Related Experiment Video
Updated: Aug 6, 2026
10:17
High-throughput and Comprehensive Drug Surveillance Using Multisegment Injection-Capillary Electrophoresis-Mass Spectrometry
Published on: April 23, 2019
Natural Language Processing to Identify Substance Use in Electronic Health Records: A Scoping Review
Chidimma Doris Azubuike1, Ahmed Farrag1, Kimia Zandbiglari1
1Department of Pharmaceutical Outcomes and Policy, University of Florida, Gainesville, FL, USA.
Substance Use & Addiction Journal
|July 21, 2026
Summary
Natural Language Processing (NLP) effectively identifies tobacco, opioid, and alcohol use in electronic health records (EHRs). However, stimulant and cannabinoid use detection needs improvement, and transparency in NLP methods is limited.
Area of Science:
- Computational linguistics
- Health informatics
- Substance use research
Background:
- Electronic health records (EHRs) contain valuable data on substance use.
- Natural Language Processing (NLP) offers potential for identifying substance use within unstructured EHR data.
- Characterizing NLP techniques and their performance in substance use identification is crucial for advancing clinical informatics.
Purpose of the Study:
- To systematically review and characterize Natural Language Processing (NLP) techniques used for identifying substance use in electronic health records (EHRs).
- To compare the performance of different NLP techniques across various substance types.
- To assess the transparency and reproducibility of NLP methods applied to substance use identification in EHRs.
Main Methods:
- Conducted a systematic literature search across major scientific databases (PubMed, Cochrane Library, Embase, Web of Science, ACM Digital Library, IEEE Xplore, Scopus).
- Included peer-reviewed original research in English applying NLP to identify non-prescription or problematic substance use in EHRs with full-text access and quantitative performance metrics.
- Extracted data on NLP techniques, substance types, and performance metrics from 86 eligible studies.
Main Results:
- Tobacco (42 studies), non-prescription opioids (30 studies), and alcohol (26 studies) were the most frequently identified substances.
- NLP techniques included rule-based (46 studies), conventional machine learning (39 studies), deep learning (17 studies), and large language/transformer-based models (22 studies).
- Most studies reported high performance metrics (>0.80), but transparency was limited, with only 30 studies providing annotation guidelines and 22 sharing code.
Conclusions:
- NLP demonstrates high performance in identifying common substance uses like tobacco, opioids, and alcohol in EHRs.
- Stimulants and cannabinoids remain underrepresented in NLP-based substance use identification research.
- Limited transparency and reproducibility necessitate routine sharing of code, datasets, and model specifications for advancing NLP in EHR research.
Related Concept Videos
01:24Substance Use Disorders Affecting Sleep
Substance use disorders involve a pattern of using drugs more extensively than intended and continuing use despite harmful consequences. This includes legal substances like alcohol and nicotine, as well as illegal drugs. These disorders often involve both physical and psychological dependence, reflecting compulsive use of substances that significantly alter thoughts, feelings, and behaviors, contributing to a major public health issue.
Understanding the concepts of physical dependence,...
Understanding the concepts of physical dependence,...
01:26Pharmaceutical Poisoning: Potential Scenarios
Pharmaceutical poisoning can occur through various channels, impacting an estimated 2 million hospitalized patients in the U.S. annually with serious adverse drug responses. These scenarios encompass both therapeutic uses, such as drug toxicity, where even standard dosages can lead to severe central nervous system depression, and non-therapeutic exposures, including accidental ingestion by children, and environmental and occupational exposures.Unintentional poisonings often involve exploratory...
01:19Pharmacovigilance
Post-marketing surveillance is a critical component of pharmaceutical regulation, often uncovering unanticipated adverse drug reactions (ADRs) once a drug is widely used over an extended period.
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...
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...