Leveraging Unstructured Data in Electronic Health Records to Detect Adverse Events From Pediatric Drug Use - a Scoping Review

Su Golder; Karen O'Connor; Guillermo Lopez-Garcia; Nicholas Tatonetti; Graciela Gonzalez-Hernandez

doi:10.1101/2025.03.20.25324320

Leveraging Unstructured Data in Electronic Health Records to Detect Adverse Events From Pediatric Drug Use - a Scoping Review

Su Golder, Karen O'Connor, Guillermo Lopez-Garcia, Nicholas Tatonetti, Graciela Gonzalez-Hernandez

Health Sciences

Research output: Working paper › Preprint

Abstract

Adverse drug events (ADEs) in pediatric populations pose significant public health challenges, yet research on their detection and monitoring remains limited. This scoping review evaluates the use of unstructured data from electronic health records (EHRs) to identify ADEs in children. We searched six databases, including MEDLINE, Embase and IEEE Xplore, in September 2024. From 984 records, only nine studies met our inclusion criteria, indicating a significant gap in research towards identify ADEs in children. We found that unstructured data in EHRs can indeed be of value and enhance pediatric pharmacovigilance, although its use has been so far very limited. Traditional Natural Language Processing (NLP) methods have been employed to extract ADEs, but the approaches utilized face challenges in generalizability and context interpretation. These challenges could be addressed with recent advances in transformer-based models and large language models (LLMs), unlocking the use of EHR data at scale for pediatric pharmacovigilance.

Original language	English
DOIs	https://doi.org/10.1101/2025.03.20.25324320
Publication status	Published - 20 Mar 2025

Publication series

Name	medRxiv
Publisher	Cold Spring Harbor Laboratory Press

Access to Document

10.1101/2025.03.20.25324320Licence: CC BY-NC-ND

Cite this

@techreport{7d1a588a55f247509eec66511db8ba6c,

title = "Leveraging Unstructured Data in Electronic Health Records to Detect Adverse Events From Pediatric Drug Use - a Scoping Review",

abstract = "Adverse drug events (ADEs) in pediatric populations pose significant public health challenges, yet research on their detection and monitoring remains limited. This scoping review evaluates the use of unstructured data from electronic health records (EHRs) to identify ADEs in children. We searched six databases, including MEDLINE, Embase and IEEE Xplore, in September 2024. From 984 records, only nine studies met our inclusion criteria, indicating a significant gap in research towards identify ADEs in children. We found that unstructured data in EHRs can indeed be of value and enhance pediatric pharmacovigilance, although its use has been so far very limited. Traditional Natural Language Processing (NLP) methods have been employed to extract ADEs, but the approaches utilized face challenges in generalizability and context interpretation. These challenges could be addressed with recent advances in transformer-based models and large language models (LLMs), unlocking the use of EHR data at scale for pediatric pharmacovigilance.",

author = "Su Golder and Karen O'Connor and Guillermo Lopez-Garcia and Nicholas Tatonetti and Graciela Gonzalez-Hernandez",

year = "2025",

month = mar,

day = "20",

doi = "10.1101/2025.03.20.25324320",

language = "English",

series = "medRxiv",

publisher = "Cold Spring Harbor Laboratory Press",

type = "WorkingPaper",

institution = "Cold Spring Harbor Laboratory Press",

}

TY - UNPB

T1 - Leveraging Unstructured Data in Electronic Health Records to Detect Adverse Events From Pediatric Drug Use - a Scoping Review

AU - Golder, Su

AU - O'Connor, Karen

AU - Lopez-Garcia, Guillermo

AU - Tatonetti, Nicholas

AU - Gonzalez-Hernandez, Graciela

PY - 2025/3/20

Y1 - 2025/3/20

N2 - Adverse drug events (ADEs) in pediatric populations pose significant public health challenges, yet research on their detection and monitoring remains limited. This scoping review evaluates the use of unstructured data from electronic health records (EHRs) to identify ADEs in children. We searched six databases, including MEDLINE, Embase and IEEE Xplore, in September 2024. From 984 records, only nine studies met our inclusion criteria, indicating a significant gap in research towards identify ADEs in children. We found that unstructured data in EHRs can indeed be of value and enhance pediatric pharmacovigilance, although its use has been so far very limited. Traditional Natural Language Processing (NLP) methods have been employed to extract ADEs, but the approaches utilized face challenges in generalizability and context interpretation. These challenges could be addressed with recent advances in transformer-based models and large language models (LLMs), unlocking the use of EHR data at scale for pediatric pharmacovigilance.

AB - Adverse drug events (ADEs) in pediatric populations pose significant public health challenges, yet research on their detection and monitoring remains limited. This scoping review evaluates the use of unstructured data from electronic health records (EHRs) to identify ADEs in children. We searched six databases, including MEDLINE, Embase and IEEE Xplore, in September 2024. From 984 records, only nine studies met our inclusion criteria, indicating a significant gap in research towards identify ADEs in children. We found that unstructured data in EHRs can indeed be of value and enhance pediatric pharmacovigilance, although its use has been so far very limited. Traditional Natural Language Processing (NLP) methods have been employed to extract ADEs, but the approaches utilized face challenges in generalizability and context interpretation. These challenges could be addressed with recent advances in transformer-based models and large language models (LLMs), unlocking the use of EHR data at scale for pediatric pharmacovigilance.

U2 - 10.1101/2025.03.20.25324320

DO - 10.1101/2025.03.20.25324320

M3 - Preprint

C2 - 40166566

T3 - medRxiv

BT - Leveraging Unstructured Data in Electronic Health Records to Detect Adverse Events From Pediatric Drug Use - a Scoping Review

ER -