From referral to a confirmed appointment

A referral to a public hospital clinic, step by step. The systems by layer, the work today, the same work with one agent, and who runs it.

A GP sends a referral to a hospital clinic. It arrives by fax, secure message or e-referral form. The result should be a confirmed appointment, or a clear decline back to the GP. Today a referral clerk in the central referral hub carries the work. A clinician triages each referral. With an agent, the clerk's typing and chasing move to the agent. The clinician still triages, and the clerk still decides any doubt about who the patient is.

The systems involved

The referral touches these layers. The healthcare page shows the full hospital estate.

Layer	Systems in this use case
Infrastructure and compute (R01)	Hosting for the agent in an Australian or New Zealand region. A text recognition (OCR) service.
Data platform (R02)	Clinical data repository for recent results. Data warehouse for waiting list reports.
Integration fabric (R03)	Integration engine for inbound messages and the fax route. FHIR server for the referral task. Secure messaging. Healthcare Identifiers Service (AU) or the NHI interface (NZ).
Systems of record (R04)	Patient administration system, PAS, for the referral, the waiting list and bookings. Patient index. Scanned medical record.
Line of business and OT (R05)	Clinic templates. Community health intake, where a referral goes there.
Intelligence and learning (R06)	Document reading and field extraction. A triage suggestion model only if the service has validated one.
Agent platform (R07)	The agent and its fixed steps. Today, robotic process automation bots may register referrals.
Productivity and collaboration (R08)	Shared inbox. Teams for clerk escalations.
Experience and channels (R09)	SMS, letters, and a patient portal where one exists. GP portal for referral status.
Security and identity (R10)	The agent's own service account. NASH certificate use. Role-based access. Security monitoring.
Governance, risk and sovereignty (R11)	Referral criteria owned by clinical leads. Privacy impact assessment. AI governance sign-off.
Observability and FinOps (R12)	Traces per referral. Integration error queue. Cost per referral.
Operating model and supervision (R13)	The referral hub team leader supervises. Clerks handle exceptions.
Agent data engineering (R14)	Extraction that keeps the page and position of each field. Versioned referral criteria as reference data. Memory per referral thread.

Layer: Infrastructure and compute (R01)
Systems in this use case: Hosting for the agent in an Australian or New Zealand region. A text recognition (OCR) service.

Layer: Data platform (R02)
Systems in this use case: Clinical data repository for recent results. Data warehouse for waiting list reports.

Layer: Integration fabric (R03)
Systems in this use case: Integration engine for inbound messages and the fax route. FHIR server for the referral task. Secure messaging. Healthcare Identifiers Service (AU) or the NHI interface (NZ).

Layer: Systems of record (R04)
Systems in this use case: Patient administration system, PAS, for the referral, the waiting list and bookings. Patient index. Scanned medical record.

Layer: Line of business and OT (R05)
Systems in this use case: Clinic templates. Community health intake, where a referral goes there.

Layer: Intelligence and learning (R06)
Systems in this use case: Document reading and field extraction. A triage suggestion model only if the service has validated one.

Layer: Agent platform (R07)
Systems in this use case: The agent and its fixed steps. Today, robotic process automation bots may register referrals.

Layer: Productivity and collaboration (R08)
Systems in this use case: Shared inbox. Teams for clerk escalations.

Layer: Experience and channels (R09)
Systems in this use case: SMS, letters, and a patient portal where one exists. GP portal for referral status.

Layer: Security and identity (R10)
Systems in this use case: The agent's own service account. NASH certificate use. Role-based access. Security monitoring.

Layer: Governance, risk and sovereignty (R11)
Systems in this use case: Referral criteria owned by clinical leads. Privacy impact assessment. AI governance sign-off.

Layer: Observability and FinOps (R12)
Systems in this use case: Traces per referral. Integration error queue. Cost per referral.

Layer: Operating model and supervision (R13)
Systems in this use case: The referral hub team leader supervises. Clerks handle exceptions.

