A tool by Firecrawl · uses 6 tools · Healthcare

Post-marketing safety signal triage

Use when a pharmacovigilance lead, medical affairs team or health journalist sees a possible new side effect for a marketed drug. Compares FAERS reaction reports against the current label, checks for published case reports, the EU regulatory status and ongoing trials, and returns a signal triage table with what is labelled, what is new and how strong the evidence is.

Open in ChatGPT Open in Claude

Save a copy for your team

Tools it calls

Each tool's price and track record across every agent today. Empty means the call worked and found nothing.

ToolPriceMedianSuccessEmpty

FDADrug labelsPrice5 creditsMedian–Success–Empty–
FDADrug eventsPrice5 creditsMedian–Success–Empty–
PubMed and PMCSearchPrice5 creditsMedian558 msSuccess99.2%Empty28.2%
PubMed and PMCArticlePrice5 creditsMedian291 msSuccess98.8%Empty0%
European Medicines AgencyMedicinesPrice5 creditsMedian–Success–Empty–
ClinicalTrials.govSearchPrice5 creditsMedian88 msSuccess100%Empty30.3%

Instructions

What your agent follows when it runs this tool. Paste them into any assistant connected to Firecrawl.

# Post-marketing safety signal triage

For one drug and one suspected reaction. The label read in step 1 is the baseline; everything after asks whether the reaction is already known.

## 1. What the label already says

1. Read the current labeling with @[FDA · Drug labels](alexandria:fda-gov/records/drug_labels) (query the generic name). Note boxed warnings, warnings and precautions, and adverse reactions that mention the suspected reaction or its synonyms.

## 2. What reporters are seeing

2. Query @[FDA · Drug events](alexandria:fda-gov/records/drug_events) with `patient.drug.medicinalproduct:<drug> AND patient.reaction.reactionmeddrapt:<reaction>` and page through recent reports. Record report count, seriousness, outcomes, reporter type and concomitant drugs that could confound.
3. Run the same reaction against one comparator in the class to see whether the pattern is drug-specific.

## 3. What the literature and regulators say

4. Search @[PubMed · PubMed search](alexandria:pubmed-ncbi-nlm-nih-gov/publications/search) for `<drug> AND <reaction> AND (case report OR pharmacovigilance)`, then read the top abstracts with @[PubMed · Article](alexandria:pubmed-ncbi-nlm-nih-gov/publications/article).
5. Check the EU picture with @[EMA · Medicines](alexandria:ema-europa-eu/records/medicines): authorisation status and any restriction or withdrawal.
6. List ongoing studies with @[ClinicalTrials.gov · Trial search](alexandria:clinicaltrials-gov/clinical-trials/search) (intervention the drug, status RECRUITING) that could capture the reaction prospectively.

## Write the triage

- **Signal table:** reaction, labelled or not, FAERS count and seriousness, comparator count, published cases.
- **Strength:** weak, moderate or strong, with the confounders noted.
- **Next step:** watch, request full case series, or escalate.
- FAERS counts are reports, not incidence. Say so.
- **Sources:** cite every figure to the capability and record it came from. Say what could not be found rather than guessing.

All Firecrawl tools