Related Experiment Video
Updated: Jun 25, 2026
07:50
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
Extracting Drug Names and Associated Attributes From Discharge Summaries: Text Mining Study
Ghada Alfattni1,2, Maksim Belousov1, Niels Peek3,4,5
1Department of Computer Science, University of Manchester, Manchester, United Kingdom.
JMIR Medical Informatics
|May 5, 2021
Summary
This study demonstrates that deep learning methods can effectively extract medication information from clinical notes. The DrugEx system achieved high accuracy in identifying drugs and their attributes, improving data usability.
Area of Science:
- Computational linguistics
- Medical informatics
- Artificial intelligence in healthcare
Background:
- Clinical narratives contain valuable drug prescription data.
- Structured drug information is crucial for health tasks.
- Existing natural language processing (NLP) methods face challenges in drug information extraction.
Purpose of the Study:
- Evaluate NLP and deep learning for extracting drug names and attributes from clinical text.
- Link identified drug information to associated attributes.
- Conduct an extensive error analysis of different extraction methods.
Main Methods:
- Developed DrugEx system with Named Entity Recognizer (NER) and Relation Extraction (RE).
- Explored deep learning (BiLSTM-CRFs) with various embeddings for NER.
- Compared rule-based RE with context-aware LSTM for relation identification.
- Trained and evaluated models using 2018 n2c2 shared task data.
Main Results:
- Best model (BiLSTM-CRFs with PWE and CE) achieved F-scores of 0.921 for NER and 0.927 for RE.
- NER with pretrained word and character embeddings showed high classification efficiency.
- Rule-based RE outperformed context-aware LSTM for most relations.
- LSTM excelled in extracting challenging reason-drug relations.
Conclusions:
- The end-to-end DrugEx system shows feasibility for deep learning-based medication extraction.
- Deep learning approaches offer a promising solution for structuring clinical drug data.
- The system achieved encouraging results in extracting drug-related information from free text.
Keywords:
discharge summarieselectronic health recordsinformation extractionmedication prescriptionsnatural language processingMore Related Videos
Related Concept Videos
01:31Discharge Summary Forms
The discharge summary is crucial as it enables a smooth transition from a healthcare facility to a patient's home or another care setting. This critical document facilitates seamless continuity of care, ensuring patients receive the necessary support and attention.
Here's a detailed look at the key components and guidelines for preparing a discharge summary:
Here's a detailed look at the key components and guidelines for preparing a discharge summary:
01:26Drug Discovery: Overview
Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
01:17Drug Nomenclature
During the development of a new pharmaceutical, the manufacturer initially assigns a code name to the drug. Once approved, the drug receives a United States Adopted Name (USAN)—a generic, nonproprietary designation. Upon being listed in the United States Pharmacopeia, this nonproprietary name becomes the drug's official name. Additionally, the manufacturer assigns a proprietary name or trademark, which serves as the brand name under which the drug is marketed. It is worth noting that the same...
01:22Heart Failure Drugs: Diuretics
Heart failure and kidney perfusion are interconnected in a complex way. Reduced renal perfusion and venous congestion are two significant factors that contribute to renal dysfunction in heart failure. The kidneys, primarily responsible for fluid balance in the body, are adversely affected due to compromised cardiac output and increased venous pressure. In response to reduced renal perfusion, the kidneys activate neurohumoral mechanisms to restore balance. However, these mechanisms can be...
01:25Factors Influencing Drug Absorption: Disease States and Pharmacology
Multiple disease states can significantly influence the oral drug absorption process by affecting blood flow and the functionality of the gastrointestinal (GI) system. Various GI diseases, including conditions that alter GI motility, such as diarrhea, decreased acid secretions (achlorhydria), and infections, have been associated with reduced drug absorption.
Substances such as alcohol and specific drugs, including antineoplastics, can also negatively impact drug absorption. For instance,...
Substances such as alcohol and specific drugs, including antineoplastics, can also negatively impact drug absorption. For instance,...
01:27Factors Influencing Drug Absorption: Drug Dissolution
The pharmacokinetic journey of drugs from solid oral dosage forms into systemic circulation is multifaceted. It begins with disintegration, a prerequisite ensuring a solid dosage form's subdivision into minute particles. Dissolution occurs next as these granulated entities solubilize in gastrointestinal fluids. This solubilization is crucial for the succeeding stage, permeation, which describes the traversal of the drug across the intestinal membrane and its subsequent entry into the blood...