Strengthening Signal Detection in Pharmacovigilance by Using International Nonproprietary Name (INN) Stems

Area of Science:

• Pharmacology
• Drug Safety
• Pharmacovigilance

Background:

• The International Nonproprietary Name (INN) system, established by the WHO, uses stems to denote pharmacological relationships between substances.
• Current pharmacovigilance practices face challenges in efficiently detecting adverse drug reactions (ADRs).

Purpose of the Study:

• To propose and explore the use of INN stems for enhancing pharmacovigilance signal detection.
• To develop a framework for integrating stem-based analysis into existing pharmacovigilance systems.

Main Methods:

• Analysis of historical pharmacovigilance data and current practices.
• Development of a stem-based classification system for adverse effect profiling.
• Proposal for integration with artificial intelligence (AI) and machine learning (ML).

Main Results:

• Stem-based classification can aid in understanding the adverse-effects profile of drug classes.
• This approach facilitates the early identification of ADRs deviating from expected class effects.
• Potential for improved signal detection for new or repurposed drugs.

Conclusions:

• INN stem analysis offers a novel approach to enhance pharmacovigilance signal detection efficiency.
• Integrating stem-based analysis with AI/ML can improve post-marketing surveillance.
• This methodology holds promise for earlier identification of unexpected ADRs, ultimately improving patient safety.