AI Pharmacovigilance ADR Extractor & MedDRA Coder

    1

    Extract suspect drugs and Adverse Drug Reactions (ADRs) from patient narratives, map symptoms to MedDRA Preferred Terms (PT), and run regulatory validity checks.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Pharmacovigilance ADR Extractor & MedDRA Coder

    Example session with this skill installed

    Analyze this patient post for potential ADR: "I took a 500 mg Paracetamol tablet yesterday for fever, and within 3 hours I developed itchy red rashes all over my arms and mild dizziness."

    • Read your context and instructions
    • Compiled the ai pharmacovigilance adr

    Summary

    Automated pharmacovigilance triage completed. Identified

    1 suspect drug and

    2 adverse events, mapped to standard MedDRA Preferred Terms, and verified regulatory case validity.

    ParameterExtracted / Mapped Output
    Suspect DrugParacetamol (500 mg)
    Raw Patient ComplaintItchy red rashes on arms; mild dizziness
    MedDRA Preferred Term (PT)Erythematous rash (10015150); Dizziness (10013573)
    System Organ Class (SOC)Skin and subcutaneous tissue disorders; Nervous system disorders
    Regulatory Case ValidityReport Valid? = True (Identifiable patient, reporter, drug, and event present)

    Next steps

    • Log this validated signal into the safety database (ICSR intake).
    • Follow up with the reporter for concomitant medications and event resolution status.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Overview

    Traditional post-marketing drug safety monitoring relies heavily on passive reporting, leading to massive underreporting and delays. Based on peer-reviewed research published in IJSRT (AI-Driven Social Media Listening and Automated ADR Extraction System), this AI agent skill transforms unstructured patient narratives and social media posts into structured, regulatory-ready pharmacovigilance data in seconds.

    Key Capabilities

    • Cognitive Semantic Extraction: Uses clinical Named Entity Recognition (NER) to isolate suspect drugs and toxicological events from raw, unformatted text.
    • Standardized MedDRA Coding: Automatically translates layman complaints (e.g., "severe dizziness and red skin rashes") into official MedDRA Preferred Terms (PT).
    • Automated Regulatory Triage: Checks reports against international safety compliance criteria to determine case validity (Report Valid? = True/False).
    • High-Speed Processing: Cuts manual data entry fatigue and accelerates initial safety signal triage.

    Who Should Use This?

    Pharmacovigilance (PV) associates, clinical researchers, pharmacy students, and healthcare AI builders looking to automate ADR intake and MedDRA encoding.

    Requires a human medical reviewer for final causality assessment. Does not handle ICSR XML generation (E2B R3).

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed2 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the extraction of adverse drug reactions from unstructured narratives and accurately maps layman symptoms to MedDRA Preferred Terms (PT), ensuring regulatory consistency and reducing manual coding errors.

    The skill is designed as a modular tool compatible with major LLM-based agent frameworks; once integrated into your workflow, you simply provide text inputs like clinical notes or social media posts for immediate processing.

    Yes, the extraction logic is built to handle the informal language, slang, and misspellings commonly found in patient forums while still mapping them to precise, standardized MedDRA terminology.

    You receive the specialized extraction logic, the MedDRA mapping protocol, and a structured output template; however, a MedDRA license is required for your organization to use the ontology for official regulatory submissions.

    While the skill performs the 'four-point' regulatory validity check, it is intended to assist human experts; a qualified medical professional should always perform the final causality assessment and clinical review.

    Buyers receive access to all future version updates, ensuring the skill stays aligned with evolving LLM capabilities and pharmacovigilance reporting standards.

    New in Research & Analysis