Adverse Drug Effects Detection

Ensuring drug safety in the healthcare industry is increasingly challenging, as roughly 80% of global data is unstructured, encompassing patient reviews, social media, and extensive medical texts (1). The difficulty lies in effectively identifying instances of medication usage and potential adverse reactions from such varied and unstructured sources. This hurdle is critical to address, considering that efficient detection and documentation of adverse drug reactions are pivotal for maintaining patient safety—a concern underscored by the millions of hospitalizations that occur annually due to medication-related issues (2)(3).

• Ensuring drug safety is challenging due to 80% of global data being unstructured, including patient reviews, social media, and medical texts.
• Identifying medication usage and potential adverse reactions from diverse sources is difficult but crucial for patient safety.
• Efficient detection of adverse drug reactions is essential, as medication-related issues lead to millions of hospitalizations annually.

To address this challenge, “MediNER AI” has been created, a system that applies named entity recognition (NER) technology for the automatic identification and categorization of medications and their adverse effects in texts, thereby improving accuracy and effectiveness. in drug safety surveillance.

User person: Pharmacovigilance Officers, Clinical Pharmacists, Regulatory Affairs Specialists, Risk Management Professionals.

MediNER AI is trained on patterns and information from research publications. These include studies on identifying adverse drug reactions on social media (1), estimating the prevalence of these reactions (2), and methods of cross-referencing Twitter discussions with medical literature (3). These studies provide the system with the ability to accurately identify and categorize relevant medical entities, helping healthcare professionals recognize potential drug safety issues.