Layer: Agent data engineering (R14)
Systems in this use case: Extraction that keeps the page and position of each field. Versioned referral criteria as reference data. Memory per referral thread.

How it runs today

#	Step	Role	System	How the data moves
1	Receive	Referral clerk in the central referral hub	Fax server, secure messaging inbox, e-referral worklist, shared email	A fax image, an HL7 version 2 message carrying a PDF letter, or form fields. The clerk opens each one on screen.
2	Find or create the patient	Referral clerk	PAS and patient index. Healthcare Identifiers Service (AU) or NHI (NZ).	Name, date of birth, and Medicare number or NHI keyed from the letter. A new record if there is no match.
3	Register the referral	Referral clerk	PAS referral module. Scanned medical record.	Date, referrer and specialty keyed in. The letter is scanned or attached. The waiting time clock starts under state rules.
4	Check completeness	Clerk for admin fields. Clinical nurse for clinical minimums.	PAS. Referral criteria such as Queensland's Clinical Prioritisation Criteria, Victoria's Statewide Referral Criteria, or HealthPathways.	A checklist on screen or paper. Missing items go in PAS comments.
5	Chase missing information	Referral clerk	Fax, phone, secure message, letter	A letter or fax to the GP. The referral goes on hold. The reply comes by fax and starts again at step 1.
6	Clinical triage	Consultant, registrar or clinical nurse consultant	Paper triage folder, PAS e-triage worklist, or the EMR	Reads the letter and attachments. In Australia, writes an urgency category of 1, 2 or 3. In New Zealand, accepts with a priority or declines with advice. Often done in weekly batches.
7	Enter the triage outcome	Referral clerk	PAS	Category and clinic keyed from the triage sheet. The patient joins the outpatient waiting list.
8	Acknowledge	Referral clerk	PAS letter templates, mail house, SMS gateway	Printed letters to the patient and the GP. SMS where set up.
9	Book and remind	Booking clerk, with automated SMS	PAS clinic templates, phone, SMS gateway	Picks patients by category and time waited. Phones the patient and books a slot. Arranges an interpreter and transport. An SMS reminder goes a few days before.
10	Report	Data and performance team	Data warehouse, state collections, dashboards	A nightly PAS extract. Monthly waiting list reports to the state health department or Health NZ.

#: 1
Step: Receive
Role: Referral clerk in the central referral hub
System: Fax server, secure messaging inbox, e-referral worklist, shared email
How the data moves: A fax image, an HL7 version 2 message carrying a PDF letter, or form fields. The clerk opens each one on screen.

#: 2
Step: Find or create the patient
Role: Referral clerk
System: PAS and patient index. Healthcare Identifiers Service (AU) or NHI (NZ).
How the data moves: Name, date of birth, and Medicare number or NHI keyed from the letter. A new record if there is no match.

#: 3
Step: Register the referral
Role: Referral clerk
System: PAS referral module. Scanned medical record.
How the data moves: Date, referrer and specialty keyed in. The letter is scanned or attached. The waiting time clock starts under state rules.

#: 4
Step: Check completeness
Role: Clerk for admin fields. Clinical nurse for clinical minimums.
System: PAS. Referral criteria such as Queensland's Clinical Prioritisation Criteria, Victoria's Statewide Referral Criteria, or HealthPathways.
How the data moves: A checklist on screen or paper. Missing items go in PAS comments.

#: 5
Step: Chase missing information
Role: Referral clerk
System: Fax, phone, secure message, letter
How the data moves: A letter or fax to the GP. The referral goes on hold. The reply comes by fax and starts again at step 1.

#: 6
Step: Clinical triage
Role: Consultant, registrar or clinical nurse consultant
System: Paper triage folder, PAS e-triage worklist, or the EMR
How the data moves: Reads the letter and attachments. In Australia, writes an urgency category of 1, 2 or 3. In New Zealand, accepts with a priority or declines with advice. Often done in weekly batches.

