How Barie Researches Adverse Event Reports for a Specific Drug Across FDA FAERS and Published Case Studies

Pharmacovigilance  ·  Deep Research  ·  FDA FAERS · PubMed · EMA  ·  Updated April 2026

Barie searches live regulatory databases and medical literature simultaneously. It compiles adverse event types, frequency, severity, and patient demographics into a structured safety report — with a direct source link to every FAERS report, published case study, and regulatory signal cited. Not a training-data summary of historical safety data.

Why adverse event data from training memory is unusable

A pharmacovigilance analyst asked an AI assistant to summarise adverse event reports for a second-generation GLP-1 agonist. The output covered the expected categories: gastrointestinal events, injection-site reactions, and the small number of serious cardiac signals from early clinical trial data. The summary was coherent and well-structured. It also completely missed the FDA’s October 2023 update to the prescribing information for semaglutide that added a new gastrointestinal obstruction warning following post-market FAERS signal analysis, and a 2024 case series published in the New England Journal of Medicine describing aspiration events in patients undergoing elective procedures while on GLP-1 receptor agonists.

Both of those updates were material to the safety assessment she was conducting. Neither was in the training data. The AI had not lied or hallucinated. It had simply described the safety profile as it was known at the time its training data was collected, without any indication that the picture had changed significantly since then.

Adverse event databases are updated continuously. FDA FAERS receives hundreds of thousands of new reports each quarter. EMA EudraVigilance is updated on a rolling basis. Published case studies appear in PubMed daily. A safety analysis built on training data is a snapshot of an earlier version of the evidence, and in pharmacovigilance, that distinction has regulatory and patient safety consequences.

Barie queries FAERS and PubMed at the moment you submit the prompt: FDA FAERS data is retrieved live from the OpenFDA API, which is updated quarterly with the latest submitted reports. PubMed case study retrieval reflects publications indexed up to the query date. The safety profile in Barie’s output describes what is known about the drug today, not what was known when any model was last trained.

Your prompt

Task prompt: “Research adverse event reports for a specific drug across FDA’s FAERS database and published case studies.”

One sentence. Barie fires parallel retrieval threads across FDA FAERS, EMA EudraVigilance, PubMed, and the WHO VigiBase, applies severity classification, extracts patient demographic patterns, identifies any disproportionality signals, and delivers a structured report with every source linked. Here is the complete workflow.

Step 1: Four databases queried simultaneously — regulatory reports and medical literature together

LIVE DATABASE RETRIEVAL

Barie Deep Research fires four parallel threads at the moment the prompt is submitted. The regulatory thread queries the FDA FAERS OpenFDA API and EMA EudraVigilance for all submitted adverse event reports for the specified drug. The literature thread queries PubMed for published case reports, case series, and observational studies describing adverse events. The WHO VigiBase query adds global spontaneous reporting data beyond the US and European markets. All four threads run simultaneously so the complete dataset is assembled before any analysis begins.

Barie Deep Research — Adverse Event Database Search — Live Query (4 sources, parallel)

• FDA FAERS (4,218 reports) — OpenFDA API · Drug: [drug name] · Event type: all · Date: all submissions to current quarter · Fields: event type, outcome, age, sex, weight, concomitant drugs, reporter type
• EudraVigilance (1,847 records) — EMA adverse reaction database · Substance name query · All EEA and non-EEA reports · Seriousness filter: serious and non-serious · MedDRA PT coding applied
• PubMed (312 publications) — Drug name AND (adverse event OR adverse reaction OR case report OR case series) · Publication type: Case Reports, Observational Study · Date: last 5 years
• WHO VigiBase (9,640 ICSRs) — Global spontaneous reporting · Substance query · Individual Case Safety Reports · Disproportionality analysis — Information Component score applied

Web Research checks for recent label changes and regulatory communications: After the primary database retrieval, Barie Web Research checks the FDA drug label current version on DailyMed, any recent FDA safety communications or REMS updates, and EMA product information updates. This catches label changes that reflect new safety findings identified through FAERS signal analysis — exactly the kind of update that would not appear in any training-data response.

Step 2: Adverse events classified by type, severity, frequency, and patient demographics

STRUCTURED SAFETY ANALYSIS

4,218 FAERS reports  ·  34 Event categories  ·  6 Disproportionality signals  ·  100% Source-linked

The combined dataset from all four sources is classified using MedDRA System Organ Class groupings. Events are ranked by report frequency, severity outcome (death, hospitalisation, life-threatening, disability, other serious, non-serious), and patient demographic patterns. Disproportionality analysis using the Reporting Odds Ratio and Information Component methodology identifies event types reported more frequently for this drug than for the overall FAERS database population — which is how novel safety signals are detected before they reach the level of a regulatory label change.

Serious · SOC: Gastrointestinal — 1,240 reports

Gastrointestinal obstruction and gastroparesis

The highest-volume serious event category across FAERS and EudraVigilance. Reports describe delayed gastric emptying progressing to obstruction requiring hospitalisation in a subset of patients. Disproportionality signal confirmed — ROR 3.8 (95% CI 3.2–4.6). FDA label updated October 2023 to include a gastroparesis warning. 18 published case reports in PubMed describe peri-operative aspiration risk in patients with delayed gastric emptying on this drug class.

Median age: 58  ·  Female: 67%  ·  Hospitalisation: 44%

Serious · SOC: Hepatobiliary — 287 reports

Acute pancreatitis and cholelithiasis

Pancreatitis and gallstone formation are established class-level adverse events for GLP-1 receptor agonists with consistent signals across FAERS, EudraVigilance, and VigiBase. The FAERS signal for this drug is consistent with the class profile. Six published case series in PubMed describe acute pancreatitis onset typically within the first 12 weeks of treatment initiation. No new disproportionality signal beyond the known class effect was detected in the current retrieval.

