Intelligent Automation Improved Efficiency in Pharmacovigilance Safety Signal Assessment

Pharmacovigilance System Integrating Artificial Intelligence for Automated Adverse Event Detection

Signal mining and safety profile analysis of prucalopride: a pharmacovigilance analysis of the FDA adverse event reporting system (FAERS) database

Prucalopride is a highly selective 5-HT 4 agonist used for chronic idiopathic constipation and gastroparesis. Although clinical trials suggest a favorable safety profile, real-world data on rare adverse events (AEs) remain scarce. This study mined the FDA Adverse Event Reporting System (FAERS) to detect safety signals warranting clinical attention. FAERS data from December 14, 2018 to September 30, 2025 were collected via OpenVigil 2.1. AEs were categorised using the Medical Dictionary for Regulatory Activities. Signal detection was performed using four specific algorithms: the Proportional Reporting Ratio (PRR), the Reporting Odds Ratio (ROR), the Multi-item Gamma Poisson Shrinker (MGPS), and the Bayesian Confidence Propagation Neural Network (BCPNN). Kappa consistency and sensitivity analyses were performed. We collected 1101 prucalopride-related reports and identified 35 positive adverse drug event (ADE) signals across 10 system organ classes. Gastrointestinal disorders dominated (12 signals, 373 cases), followed by psychiatric disorders (9 signals, 107 cases) and nervous system disorders (5 signals, 181 cases). Frequent reactions included headache, diarrhoea, nausea, dizziness and abdominal pain. Signal intensity varied across algorithms; gastrointestinal bacterial overgrowth emerged as a strong signal in all four. We found 19 ADEs that were not listed in the prescribing information of China, the United States, or Europe; serious unlabeled signals included intestinal obstruction and serotonin syndrome. Notably, depression, suicidal ideation, depressed mood, and nightmares appear only in the United States prescribing information. Prucalopride-related ADEs involve multiple organ systems, predominantly presenting as gastrointestinal disorders, psychiatric disorders and nervous system disorders. Some ADEs not included in the instructions may be serious adverse events, require great attention from clinicians. For patients with underlying comorbidities or those undergoing combination therapy, close monitoring for potential severe adverse events is essential to ensure clinical medication safety.

Optimising Pharmacovigilance Efficiency with MLIT (Machine Learning for Intelligent Triage): A Tool for Statistical Safety Alerts.

BACKGROUND AND AIM Pharmacovigilance is essential to ensuring patient safety by enabling timely identification of adverse reactions in increasingly complex and voluminous data. Routine quantitative signal detection methods generate statistical alerts for product-event pairs based on predefined criteria; however, most alerts do not warrant further investigation, creating inefficiencies and significant time demands for pharmacovigilance teams. Manual triage of these alerts is often resource-intensive, prone to variability, and challenging to audit, highlighting the need for more reliable, transparent and efficient triage strategies. This study aimed to design, develop and prospectively evaluate an explainable Machine Learning for Intelligent Triage (MLIT) tool to assist pharmacovigilance teams in reviewing statistical alerts for vaccine and drug portfolios. The objective was to enhance signal detection performance without increasing the risk of missing signals, improving operational efficiency and maintaining decision traceability and regulatory compliance. METHODS Alert and individual case safety report data were retrieved from the company's safety and signal management databases. Feature selection was guided by prior experience with a published case completeness tool, called Clinical Utility Score for Prioritisation (CUSP), and expert input. Of several ML methods explored, eXtreme Gradient Boosting (XGBoost) emerged as the optimal algorithm, with models trained and tested using a 75/25 split dataset. Iterative model refinement was conducted using Shapley Additive Explanations analyses to ensure explainability and alignment with safety reviewers' decision-making processes. Refined models underwent prospective validation in two four-month prospective validation studies, covering over 20 products across vaccine and drug portfolios. The prospective validations assessed concordance between model predictions and reviewers' decision under real-world conditions, as well as estimated time savings. RESULTS The vaccine model demonstrated robust predictive performance, achieving a weighted-average F1 score of 0.81 and an accuracy of 0.79. In the prospective validation phase, 92% of vaccine alerts were closed in alignment with the model's top-ranked prediction, while 98% were closed within the top 3 predictions. The MLIT tool also identified inconsistencies and human errors in manual triage, highlighting its potential role as a quality-control mechanism. Safety reviewers reported a 24% reduction in time spent on triage activities, and explainability analyses confirmed that the model's decision-making was conceptually aligned with safety reviewers' logic. Comparable results were observed for the drug portfolio. CONCLUSION This study highlights the potential of ML-based tools to improve pharmacovigilance by enhancing signal detection performance, reducing the likelihood of missed signals, while increasing operational efficiency, and strengthening reproducibility and transparency. While MLIT demonstrated high concordance with expert decisions and provided meaningful time savings, human oversight remains essential, especially for low-confidence predictions. Ongoing refinement and user engagement will be critical for broader implementation and further automation, marking a significant step forward in ensuring safer and more efficient drug safety surveillance.

Possibility of using artificial intelligence models in routine pharmacovigilance processes

A critical analysis of the potential of NLP systems to optimize routine PV tasks, taking into account data protection requirements is provided, and AI can become a robust tool for increasing the efficiency of PV processes.

Using Artificial Intelligence to Identify Patterns and Predictors of Adverse Drug Reactions in Cardiovascular Patients: A Comprehensive Narrative Review

Adverse Drug Event Prediction in Pharmacovigilance Using KG-Augmented LLM

Adverse drug events (ADEs), referring to harmful and unintended reactions from routine medication use, continue to pose a significant challenge for pharmacovigilance, one that can be addressed through AI-enabled Web services. In the United States, more than two million serious ADEs have been reported among hospitalized patients. These instances can be reduced if hospitals and health centers use systems to identify, anticipate, or estimate the likelihood of ADE occurrences documented on clinical notes. While computational methods leveraging natural language processing (NLP) have been developed for ADE detection in clinical texts, most of them rely on classical machine learning or deep learning models that often fail to incorporate domain-specific biomedical knowledge. We propose a knowledge graph-augmented large language model (LLM) framework for ADE prediction. Our approach uses zero shot prompting and instruction-based prompting for finetuning, while integrating structured knowledge from a Drug Adverse Event Knowledge Graph (KG) constructed with the Ontology of Adverse Events (OAE), RxNorm, and the Cadec ADE dataset. Experiments on ADE prediction indicate that KG-enhanced LLMs outperform standard LLM-based approaches, achieving up to an 8% improvement in F1 score with Mistral 7B and a 16% boost with GPT-4.1 on instruction-tuned ADE data, as well as a 1% and 2% F1-score increase, respectively, on instruction-tuned TAC data. These results suggest the effectiveness of combining symbolic biomedical knowledge with LLMs for advancing ADE prediction and improving drug safety in clinical settings.