#: 7
Step: Enter the triage outcome
Role: Referral clerk
System: PAS
How the data moves: Category and clinic keyed from the triage sheet. The patient joins the outpatient waiting list.

#: 8
Step: Acknowledge
Role: Referral clerk
System: PAS letter templates, mail house, SMS gateway
How the data moves: Printed letters to the patient and the GP. SMS where set up.

#: 9
Step: Book and remind
Role: Booking clerk, with automated SMS
System: PAS clinic templates, phone, SMS gateway
How the data moves: Picks patients by category and time waited. Phones the patient and books a slot. Arranges an interpreter and transport. An SMS reminder goes a few days before.

#: 10
Step: Report
Role: Data and performance team
System: Data warehouse, state collections, dashboards
How the data moves: A nightly PAS extract. Monthly waiting list reports to the state health department or Health NZ.

Swimlanes for the GP and patient, the referral clerk, the clinician, the booking clerk and the systems. Step 1: the referral clerk receives a fax, secure message or e-referral. Step 2: the clerk finds the patient in the patient administration system (PAS). Step 3: the clerk registers the referral. Step 4: the clerk checks it is complete. Step 5: the clerk chases missing items, and the GP's reply by fax goes back to step 1. Step 6: a clinician triages it. Step 7: the clerk keys in the triage result. Step 8: letters go to the patient and the GP. Step 9: the booking clerk phones the patient, books and sends an SMS reminder. Step 10: the data warehouse reports the waiting list. A blue box under each step names the system it uses. — **Referral to appointment today**Most steps are keyed by hand. Missing information sends the referral round the loop again.Open image at full size ↗

Handoffs. The clerk hands to the clinician for triage, then gets it back. The referral hub hands to the clinic. The hospital writes to the GP to ask for information, to acknowledge, or to decline. The clinic books interpreters and patient transport.

Where reporting comes in. PAS data reaches the data warehouse every night. The measures are time to triage, the number waiting, and the share seen within the recommended time. Queensland publishes specialist outpatient performance by category. Category 1 should be seen within 30 days and Category 2 within 90 days. Category 3 should be seen within 365 days (Queensland Health, accessed 15 October 2026). New Zealand reports Elective Services Patient Flow Indicators to Health NZ. One counts referrals processed within 10 working days. These rules were not checked in this research.

Volumes and cycle time.

In May 2026, 362,886 people in Queensland were waiting for a first specialist appointment. That was 15 percent more than a year earlier (AMA Queensland, August 2026, citing Queensland Health).
AMA Queensland calls the people waiting to get onto the list a "hidden waiting list".
One ENT service at Logan gets about 700 referrals a month. Sorting them takes about 12 clinical hours (Metro South Health research abstract, undated).
Waikato dermatologists handled more than 8,000 e-referrals in 2023 (Health Research Council, 2024).
Receipt to triage takes a few working days, and longer when clinicians are busy (typical, unsourced).
No current figure was found for the share of referrals that still arrive by fax.

Pain points.

Fax and re-keying.
The same referral arrives twice, by two channels.
The wrong patient is matched, or a duplicate record is created.
Incomplete referrals bounce back and forth.
Triage backs up when consultants are in theatre or on leave.
The GP and the patient do not know the status.
Long waiters lose touch, and phone numbers go stale.
Referral criteria differ by state and by clinic.

How agents run it

One agent runs fixed steps. Model calls only read documents and draft messages. Fixed rules decide order, limits and status. The agent writes nothing to the PAS until a clinician has triaged.

