Back to Products & Projects
AI ProductsComplianceContent Strategy

Drug Safety Classification System (RAG Pipeline)

  • Identified critical accuracy gaps in Tata 1mg's drug safety classification system.
  • Led the design of a retrieval-augmented generation (RAG) pipeline to automate validation and classification of drug safety advisories.
  • The system validates clinical content and regulatory classifications across safety categories like pregnancy, breastfeeding, driving, and organ impairment.

The Challenge

  • Manual classification against official drug labels was producing 48% safety advice accuracy, meaning over half of the drugs had incorrect or incomplete safety details visible.
  • In a clinical context, an incorrect pregnancy or breastfeeding classification is a patient safety risk, not merely a content quality issue.
  • Diagnostics over-claims and incorrect assertions were creating regulatory and brand risk.

The Approach

  • Scoped and co-designed a RAG pipeline that retrieves the relevant section from the official drug label (SmPC), compares it against Tata 1mg's internal classification, and maps the correct advisory.
  • Defined the evaluation rubric and accuracy benchmarking framework for the pipeline's output validation.
  • Collaborated with engineering and medical affairs to establish the confidence threshold for automated vs human-reviewed classifications.

Results

Safety advice accuracy improved from 48% to 85% post-pipeline deployment.
Reduced diagnostics over-claims by 30% across the eDiagnostics platform.
Automated validation across six safety advisory categories (pregnancy, breastfeeding, hepatic impairment, renal impairment, driving, and alcohol risk).

Tech Stack

RAG (Retrieval-Augmented Generation)PythonLLMChatGPTCMSConfluence

Have a similar project?

Let's discuss how we can help bring your vision to life.

Start a Conversation