Home / Tools / Drugs and formularies

Drugs and formulariesL2 · v1.0.0 · read-only

ira_drug_label_risk_screen

Ira Drug Label Risk Screen

What it answers

Given an optional drug_name (brand or generic substring), returns IRA-Selected Drugs with their CURRENT FDA structured-label posture (boxed warning / REMS / pregnancy / pediatric flags) and most-recent Drugs@FDA approval activity. When drug_name is omitted, screens ALL drugs in fact_drug_reimbursement.

The wedge: drugs with active boxed warning + REMS carry FDA-acknowledged safety signals that weaken the manufacturer's MFP-defense argument during CMS negotiation. Hedge funds track this for negotiated-rate directional signal; pharma market access uses it to brief the negotiation team; plaintiff bar uses it to weight cross-substrate exposure.

Substrate joins: fact_drug_reimbursement (IRA list) × dim_drug_label (shipped 2026-05-16, SPL summary) × dim_drug_application (shipped 2026-05-16, Drugs@FDA approval history).

Reference demo (MEASURED 2026-08-01): ELIQUIS -> 22 current label revisions, boxed warning YES, REMS no, pregnancy warning YES, risk_signal_count 2. Across the whole IRA cohort: 25 drugs screened, 14 carry a boxed warning, 0 carry a REMS.

KNOWN GAPS: ira_drug_name_to_label_fuzzy_match (drug_name match is case-insensitive substring on brand_name OR generic_name — no robust ingredient resolver yet). manufacturer_to_sponsor_fuzzy_match (IRA manufacturer field matched against dim_drug_application.sponsor_name via substring — same name can appear in multiple corporate forms).

Inputs

acknowledge_era_break
boolean · optional
default: false
drug_name
string · optional
require_signal
boolean · optional
default: false
top_n
integer · optional
default: 25

Call it

From an agent: connect the Vlada MCP once (one click for Claude, ChatGPT, Cursor, VS Code) and ask in plain English; the agent selects ira_drug_label_risk_screen when the question fits. From code: the same tool over REST with an API key. The schema endpoint needs no key.

curl -X POST https://api.vladahealth.com/v1/tools/ira_drug_label_risk_screen \
  -H "Authorization: Bearer $VLADA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
curl https://api.vladahealth.com/v1/tools/ira_drug_label_risk_screen/schema      # the JSON schema, no auth
# MCP endpoint (Streamable HTTP): https://mcp.vladahealth.com/mcp

What comes back

Typed rows plus provenance on every answer: the public source file, its vintage, the methodology, and a response_hash you can replay. Prove and replay tools turn any number into a re-runnable receipt. A number the data cannot support comes back as “not in the data”, never as zero.

Sources behind it

  • drug_silver.fact_drug_reimbursement#ira_mfp
  • drug_silver.dim_drug_label
  • drug_silver.dim_drug_application

tables: drug_silver.fact_drug_reimbursement · drug_silver.dim_drug_label · drug_silver.dim_drug_application

Known limits

  • ira_drug_name_to_label_fuzzy_match
  • manufacturer_to_sponsor_fuzzy_match

As of the 2026-09-19 build of the served surface · machine-readable catalog · the live server may run a different version; the schema endpoint above is authoritative for what is deployed.