#	Step	Agent or person	Reads, and from where	Writes	Who approves, and where
1	Take in the referral	Agent	The fax image through the document capture service. The HL7 message from the integration engine. The e-referral as a FHIR ServiceRequest or form data.	A new FHIR Task with status "received", linked to the original document. Each field keeps its page and position.	No one. Nothing goes to the PAS yet.
2	Propose the patient match and check for duplicates	Agent	The PAS or patient index through a FHIR Patient search. The IHI from the HI Service (AU) or the NHI FHIR interface (NZ). Open referrals for the same patient and specialty.	A proposed match on the task. A duplicate flag, with both documents side by side.	The clerk confirms any doubt in the referral worklist. The agent never creates or merges a patient record.
3	Check completeness	Fixed rules, run by the agent	Versioned referral criteria for the clinic, held as reference data. The extracted fields.	A list of missing items on the task. Status "awaiting information".	The clinic's clinical lead approves the rules before go-live.
4	Ask for missing items and match replies	Agent	Referrer details from the provider directory. Inbound secure messages and faxes, as events.	A secure message from an approved template, with a copy kept with the referral. The updated task. Step 3 runs again.	The clerk approves each message at first. The clerk sees any reply that does not answer the request.
5	Prepare the triage view	Agent	The referral. Recent results from the clinical data repository (FHIR Observation and DiagnosticReport). Imaging reports. Prior letters. My Health Record documents where policy allows.	A triage view. Each item shows its source and date. Gaps are listed.	No one. It is a draft for the clinician.
6	Clinical triage	Consultant or clinical nurse consultant	The triage view and the original documents	The urgency category or decision, in the PAS or EMR triage worklist	This is the clinical decision. The agent records it as given.
7	Put on the waiting list	Agent	The triage outcome	The waiting list entry in the PAS, through its interface or an HL7 message. Fixed checks run first.	The clerk approves at first. Later, a fixed rule does.
8	Offer appointments	Agent	Clinic slots from the PAS interface or FHIR Slot. Booking order rules. Contact and interpreter preferences.	An SMS or portal message offering slots. The patient chooses.	The booking order is a fixed rule. The clerk approves any booking out of order.
9	Book and read back	Agent	The patient's choice	A booking through the PAS interface or a FHIR Appointment. The agent reads back the booking number and status.	The clerk handles any failed or clashing write.
10	Report	Existing data team	The PAS as today. Agent traces.	Waiting list reports, unchanged. New measures: time per step, requests sent, clerk overrides.	The performance manager

#: 1
Step: Take in the referral
Agent or person: Agent
Reads, and from where: The fax image through the document capture service. The HL7 message from the integration engine. The e-referral as a FHIR ServiceRequest or form data.
Writes: A new FHIR Task with status "received", linked to the original document. Each field keeps its page and position.
Who approves, and where: No one. Nothing goes to the PAS yet.

#: 2
Step: Propose the patient match and check for duplicates
Agent or person: Agent
Reads, and from where: The PAS or patient index through a FHIR Patient search. The IHI from the HI Service (AU) or the NHI FHIR interface (NZ). Open referrals for the same patient and specialty.
Writes: A proposed match on the task. A duplicate flag, with both documents side by side.
Who approves, and where: The clerk confirms any doubt in the referral worklist. The agent never creates or merges a patient record.

#: 3
Step: Check completeness
Agent or person: Fixed rules, run by the agent
Reads, and from where: Versioned referral criteria for the clinic, held as reference data. The extracted fields.
Writes: A list of missing items on the task. Status "awaiting information".
Who approves, and where: The clinic's clinical lead approves the rules before go-live.

#: 4
Step: Ask for missing items and match replies
Agent or person: Agent
Reads, and from where: Referrer details from the provider directory. Inbound secure messages and faxes, as events.
Writes: A secure message from an approved template, with a copy kept with the referral. The updated task. Step 3 runs again.
Who approves, and where: The clerk approves each message at first. The clerk sees any reply that does not answer the request.

#: 5
Step: Prepare the triage view
Agent or person: Agent
Reads, and from where: The referral. Recent results from the clinical data repository (FHIR Observation and DiagnosticReport). Imaging reports. Prior letters. My Health Record documents where policy allows.
Writes: A triage view. Each item shows its source and date. Gaps are listed.
Who approves, and where: No one. It is a draft for the clinician.

