Arrow
use cases

Predict Adverse Drug Reactions with AI

Advanced AI to Detect Drugs and Adverse Reactions in Text from Social Media.

Problem

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).

Why it matters

  • 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.

Solution

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.

Discover more and interact with our AI!

Datasources

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.

Citations

  1. Lardon J, Abdellaoui R, Bellet F, Asfari H, Souvignet J, Texier N, Jaulent MC, Beyens MN, Burgun A, Bousquet CAdverse Drug Reaction Identification and Extraction in Social Media: A Scoping ReviewJ Med Internet Res 2015;17(7):e171doi: 10.2196/jmir.4304
  2. Nguyen, T., Larsen, M. E., O’Dea, B., Phung, D., Venkatesh, S., & Christensen, H. (2017). Estimation of the prevalence of adverse drug reactions from social media. International Journal of Medical Informatics, 102, 130-137. https://doi.org/10.1016/j.ijmedinf.2017.03.013
  3. De Rosa, M., Fenza, G., Gallo, A., Gallo, M., & Loia, V. (2021). Pharmacovigilance in the era of social media: Discovering adverse drug events cross-relating Twitter and PubMed. Future Generation Computer Systems, 114, 394-402. https://doi.org/10.1016/j.future.2020.08.020

Book a Free Consultation

Trusted by the world's top healthcare institutions