The Impact of Variability in Patient Exposure During Premarket Clinical Development on Postmarket Safety Outcomes

Description and Validation of a Novel AI Tool, LabelComp, for the Identification of Adverse Event Changes in FDA Labeling

INTRODUCTION

The accurate identification and timely updating of adverse reactions in drug labeling are crucial for patient safety and effective drug use. Postmarketing surveillance plays a pivotal role in identifying previously undetected adverse events (AEs) that emerge when a drug is used in broader and more diverse patient populations. However, traditional methods of updating drug labeling with new AE information have been manual, time consuming, and error prone. This paper introduces the LabelComp tool, an innovative artificial intelligence (AI) tool designed to enhance the efficiency and accuracy of postmarketing drug safety surveillance. Utilizing a combination of text analytics and a trained Bidirectional Encoder Representations from Transformers (BERT) model, the LabelComp tool automatically identifies changes in AE terms from updated drug labeling documents.

OBJECTIVE

Our objective was to create and validate an AI tool with high accuracy that could enable researchers and FDA reviewers to efficiently identify safety-related drug labeling changes.

RESULTS

Our validation study of 87 drug labeling PDF pairs demonstrates the tool's high accuracy, with F1 scores of overall performance ranging from 0.795 to 0.936 across different evaluation tiers and a recall of at least 0.997 with only one missed AE out of 483 total AEs detected, indicating the tool's efficacy in identifying new AEs.

CONCLUSION

The LabelComp tool can support drug safety surveillance and inform regulatory decision-making. The publication of this tool also aims to encourage further community-driven enhancements, aligning with broader interests in applying AI to advance regulatory science and public health.

Prescriber perceptions of boxed warnings: A qualitative study

PURPOSE

To explore how boxed warning (BW) information fits within the context of prescribers' overall treatment decision-making and communication with patients.

METHODS

In-depth interviews (N = 52) were conducted with primary care providers and specialists. Participants were presented with one of two prescribing scenarios: (1) estrogen vaginal inserts to treat vulvovaginal atrophy (VVA) associated with menopause; or (2) direct-acting antivirals (DAA) to treat chronic hepatitis C virus infection (HCV). The semi-structured interviews explored participants' treatment decision-making within the scenario, reactions to current prescribing information for a product within the FDA-approved drug class, as well as their perceptions of BWs generally.

RESULTS

Across scenarios, providers described that the BW is only one of several factors that influence treatment decision-making. In the VVA scenario, symptom severity, family history, and experience with nonprescription drugs were raised as common factors that influence prescribing considerations; compared to comorbid infections, viral load, and HCV genotype in the HCV scenario. Perceptions of the DAA BW were generally positive or neutral, as many participants found the information important and appropriate. The VVA BW was viewed less favorably, with many participants stating the BW overstates the risk for this drug.

CONCLUSIONS

Findings suggest that BWs are one of several factors that influence providers' treatment decisions, and BW influence largely depends on context. Providers across scenarios expressed notable differences in their perceptions of the risk information provided in the presented BWs; however, across scenarios participants expressed consideration of how patients may perceive the BW.

Analysis and enhancement of risk management for ethnic differences in antineoplastic drugs in Japan

Background

Risk management in the post-marketing phase is crucial to minimize health problems caused by drugs. Because ethnic factors may affect drug safety, the objective of this study was to explore concrete approaches to reflecting ethnic factors in risk management under multi-regional drug development.

Methods

We assessed Pharmaceuticals and Medical Devices Agency (PMDA) review reports on antineoplastic drugs approved as new molecular entities in the last 10 years to identify any differences in the incidence of adverse drug reactions (ADRs) related to myelosuppression, hepatic impairment, renal impairment, and interstitial lung disease between Japanese and non-Japanese populations. In addition, we investigated how those ADRs were handled in the labeling of each drug.

Results

In total, 44 drugs were available for comparing the incidence of ADRs between Japanese and non-Japanese populations. Of these, 32 drugs had a higher incidence of ADRs in the Japanese population. However, the incidence of ADRs in the Japanese population was described in the labeling for 7 drugs, and only the incidence in the overall population in multi-regional phase III trials was described in the labeling for the remaining 25 drugs. Of these 25 drugs, two drugs were immediately placed under emergency safety control measures after approval because of the high incidence of ADRs in Japanese patients.

Conclusions

For drugs that might cause serious ADRs and with a higher incidence in the Japanese population, information should be provided on the incidence in the Japanese population as well as in the overall population.

Sources of Evidence Triggering and Supporting Safety-Related Labeling Changes: A 10-Year Longitudinal Assessment of 22 New Molecular Entities Approved in 2008 by the US Food and Drug Administration

INTRODUCTION

New safety issues concerning US FDA-approved drugs are commonly communicated through safety-related labeling changes. Therefore, to optimize and refine postmarket safety surveillance strategies, it is important to comprehensively characterize the sources of data giving rise to safety-related labeling changes.

OBJECTIVES

Our objective was to characterize the sources of data triggering and supporting the identification of new safety risks of FDA-approved drugs communicated through safety-related labeling changes.

METHODS

We conducted a retrospective study with a 10-year observation period using FDA's internal electronic data repositories for all prescription new molecular entities (NME) approved in 2008. We collected and analyzed information on new safety issues, the section of the full prescribing information updated, initiators (FDA, drug manufacturer), and triggering and supporting sources of evidence.

RESULTS

Among 22 NMEs approved in 2008, 189 new safety issues for 18 NMEs were identified. Compared to drug manufacturer, FDA initiated safety-related labeling changes in nine of the ten changes to the Boxed Warnings, 28 of the 52 changes to the Warnings and Precautions, and 43 of the 134 changes to the Adverse Reactions sections of the full prescribing information. The most frequent triggering sources of evidence included the drug manufacturer safety database (32.3%) and FDA Adverse Event Reporting System (FAERS) safety reports (15.3%) for all relevant sections of the full prescribing information, and class-labeling changes (17.5%) for Boxed Warnings and the Warnings and Precautions sections. The most frequent triggering source of evidence was FAERS safety reports (69%) in the first year after drug approval and the drug manufacturer safety database in subsequent years.

CONCLUSIONS

Our findings emphasize the continued importance of safety reports from FAERS and drug manufacturer safety databases and a comprehensive drug safety surveillance program throughout a drug's lifecycle.