatics #Biomedical Text Mining and Ontologies #Categorization #Computation and Language (cs.CL) #Computational model #Computer science #Data science #FOS: Computer and information sciences #Feature (linguistics) #Generalizability theory #Interpretability #Machine Learning in Healthcare #Machine learning #Natural language processing #Pharmacogenomics #Phenome #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1806.04820

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2018/06/13 · arxiv created 2018/06/14 · arxiv updated 2018/06/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This article reviews recent advances in applying natural language processing (NLP) to Electronic Health Records (EHRs) for computational phenotyping. NLP-based computational phenotyping has numerous applications including diagnosis categorization, novel phenotype discovery, clinical trial screening, pharmacogenomics, drug-drug interaction (DDI) and adverse drug event (ADE) detection, as well as genome-wide and phenome-wide association studies. Significant progress has been made in algorithm development and resource construction for computational phenotyping. Among the surveyed methods, well-designed keyword search and rule-based systems often achieve good performance. However, the construction of keyword and rule lists requires significant manual effort, which is difficult to scale. Supervised machine learning models have been favored because they are capable of acquiring both classification patterns and structures from data. Recently, deep learning and unsupervised learning have received growing attention, with the former favored for its performance and the latter for its ability to find novel phenotypes. Integrating heterogeneous data sources have become increasingly important and have shown promise in improving model performance. Often better performance is achieved by combining multiple modalities of information. Despite these many advances, challenges and opportunities remain for NLP-based computational phenotyping, including better model interpretability and generalizability, and proper characterization of feature relations in clinical narratives

Citations

• Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation
• Narrative based medicine: Narrative based medicine in an evidence based world
• The Unreasonable Effectiveness of Data
• Learning to Diagnose with LSTM Recurrent Neural Networks
• SMOTE: Synthetic Minority Over-sampling Technique
• Using Machine Learning to Predict Laboratory Test Results
• Comparing Rule-Based and Deep Learning Models for Patient Phenotyping

Cited by

• HARMON-E: Hierarchical Agentic Reasoning for Multimodal Oncology Notes to Extract Structured Data
• A survey of using EHR as real-world evidence for discovering and validating new drug indications
• Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks

Related

• Health Analytics: a systematic review of approaches to detect phenotype cohorts using electronic health records
• A Large Language Model Outperforms Other Computational Approaches to the High-Throughput Phenotyping of Physician Notes
• Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review
• Natural Language Processing in Electronic Health Records in Relation to Healthcare Decision-making: A Systematic Review
• PHEONA: An Evaluation Framework for Large Language Model-based Approaches to Computational Phenotyping