use cases

Adverse Drug Effects Detection

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


Monitoring drug safety is challenging due to the vast amount of unstructured data across reviews, tweets, and medical texts. There is a critical need for precise identification and labeling of drugs and their adverse reactions.

Why it matters

- Monitoring drug safety is crucial but complex due to the plethora of unstructured data from social media, user reviews, and medical texts. Precise detection and timely reporting of adverse drug effects are essential for reducing patient harm and improving clinical outcomes. Rapid identification aids in the swift adjustment of treatment protocols, ensuring that patients receive the safest and most effective care possible.

- Efficiently processing and analyzing vast, unstructured datasets to identify adverse drug reactions can greatly enhance drug safety monitoring. This leads to more accurate drug labeling and usage guidelines, which help healthcare providers make better prescribing decisions. Improved information accuracy supports regulatory bodies in updating safety standards that protect public health.

- By enhancing the detection of adverse drug reactions, we can improve public health surveillance systems and inform policy decisions. This is critical for developing preventive strategies and educational campaigns that raise awareness about potential drug risks. Better data analysis and reporting can also influence the allocation of resources to the most pressing healthcare needs, optimizing public health responses and safety measures.


MediNER AI addresses this issue by deploying advanced Name Entity Recognition (NER) technology to accurately detect and label drugs and adverse reactions from diverse textual sources, enhancing drug safety monitoring.

Discover more and interact with our AI!


  • Text Sources: Input textual data such as drug reviews, tweets, and medical documentation.
  • Format Requirements: Text must be in a readable format (e.g., plain text).
  • Contextual Information: Providing additional context or specifying the source type can enhance the accuracy of entity recognition.
  • User Preferences: Optional settings for sensitivity (how aggressively the AI searches for entities) and output format (such as JSON or plain text).
  • Language Specification: Indicate the language of the text if the AI supports multiple languages.


  • 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
  • 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.
  • 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.

Book a Free Consultation

Trusted by the world's top healthcare institutions

Button Text