Onset: 0–12 weeks  ·  Class-level event  ·  Hospitalisation: 71%

Emerging signal · SOC: Psychiatric — 198 reports

Suicidal ideation and self-injurious behaviour

An emerging signal that generated an EMA review in 2023 and an FDA safety evaluation completed in early 2024. The FDA concluded that the current data does not establish a causal relationship. The EMA reached a similar conclusion but added a label statement recommending monitoring. Barie’s current retrieval shows 198 FAERS reports and 12 VigiBase ICSRs. The signal remains under active post-market monitoring. Three PubMed publications describe potential neurobiological mechanisms being investigated.

Active monitoring  ·  FDA: no causality established  ·  EMA: monitoring label added

Non-serious · SOC: Skin and subcutaneous — 441 reports

Injection site reactions and alopecia

The most frequently reported non-serious events. Injection site reactions are expected and consistent with the route of administration. Alopecia is a more recently characterised adverse event for this drug class, generating increasing report volume in FAERS from 2022 onwards. No serious outcomes associated with alopecia reports. Patient demographics for alopecia reports show a female predominance of 82% and association with rapid weight loss rather than direct drug effect in most published commentary.

Non-serious outcome  ·  Alopecia: 82% female  ·  Onset: 8–16 weeks

Step 3: The structured safety report — every data point linked to its source

STRUCTURED SAFETY REPORT

Adverse Event Safety Report — Barie Deep Research Output

• Total reports — 4,218 FAERS reports · 1,847 EudraVigilance records · 9,640 WHO VigiBase ICSRs · 312 PubMed publications screened · 47 included case reports and series
• Most reported event — Nausea (2,180 reports, 51.7% of FAERS total) — consistent with class-level GI profile and known from clinical trial data. No new disproportionality signal versus the class comparator.
• Serious events with signal — 6 event categories with confirmed disproportionality: gastroparesis, cholelithiasis, pancreatitis, hypoglycaemia in combination therapy, injection site necrosis, and renal impairment. All 6 have corresponding PubMed case literature.
• Patient demographics — Median reporter age: 56 years. Female: 63%. Serious outcome reports skew older (median 62). Concomitant diabetes medication present in 41% of serious event reports — relevant for hypoglycaemia risk assessment.
• Label changes detected — 2 label updates detected via Web Research layer: October 2023 gastroparesis warning addition and March 2024 aspiration risk note for peri-operative patients. Both updates postdate common training dataset cutoffs.
• Active regulatory review — 1 signal under active monitoring: suicidal ideation and self-injurious behaviour. FDA safety communication January 2024 concluded no causal relationship established. EMA label monitoring statement added June 2023.

The two label changes would be absent from any training-data response: The October 2023 gastroparesis warning and the March 2024 peri-operative aspiration note were added to the prescribing information after most AI training datasets were collected. A pharmacovigilance analyst relying on a training-data answer would have an incomplete safety picture and would need to verify separately. Barie’s Web Research layer retrieves the current DailyMed label version and flags any updates detected against the base retrieved data.

Step 4: Report delivered to your pharmacovigilance and medical affairs tools

EXPORT

The structured safety report and the full citation database export to the tools your medical affairs, regulatory affairs, or pharmacovigilance team uses. Notion receives the complete report as a linked database with every source entry connecting to its primary FAERS record, PubMed PMID, or regulatory communication page. A Word document version is available for inclusion in a PSUR, DSUR, or regulatory submission package. The six disproportionality signal summaries go to Slack for team awareness before the next safety review meeting.

Export flow: Notion → Word (.docx) → Google Docs → Slack

Quarterly re-runs align with the FAERS update cycle: FDA FAERS is updated quarterly. Configure Barie to re-run the same adverse event query each quarter and push new signal findings to Notion automatically. When a new event category crosses a disproportionality threshold or a new label change is detected via the Web Research layer, the team receives an alert before the next scheduled signal review. Continuous safety monitoring rather than point-in-time research.

What you get

A structured adverse event safety report covering 4,218 FAERS reports, 1,847 EudraVigilance records, 9,640 WHO VigiBase ICSRs, and 47 included PubMed case reports and series. Adverse events classified by MedDRA System Organ Class, ranked by frequency, severity, and disproportionality signal strength. Patient demographic analysis across age, sex, and concomitant medication patterns. Two label changes detected via the Web Research layer that would not appear in any training-data response. The complete report exported to Notion, Word, Google Docs, and Slack in one session. Configured for quarterly re-runs aligned to the FAERS update cycle.

The Verdict

FDA FAERS receives over two million new reports per year. The most consequential safety findings for any drug are often the most recent ones — the signals that have just crossed a threshold, the label changes that were issued last quarter, the case series that was published in the last three months. A pharmacovigilance review built from training data describes the safety profile as it was understood at an unknown historical point. It cannot tell you about the October 2023 gastroparesis warning. It cannot tell you about the active suicidal ideation signal review. It cannot tell you what the current label says. Barie queries the live databases at the moment the prompt is submitted. That is not a convenience. That is the standard the task requires.

Barie features used in this task

Next steps

→ Barie Deep Research — live regulatory and medical database retrieval

→ Prompt Library — pharmacovigilance and adverse event research templates

→ Wall of Love — what medical affairs and regulatory teams are building with Barie