tooluniverse-adverse-event-detection

Provide the generic drug name and the skill resolves it to a ChEMBL ID, queries FAERS for top adverse events, then calculates PRR, ROR, and IC with 95% confidence intervals for each event. A signal is detected when PRR is at least 2.0, the lower confidence interval exceeds 1.0, and case count is at least 3.

Disproportionality analysis compares the reporting rate of a specific adverse event for a drug against all other drugs in FAERS using metrics like PRR, ROR, and IC. PRR of 5.0 or higher indicates a strong signal requiring investigation, while 2.0-2.9 indicates a weak signal.

Yes, the FAERS_compare_drugs tool calculates PRR, ROR, and IC side-by-side for two drugs on a specific adverse event such as haemorrhage. You can also aggregate adverse reactions across an entire drug class to distinguish drug-specific from class-wide signals.

For drugs with no FAERS reports, the workflow skips FAERS phases and relies on FDA label data, mechanism-based predictions, and literature evidence. A NOT_FOUND error from FDA label tools is normal and simply means that section, such as a boxed warning, does not exist.

The score sums four components: FAERS signal strength (0-35 points), serious adverse events like deaths (0-30 points), FDA label warnings such as boxed warnings (0-25 points), and literature evidence (0-10 points). Scores of 75-100 indicate high concern requiring regulatory attention.

Use generic drug names in uppercase for FAERS queries, such as ATORVASTATIN, and MedDRA preferred terms for specific events, such as Rhabdomyolysis rather than informal descriptions. The skill resolves names to ChEMBL and DrugBank identifiers automatically.