Tooluniverse Product Safety Surveillance

Product Safety Surveillance (multi-product, openFDA)

Retrieve and interpret post-market safety records across every FDA-regulated product class except drug-AE signal mining: medical devices, food / dietary supplements / cosmetics, veterinary drugs, and drug supply (shortages), plus cross-product enforcement/recall reports.

KEY PRINCIPLES 1. Decide the product class first. Device? Food/supplement/cosmetic? Vet drug? Drug shortage? Recall? The class picks the tool. 2. Build a valid Lucene query. openFDA uses field-scoped field:value terms; combine with a space-separated AND. Phrases and special characters need care (see Query Grammar). 3. Retrieve, then interpret. These are spontaneous/voluntary reports. Report the records and their fields; never assert causation or rates. 4. Cite every record with the tool name, the openFDA endpoint, the query used, and the total hit count from meta.results.total. 5. Stay in scope. If the request is drug-AE signal detection (PRR/ROR/IC), STOP and point to tooluniverse-pharmacovigilance / tooluniverse-adverse-event-detection.

---

When to Use vs When NOT to Use

USE for:

• Device adverse events (MAUDE): "adverse events / malfunctions / deaths for [device]"
• Device recalls & enforcement: "device recalls for [firm]", "Class I device recalls"
• Device clearance context: "510(k) clearances for [device type]"
• Food / dietary-supplement / cosmetic adverse events (CAERS): "supplement reactions", "cosmetic adverse events for [brand]"
• Food recalls/enforcement: "food recall for listeria / undeclared allergen"
• Veterinary drug adverse events: "adverse events for [drug] in dogs"
• Drug shortages: "is [drug] in shortage", "injectables on current shortage"
• Drug recalls/enforcement: "drug recalls for contamination"

DO NOT USE for (point elsewhere):

• Drug adverse-event SIGNAL detection / disproportionality (PRR, ROR, IC) → tooluniverse-pharmacovigilance or tooluniverse-adverse-event-detection
• Drug-AE association strength scoring, demographic risk stratification of drug AEs → same two skills
• Drug efficacy, mechanism, pharmacogenomics → other tooluniverse-* skills

This skill retrieves and interprets multi-product safety records. It does not compute drug-AE signal statistics.

---

Tool Map (which tool for which question)

All tools take a Lucene search string plus optional limit and skip. All are keyless and verified live.

---

openFDA Query Grammar (CRITICAL — read before querying)

• Field-scoped term: field:value (e.g. event_type:Death, status:Current).
• Nested fields use dot paths: device.generic_name:pacemaker, products.industry_name:Cosmetics, animal.species:Dog, reaction.veddra_term_name:Vomiting, drug.active_ingredients.name:carprofen.
• Combine terms with a SPACE-separated `AND` (verified working): device.generic_name:pacemaker AND event_type:Death.
• Do NOT use `+AND+` — the +-joined boolean form errors through these tools. Use a literal space around AND.
• Multi-word values: join with + only for adjacency within a single field value (e.g. device.generic_name:infusion+pump). This is matched as tokens, not an exact phrase.
• Avoid raw special characters ((, ), /, leading +) inside values — they break the query. Pick a simpler token (e.g. products.industry_name:Dietary instead of the full Dietary Conventional Foods/Meal Replacements).
• Dates are strings: device AE/MAUDE use YYYYMMDD (e.g. date_received); recalls/enforcement use YYYY-MM-DD (e.g. event_date_initiated, recall_initiation_date).
• Result envelope: every successful call returns {status:"success", data:{meta:{results:{total, skip, limit}}, results:[...]}}. Read the hit count from data.meta.results.total.
• Counts/aggregations: native openFDA supports &count=<field>; these TU wrappers center on search. To rank terms, retrieve a batch (e.g. limit:100) and tally the field yourself in Python.

---

Interpretation Tables (raw openFDA field → meaning)

Medical devices — MAUDE adverse events (/device/event.json)

Medical devices — recalls (/device/recall.json)

Enforcement reports (device / drug / food /.../enforcement.json)

Food / supplement / cosmetic — CAERS adverse events (/food/event.json)

Veterinary — animal drug adverse events (/animalandveterinary/event.json)

Drug shortages (/drug/shortages.json)

---

Workflow

1. Classify the product from the request (device / food-supplement-cosmetic / vet / drug shortage / recall). 2. Pick the tool from the Tool Map. 3. Build the Lucene query following Query Grammar (single field for a first pass; add AND for combinations). Keep values simple; avoid special characters. 4. Run it and read data.meta.results.total and data.results[]. 5. Interpret the fields with the table above. For severity: device event_type:Death; enforcement classification:Class I; CAERS outcomes:Death/Hospitalization; shortage status:Current. 6. Summarize and cite. Report counts, key fields, the query used, and the LIMITATIONS caveat. To rank terms, pull limit:100 and tally in Python (no count aggregation in these wrappers). 7. If out of scope (drug-AE signal/PRR/ROR), stop and route to the pharmacovigilance skills.

