Skip to Content

Pharmacovigilance, Live on Day One: The Clock Inside Every Case

Pharmacovigilance · Regulated AI · Latin America
November 5, 2026 by
Hugo Acurio
Live in Ecuador since November 4, 2026Iris Mexico nextAI layer: next, behind human gates

The short answer

I'm Hugo Acurio, and I designed and built Iris Global Ecuador's pharmacovigilance system for ARCSA's new standard, in full force since November 4, 2026. It's a regional platform under Iris LLC. Ecuador went live first, and Iris Mexico is next.

It runs on the ERP the company already uses. A report comes in through any of four channels, becomes a ticket the moment it lands, and turns into a regulated case with its own ID and its own regulatory clock. Seven stages carry it to the regulator, two human signatures gate the release, and seven automated escalations keep anything from sitting. The screens in the video and further down are the real system, with test data and names blurred.

4
ways in, from the web form to a field rep
47
intake questions in three branches
7
stages, Received to Closed
2
human signatures before anything reaches ARCSA
7
automated escalations
15 / 30
days on the clock: serious / non-serious

Watch the 2-minute version

The design came first. I wrote it up in October, before go-live, and that piece is here →

The board I saw

ARCSA published its substitute pharmacovigilance standard in February 2026. It names a responsible pharmacovigilance officer who must sign every submission, specifies the causality algorithms allowed, requires duplicate detection as a system function, and moves reporting onto WHO's e-Reporting platform. Ecuador isn't moving alone.

CountryThe ruleWhat it asks for
EcuadorARCSA, Resolución ARCSA-DE-2025-052-DASP. In full force since November 4, 2026.A named pharmacovigilance officer signs every submission. Duplicate detection as a system function. Reporting through WHO's e-Reporting.
BrazilANVISA, RDC 967/2025. In force since March 2026.VigiMed, E2B(R3), MedDRA and WHODrug, all mandatory.
MexicoCOFEPRIS82,993 notifications received in 2025. Iris Mexico is next on this platform.

The 15 and 30 day clocks (serious and non-serious cases) run from the moment any employee becomes aware of the event (a sales rep, a phone assistant, whoever reads the comment on social media), not from when a case is opened. A system that starts the clock at case creation is already late.

Most AI-in-pharmacovigilance pitches cannot survive an auditor. A language model is probabilistic, and a regulator asking how a case was coded wants a reproducible answer. Compliance is a systems problem, not a knowledge problem: I cannot audit how a model thinks any more than I can audit how a person thinks, so the audit happens outside the model, in the middleware. Every model call gets an input hash, a version, a confidence score, and a human on the transmission trigger.

The clock starts before the case does

So the system stamps day 0 when the report is received, before anyone opens a case, counts in Ecuador time, and puts the days left on every case and every kanban card. The color changes as the deadline gets close. Nobody has to remember to check.

The regulatory clock, day by day
Serious case · 15 days
Non-serious case · 30 days
1
2
3
051015202530
More than 10 days left5 to 10 days leftFewer than 5 days left
  1. 1Day 0. The report is received and the clock starts. The case has to reach triage within 6 business hours.
  2. 2Day 8. Causality still not done: the causality escalation fires.
  3. 3Day 10 and not sent to ARCSA: both managers get the alarm, every morning until someone acts.
Days since the report was received. The bars are colored by days left, the same way the case and the kanban card show it.

The deadline depends on seriousness: 15 days for a serious case, 30 for a non-serious one. That's why seriousness gets called at triage, early, by a person. Calling it late eats the clock you need most.

The path of a case

From the first message to the regulator's acknowledgment, this is what happens, and what happens on its own.

1
Four ways in
However the report arrives, it lands in the same queue with the same clock.
Public web formMonitored email inboxPhone, entered by the deskField reps, social media, WhatsApp
2
One conditional form
Data-protection (LOPDP) consent comes first. Then up to 47 questions in three branches: patient or family member, internal staff, health professional. Each reporter only sees their own branch.
3
A ticket and a cascade
The report becomes a helpdesk ticket and four things happen on their own: an acknowledgment to the reporter, a notice to the pharmacovigilance team with the timestamp and the owner, a task to finish triage within 24 hours, and a reminder at 48 hours if nothing moved.
4
The case opens at triage
Moving the ticket to triage creates the regulated case: an ID like EC-IRIS-26-0009, a worldwide unique case identifier, the seriousness call and the clock. The ticket keeps the conversation. The case is the regulated record.
5
Seven stages, two signatures, one upload
Investigation, coding and assessment, the Regulatory Manager's approval, the pharmacovigilance officer's signature, and then a person uploads to ARCSA. The acknowledgment closes the case.

Seven stages, two human gates

The kanban is the work queue. The first four stages run with the team. Stages V and VI sit behind a named person's signature.

I
Received
II
Triage
III
Investigation
IV
Coding and assessment
V
Ready to send
VI
Sent to ARCSA
VII
Closed
Gate 1 · Regulatory Manager
Approves the coding and the assessment before anything is ready to send. 24-hour SLA, checked every 4 hours.
Gate 2 · Pharmacovigilance officer
The only role that can move a case to Sent. Signs, and a person does the upload to ARCSA. 24-hour window.
Not reportable
After three contact attempts with no answer, the case closes as not reportable, with every attempt on the record.
Rejected by ARCSA
A rejection reopens the case at coding or at ready-to-send, with the regulator's error visible on the card.

The officer-only rule is enforced by the system itself, so nobody has to remember it. Closed cases can't be edited. A follow-up opens a new version of the same case under the same worldwide ID, so the original stays exactly as it was submitted.

Seven escalations, so nothing sits

The system watches the work as well as the deadline. These run on their own, on Ecuador business hours.

