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

Pharmacovigilance01:19

Pharmacovigilance

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...
Drug Regulation01:25

Drug Regulation

Drug regulation encompasses the management of drug usage by evaluating its safety and efficacy through assessments conducted by regulatory authorities. Regrettably, the history of drug regulation is marred by several catastrophic events. One such incident is the Elixir Sulfanilamide tragedy, in which the toxic compound diethyl glycol was included in a sweet-tasting medication, leading to numerous fatalities. This event prompted the enactment of the Food, Drug, and Cosmetic Act in 1938. Under...
Impact of Pharmacokinetic–Pharmacodynamic Models: Regulatory Decisions01:15

Impact of Pharmacokinetic–Pharmacodynamic Models: Regulatory Decisions

PK–PD modeling has significantly influenced FDA regulatory decisions, particularly drug approval, dosage optimization, and labeling. These models integrate pharmacokinetics (PK) and pharmacodynamics (PD) to predict drug behavior and effects, aiding in optimizing dosing regimens and enhancing the probability of clinical trial success.One notable example is Nesiritide (Natrecor®), a recombinant human brain natriuretic peptide for treating acute decompensated congestive heart failure (CHF).
Pharmaceutical Poisoning: Potential Scenarios01:26

Pharmaceutical 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...
Investigation of Disease Outbreaks01:23

Investigation of Disease Outbreaks

Multistate foodborne outbreaks pose significant public health risks and require meticulous investigation to identify sources and implement control measures. The Centers for Disease Control and Prevention (CDC) utilizes a dynamic seven-step process for these investigations, integrating data from laboratories, interviews, and environmental assessments to protect public health.Outbreak Detection: The detection of multistate outbreaks typically begins with PulseNet, the CDC's national laboratory...
Analysis of Population Pharmacokinetic Data01:12

Analysis of Population Pharmacokinetic Data

Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...

You might also read

Related Articles

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

Sort by
Same author

Effects of glucagon-like peptide-1 receptor agonists on anthropometric and adiposity measures in patients with antipsychotic-induced weight gain: A systematic review and meta-analysis.

Journal of psychopharmacology (Oxford, England)·2026
Same author

Theoretical Framework and Key Considerations for Time-to-Onset Analysis in Spontaneous Reporting Systems.

Drug safety·2026
Same author

Uncovering Coenzyme Q10-Related Genetic Determinants of Statin-Associated Muscle Symptoms: Evidence from the UK Biobank and the All of Us Research Program.

Clinical pharmacology and therapeutics·2026
Same author

Calvert Formula Modification for Optimized Carboplatin Dosing in Breast Cancer with Preserved Renal Function.

Pharmaceutics·2026
Same author

Prioritization of adverse events related to integrase inhibitors and NNRTIs: a disproportionality analysis using data from the FAERS database.

The Journal of antimicrobial chemotherapy·2026
Same author

Rosuvastatin Versus Atorvastatin for Cardiovascular Disease Risk in Patients with Type 2 Diabetes: A Korean Cohort Study.

Pharmaceuticals (Basel, Switzerland)·2025

Related Experiment Videos

Large Language Models for World Health Organization-Uppsala Monitoring Centre Drug-Adverse Event Causality Assessment

Young Mi Ha1, Minjung Kim1, YoungIn Bang2

  • 1Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul, Republic of Korea.

Journal of Medical Internet Research
|July 8, 2026
PubMed
Summary

Large language models (LLMs) show moderate agreement in drug-adverse event causality assessment, offering potential support for pharmacovigilance but not independent decision-making.

Keywords:
GPTGeminiWHO-UMC causality assessmentWorld Health Organization–Uppsala Monitoring Centre causality assessmentgenerative pretrained transformerlarge language modelsprompt engineering

Related Experiment Videos

Area of Science:

  • Pharmacovigilance and Artificial Intelligence
  • Natural Language Processing in Healthcare

Background:

  • Causality assessment in pharmacovigilance is crucial but labor-intensive and subjective.
  • The utility of large language models (LLMs) for formal World Health Organization-Uppsala Monitoring Centre (WHO-UMC) causality assessment requires investigation.

Purpose of the Study:

  • To evaluate the performance of LLMs in conducting WHO-UMC drug-adverse event causality assessments.
  • To compare different prompting strategies and LLM models for this task.

Main Methods:

  • A dataset of 55 cases (337 drug-level assessments) from the FDA Adverse Event Reporting System was curated.
  • Multiple LLMs (GPT-5.4, Gemini 2.5 Flash/Pro) and prompting strategies (standard, CoT, few-shot, etc.) were employed.
  • Agreement with expert assessments was measured using Cohen κ, weighted κ, and accuracy metrics.

Main Results:

  • LLM performance varied, with Cohen κ ranging from 0.368 to 0.641.
  • Gemini 2.5 Flash with CoT-self-consistency prompting achieved the highest metrics (weighted κ=0.821, accuracy=0.804).
  • Performance was strongest for
  • Certain
  • and
  • Unlikely
  • categories, but lower for
  • Possible
  • causality.

Conclusions:

  • LLMs demonstrate moderate to substantial agreement with expert judgment in WHO-UMC causality assessment.
  • LLMs show potential as supportive tools for preliminary case triage in pharmacovigilance.
  • Further research with larger datasets and raw narrative reports is recommended.