---

Worked Examples (verified live)

Example 1 — Device deaths for a device type (MAUDE)

"Are there any reported deaths in adverse-event reports for pacemakers?"

OpenFDA_search_device_adverse_events {"search":"device.generic_name:pacemaker AND event_type:Death","limit":1}

Real output (abbrev): status:success, meta.results.total = 16619; first record event_type = Death, device.generic_name = DEFIBRILLATOR/PACEMAKER. Interpretation: 16,619 MAUDE reports match a pacemaker device with a Death event type. These are spontaneous reports — duplicates likely, and "Death" means a death was reported in temporal association, not that the device caused it.

Example 2 — Device recalls for a firm

"What device recalls has Medtronic Navigation issued?"

OpenFDA_search_device_recalls {"search":"recalling_firm:Medtronic","limit":1}

Real output (abbrev): total = 1896; first record recall_status = Terminated, product_code = HAW, root_cause_description = Labeling design, k_numbers = ["K990214"], event_date_initiated = 2011-01-20, product_description = a tactile probe for spine surgery. Interpretation: 1,896 recall records match firms containing "Medtronic". recall_status: Terminated means FDA has closed this action; the root cause was a labeling-design issue.

Example 3 — Drug shortage lookup for an injectable

"Is ketorolac injection in shortage right now?"

OpenFDA_search_drug_shortages {"search":"dosage_form:Injection AND status:Current","limit":1}

Real output (abbrev): total = 799; first record generic_name = Ketorolac Tromethamine Injection, status = Current, shortage_reason = Delay in shipping of the drug, availability = Unavailable, company_name = Fresenius Kabi USA, LLC. Interpretation: 799 current shortage records are injectables; ketorolac tromethamine injection is currently in shortage (status Current, availability Unavailable) due to a shipping delay.

Example 4 — Supplement / cosmetic CAERS reactions

"Are there CAERS adverse-event reports implicating cosmetics?"

OpenFDA_search_food_adverse_events {"search":"products.industry_name:Cosmetics","limit":1}

Real output (abbrev): total = 52214; first record products[].industry_name = Cosmetics, products[].role = SUSPECT, outcomes = ["Hospitalization","Other Serious or Important Medical Event"]. Interpretation: 52,214 CAERS reports name a cosmetic product as SUSPECT. CAERS is voluntary; a SUSPECT role reflects the reporter's attribution, not a verified causal link.

Example 5 — Veterinary adverse events for a drug in a species

"What adverse events are reported for carprofen in dogs?"

OpenFDA_search_animalvet_adverse_events {"search":"drug.active_ingredients.name:carprofen AND animal.species:Dog","limit":1}

Real output (abbrev): total = 46469; first record animal.species = Dog, reaction[].veddra_term_name includes Leucocytosis NOS, Neutrophilia, Depression, Elevated alanine aminotransferase (ALT). Interpretation: 46,469 veterinary reports match carprofen-containing products in dogs. VeDDRA terms describe reported clinical signs; counts reflect reporting, not incidence.

---

Limitations (state these in every report)

• Spontaneous / voluntary reports. MAUDE (device), CAERS (food/supplement/cosmetic), FAERS (drug), and the animal/vet system are passive surveillance. Reports are unverified and a report is not a confirmed causal event.
• No causation, no denominator. Counts (meta.results.total) are report counts, not incidence or rates. There is no exposure denominator, so you cannot compute risk.
• Reporting bias. Serious events, new products, recalls, and media/regulatory attention drive reporting spikes (Weber effect). High counts may reflect usage volume or attention, not hazard.
• Duplicate reports. MAUDE in particular contains follow-up/duplicate reports of the same event; do not treat report counts as event counts.
• CAERS voluntary & sparse. Consumer/age/gender fields are often missing; SUSPECT role is reporter attribution.
• This skill does not compute signal statistics (PRR/ROR/IC). For drug-AE disproportionality use tooluniverse-pharmacovigilance / tooluniverse-adverse-event-detection.
• Data currency: each response carries a meta.last_updated date; openFDA lags real-world events.

See references/openfda_fields.md for the full per-endpoint field reference and additional query examples.

---

References

• openFDA: https://open.fda.gov
• MAUDE (device adverse events): https://www.fda.gov/medical-devices/mandatory-reporting-requirements-manufacturers-importers-and-device-user-facilities
• Device recalls / 510(k): https://www.fda.gov/medical-devices
• CAERS (food/supplement/cosmetic): https://www.fda.gov/food/compliance-enforcement/cfsan-adverse-event-reporting-system-caers
• Drug shortages: https://www.fda.gov/drugs/drug-shortages
• Recall classifications: https://www.fda.gov/safety/industry-guidance-recalls

openFDA Field Reference — Product Safety Surveillance

Per-endpoint searchable fields and verified query patterns. All tools take search (Lucene string), optional limit, optional skip. Combine terms with a literal space-separated AND (NOT +AND+). Read the hit count from data.meta.results.total.