What it watchesWhen it firesChecked
Reporter schedulingNo call booked with the reporterDaily
Daily follow-upsThe day's follow-up isn't doneDaily
Lab resultsResults still pendingEvery 12 hours
CausalityNot done 8 days after receiptDaily
The day-10 cascadeDay 10 and not sent to ARCSA: both managers are alertedEvery morning
Manager approvalWaiting more than 24 hoursEvery 4 hours
Officer's submission windowWaiting more than 24 hoursEvery 4 hours

The day-10 cascade repeats every morning until someone acts. The third screen below is exactly that, three mornings in a row.

One record, in the regulator's format

The case follows the structure of ICH E2B(R3), the format regulators use to exchange safety reports. Each section is its own part of the case, so the XML comes out of the record instead of being retyped into a portal.

C · Case and source
Who reported, how, and when we first knew.
D · Patient
Medical history, prior drugs, cause of death if there was one.
E · Reactions
Each event, coded in MedDRA.
F · Tests
Lab results and exams, with their dates.
G · Drugs
Dosage, indication, WHODrug code, and causality for each drug and reaction pair.
N · Transmission
The E2B(R3) message, the upload and the regulator's answer.

Every kanban card shows how many required fields are complete, so the team sees 22 of 22, ready to send, before anyone has to ask. The XML is generated from the case and checked against the schema before the upload. The MedDRA version used is stored with the case, so a disputed code can be reproduced exactly as it was sent.

Every change to a section of the case leaves a note with who and when. The audit trail, the compliance evidence pack, the inspection response and data-subject requests all come from that one record, viewed differently. Today the record is the ERP's own tracking log. The next version chains each entry to the one before it, so any edit would show.

What is running today

The case-handling spine runs on the production instance, built to the workflow our pharmacovigilance lead designed. Her rule was simple and non-negotiable: the regulatory clock does not stop. The days remaining render on every case and every kanban card, including while the team waits on a reporter or a lab result.

Role-gated access covers four groups (analyst, pharmacovigilance officer, regulatory manager, general manager), with case data visible only to them and no administrator back door. Reporter data is protected: consent captured at intake, phone reports typed straight into the ticket with no recordings kept, and a published privacy section built for the standard's data-protection article.

It went live on November 4, 2026, after end-to-end testing on the production instance with test records, with MedDRA and WHODrug licensed and the ARCSA upload path settled. The screens below come from that testing, names blurred.

Pharmacovigilance case queue in the ERP, one column per stage, each card showing the days left on its regulatory clock (test data, names blurred)
The case queue. Every card carries its own clock and its form count.
A pharmacovigilance case record showing day 0, the regulatory deadline and the days left, in Ecuador time (test data, names blurred)
One case, one clock: day 0, the regulatory deadline and the days left, in Ecuador time.
Automated day-10 escalation posted on a case that has not been sent to ARCSA, with the deadline and the days left (test data)
Day 10 and still not sent to ARCSA. The escalation posts every morning until someone acts.

The next layer: AI with a narrow job

The AI sits on top of the native automation instead of replacing it, and it comes after go-live. Each piece takes follow-up work that lands on the analyst today and closes it in the background, ranked by how much human time it gives back.

STAGE II
Scheduling over WhatsApp
When a case needs the reporter, an agent offers three or four open slots from the team calendar, reads the reply, books the call and logs it on the case. It's designed to save 15 to 30 minutes per case, on the WhatsApp integration already running in the group.
STAGE II
Seriousness pre-classification
A model reads the event description when the case is created and proposes serious or non-serious with a confidence level. A person confirms at triage, so the right clock starts hours earlier.
STAGE IV
MedDRA and WHODrug suggestions
Spanish free text in, ranked MedDRA lowest-level terms and WHODrug entries out, aimed at the biggest time sink in manual work. The person verifies and decides. The system keeps the model, the prompt and the decision for audit.
STAGE III
Recontact before auto-close
Before a case closes after three unanswered attempts, an agent tries other channels (WhatsApp, SMS, a second email), so fewer reachable cases get written off as not reportable.
The model may
  • Prepare: schedule, draft, gather
  • Suggest, with a confidence score
  • Follow up across channels
  • Log every action next to the human call
The model may never
  • Decide seriousness
  • Choose the causality result
  • Sign for the officer
  • Send anything to the regulator

Seriousness, causality, the officer's signature and the upload to ARCSA stay as traceable human decisions by design. An inspector won't accept "the model decided" as an answer, so the design never asks one to.

The result

Seven stages, with two human gates before submission. Four role groups, access by role, no back door. Seven automated escalations, on Ecuador business hours. One record of every action, which is also the audit trail and the evidence pack.

I presented this architecture at Seton Hall Law's Latin America Healthcare Compliance program in Bogotá in September 2026, to compliance officers, regulatory counsel and pharma in-house teams from across the region, who read it as an immediate risk rather than a topic.

It's built to travel. A second company gets its own scoped space on the same system (setup, not a rebuild). The evidence pack is a query, so one log answers any regulator: ARCSA, ANVISA or COFEPRIS. And it covers a segment others skip: Spanish-language regulated pharma, on the same clock everywhere, with no global vendor built for it.

What this proves

Put the audit outside the model. Log every call with input hash, version, confidence and the human decision, so the model can change without the record changing.

Build the regulator's clock into the record. Start it where the law starts it, show it where people work, and escalate before the deadline instead of reporting after it.

Let the model suggest, keep a person on the trigger. Map which steps a regulator cares about and keep every one of them with a named human role.

See the board, invent the system, build it.

How the AI layer stays auditable: AI regulatory compliance for healthcare and pharma operations.

The regulatory side, country by country: AI in pharmacovigilance in Latin America.

Share this post
Tags
Archive