Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Methods of Documentation VII: EMR01:30

Methods of Documentation VII: EMR

1.4K
Electronic Medical Records (EMRs) primarily center around electronically documenting patients' health information within a single healthcare organization or practice. They contain essential clinical data related to a patient's medical history, diagnoses, medications, treatment plans, lab results, and other pertinent information relevant to the specific encounter or episode of care. EMRs are designed to streamline documentation and workflow processes within individual healthcare...
1.4K
Survival Tree01:19

Survival Tree

390
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
390

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An Expedited Chart Review Process for Large Database Studies Using Natural Language Processing and Multiwave Adaptive Sampling.

Epidemiology (Cambridge, Mass.)·2026
Same author

Serious Infection in Crohn's Disease Patients Treated With Ustekinumab: US Food and Drug Administration Active Postmarket Risk Identification and Analysis in the Sentinel Initiative.

Clinical pharmacology and therapeutics·2026
Same author

Association of GLP-1 receptor agonists with intentional self-harm in patients with type 2 diabetes: a Sentinel Distributed Database study.

BMJ open diabetes research & care·2026
Same author

Characterization and comparison of structured and unstructured electronic health record data mapped to MedDRA for post-marketing surveillance.

JAMIA open·2026
Same author

Use of Clinical Notes to Assess Neuropsychiatric Events After Montelukast Initiation.

JAMA network open·2026
Same author

Strengthening inferential studies in the FDA Sentinel initiative: results from a methodological demonstration project.

NPJ digital medicine·2025

Related Experiment Video

Updated: Jan 18, 2026

Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
06:16

Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease

Published on: August 9, 2024

813

Electronic health record-enhanced signal detection using tree-based scan statistic methods.

Massimiliano Russo1,2, Sushama Kattinakere Sreedhara2, Joshua Smith3

  • 1Department of Statistics, The Ohio State University, Columbus, OH, United States.

American Journal of Epidemiology
|September 8, 2025
PubMed
Summary
This summary is machine-generated.

Tree-based scan statistics (TBSS) methods were enhanced to analyze electronic health records (EHR), detecting adverse drug effects like headaches associated with diabetes medications.

Keywords:
data miningelectronic health recordsnatural language processingpermutation testingpharmacoepidemiologyreal-world datatree-based scan statistics

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.9K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.6K

Related Experiment Videos

Last Updated: Jan 18, 2026

Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
06:16

Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease

Published on: August 9, 2024

813
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.9K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.6K

Area of Science:

  • Pharmacovigilance
  • Data Mining
  • Health Informatics

Background:

  • Tree-based scan statistics (TBSS) traditionally use diagnosis codes from claims data to detect adverse drug effects.
  • Application of TBSS to rich electronic health record (EHR) data, including clinical notes and lab results, has not been explored.
  • Integrating diverse EHR data sources can potentially improve the sensitivity of TBSS for detecting safety signals.

Purpose of the Study:

  • To develop and evaluate approaches for integrating EHR data into TBSS analyses.
  • To assess the utility of TBSS with various EHR data sources for detecting adverse drug events.
  • To compare the performance of TBSS using diagnosis codes versus NLP-derived outcomes, lab results (binary and continuous).

Main Methods:

  • Developed novel approaches to incorporate EHR data, including natural language processing (NLP) outcomes and laboratory results, into TBSS.
  • Analyzed data from a comparative cohort study of second-generation sulfonylureas (SUs) and dipeptidyl peptidase 4 (DPP-4) inhibitors in adults with type 2 diabetes.
  • Sequentially added data sources to the TBSS model: diagnosis codes, NLP outcomes, binary lab results, and continuous lab results.

Main Results:

  • Diagnosis codes alone did not yield alerts for hypoglycemia-related events in inpatient or emergency settings.
  • Incorporating NLP-derived outcomes identified 'Headaches' as a potential safety signal (P = .047), a nonspecific symptom of hypoglycemia.
  • Adding binary and continuous lab results progressively confirmed the 'Headaches' alert, demonstrating increased signal detection capability.

Conclusions:

  • Integrating EHR data, particularly NLP-derived outcomes and lab results, significantly enhances the capability of TBSS for detecting potential adverse drug events.
  • TBSS adapted for EHR data can serve as a valuable tool for identifying safety signals that may be missed by traditional claims data analysis.
  • This approach holds promise for proactive pharmacovigilance and improving patient safety in real-world clinical settings.