---

Device adverse events — OpenFDA_search_device_adverse_events (/device/event.json)

Key searchable fields:

• event_type — Death, Injury, Malfunction, No answer provided
• device.generic_name, device.brand_name, device.manufacturer_d_name
• device.openfda.device_class (1/2/3), product_problem_flag
• date_received (YYYYMMDD), date_of_event (YYYYMMDD)
• report_number, report_to_fda, mdr_text.text_type_code

Example queries (verified):

• event_type:Death → total 226190
• device.generic_name:infusion+pump → first record event_type: Malfunction
• device.generic_name:pacemaker AND event_type:Death → total 16619

Caveat: duplicate / follow-up reports of the same event are common; report count ≠ event count.

---

Device recalls — OpenFDA_search_device_recalls (/device/recall.json)

Key fields:

• product_description, recalling_firm, recall_status (Open/Terminated)
• product_code, k_numbers, root_cause_description
• event_date_initiated (YYYY-MM-DD)

Example (verified): recalling_firm:Medtronic → total 1896; first record recall_status: Terminated, product_code: HAW, k_numbers: ["K990214"], root_cause_description: Labeling design.

---

Device 510(k) — OpenFDA_search_device_510k (/device/510k.json)

Key fields: device_name, applicant, k_number, decision_description, product_code, clearance_type, decision_date.

Example (verified): device_name:pacemaker → total 185; first record decision_description: Substantially Equivalent, k_number: K780776.

---

Device / Drug / Food enforcement — OpenFDA_search_device_enforcement, OpenFDA_search_drug_enforcement, OpenFDA_search_food_enforcement (/.../enforcement.json)

Shared fields:

• classification (Class I / Class II / Class III)
• status (Ongoing / Terminated / Completed)
• reason_for_recall, product_description, recalling_firm
• recall_initiation_date (YYYY-MM-DD), state, country, voluntary_mandated

Examples (verified):

• device: recalling_firm:Medtronic → total 1248; first classification: Class II, status: Ongoing
• food: reason_for_recall:listeria → total 7467; first classification: Class I, status: Terminated
• drug: reason_for_recall:contamination → total 2057; first classification: Class II, status: Ongoing

---

Food / supplement / cosmetic CAERS — OpenFDA_search_food_adverse_events (/food/event.json)

Key fields:

• reactions (MedDRA, British spelling: Nausea, Diarrhoea, Hypersensitivity)
• outcomes (Hospitalization, Life Threatening, Disability, Death, Visited an ER, Other Serious or Important Medical Event)
• products.industry_name (Cosmetics, Dietary Conventional Foods/Meal Replacements, Milk/Butter/Dried Milk Prod, …)
• products.role (SUSPECT / CONCOMITANT), products.name_brand, products.industry_code
• consumer.age, consumer.gender

Examples (verified):

• reactions:NAUSEA → total 16015
• products.industry_name:Cosmetics → total 52214; products.role: SUSPECT
• products.industry_name:Dietary → total 2189; industry_name: Dietary Conventional Foods/Meal Replacements
• outcomes:Hospitalization → total 23433

Caveat: avoid special chars (/, (, )) in values — use a single simple token like Dietary rather than the full industry-name string.

---

Veterinary adverse events — OpenFDA_search_animalvet_adverse_events (/animalandveterinary/event.json)

Key fields:

• animal.species (Dog, Cat, Horse, …), animal.gender, animal.breed.breed_component
• number_of_animals_affected, number_of_animals_treated
• reaction.veddra_term_name (VeDDRA clinical signs: Vomiting, Diarrhoea, …)
• drug.brand_name, drug.active_ingredients.name, drug.route
• drug.used_according_to_label, drug.off_label_use

Examples (verified):

• animal.species:Dog → total 974175
• drug.active_ingredients.name:carprofen → success
• drug.active_ingredients.name:carprofen AND animal.species:Dog → total 46469; VeDDRA terms Leucocytosis NOS, Neutrophilia, Depression, Elevated alanine aminotransferase (ALT)

---

Drug shortages — OpenFDA_search_drug_shortages (/drug/shortages.json)

Key fields:

• status (Current / Resolved), availability (Unavailable, Limited)
• generic_name, shortage_reason, dosage_form, presentation
• therapeutic_category, company_name, package_ndc
• update_type, initial_posting_date, update_date, related_info

Examples (verified):

• status:Current → total 1146
• dosage_form:Injection AND status:Current → total 799; first generic_name: Ketorolac Tromethamine Injection, status: Current, availability: Unavailable, shortage_reason: Delay in shipping of the drug

---

Drug events / labels (raw, no signal stats) — OpenFDA_search_drug_events (/drug/event.json), OpenFDA_search_drug_labels (/drug/label.json)

For raw FAERS record / label retrieval only. For drug-AE disproportionality (PRR/ROR/IC) use tooluniverse-pharmacovigilance / tooluniverse-adverse-event-detection.

• events: patient.drug.medicinalproduct:metformin → total 425796
• labels: openfda.generic_name:metformin → total 380