#: 6
Step: Clinical triage
Agent or person: Consultant or clinical nurse consultant
Reads, and from where: The triage view and the original documents
Writes: The urgency category or decision, in the PAS or EMR triage worklist
Who approves, and where: This is the clinical decision. The agent records it as given.

#: 7
Step: Put on the waiting list
Agent or person: Agent
Reads, and from where: The triage outcome
Writes: The waiting list entry in the PAS, through its interface or an HL7 message. Fixed checks run first.
Who approves, and where: The clerk approves at first. Later, a fixed rule does.

#: 8
Step: Offer appointments
Agent or person: Agent
Reads, and from where: Clinic slots from the PAS interface or FHIR Slot. Booking order rules. Contact and interpreter preferences.
Writes: An SMS or portal message offering slots. The patient chooses.
Who approves, and where: The booking order is a fixed rule. The clerk approves any booking out of order.

#: 9
Step: Book and read back
Agent or person: Agent
Reads, and from where: The patient's choice
Writes: A booking through the PAS interface or a FHIR Appointment. The agent reads back the booking number and status.
Who approves, and where: The clerk handles any failed or clashing write.

#: 10
Step: Report
Agent or person: Existing data team
Reads, and from where: The PAS as today. Agent traces.
Writes: Waiting list reports, unchanged. New measures: time per step, requests sent, clerk overrides.
Who approves, and where: The performance manager

Swimlanes for the agent, the referral clerk, the clinician, fixed rules, the systems and the evidence store. Step 1: the agent takes in the referral and opens a referral task. Step 2: it proposes the patient match, and the clerk confirms. Step 3: fixed rules check completeness, and the clinical lead approves the rules. Step 4: the agent asks the referrer for missing items, and the clerk approves. Step 5: it prepares the triage view. Step 6: a clinician triages, which is the clinical decision. Step 7: the agent adds the patient to the waiting list in the PAS, and the clerk approves. Step 8: it offers slots in a fixed booking order, and the clerk approves any exception. Step 9: it books and reads back the result. Step 10: waiting list reports run as today. The evidence store keeps traces, the PAS audit log, message logs and the original documents. A diamond marks each approval. — **Referral to appointment with an agent**A diamond marks each approval. Triage stays with the clinician.Open image at full size ↗

What stays with a person, and why.

The urgency category, and accepting or declining the referral. That is a clinical decision.
Any doubt about who the patient is. A wrong match exposes one patient's record to another.
Booking out of category order. That is a fairness decision about a person.
Declining a referral and telling the GP. It is a clinical decision and a legal record.
Using My Health Record. Access rules and the patient's own controls apply.

At Logan, a model called ReferralAI suggests an urgency category to clinicians. A suggestion model like this is a separate tool. It needs its own testing and a TGA check. The agent shows such a suggestion only if the service has validated it. The agent still does not set urgency.

Where the evidence is kept. Every agent step is a trace, stored outside the agent and keyed to the task. Every write to the PAS shows in the PAS audit log, under the agent's own account. Every message stays in the secure messaging log. The original documents stay unchanged in the document store.

What changes in the systems.

A referral staging worklist built on FHIR Task, in front of the PAS.
New statuses: received, matched, awaiting information, ready for triage, triaged, offered, booked, closed.
Event subscriptions for a new inbound document, a reply received and a slot released.
An agent service account in the PAS. It can write only referral status, waiting list entries and bookings.
HI Service calls use the organisation's existing NASH certificate and are logged per call. Check the HI Service rules if a vendor hosts the agent.

What does not change. The PAS stays the record of the waiting list. State waiting time rules and reporting definitions stay. The specialist team still triages. GP software and the secure messaging networks stay as they are.

Who does this today

Who	What	Status and date
ReferralAI, Logan ENT, Metro South Health	Suggests an urgency category for ENT referrals. Clinicians decide.	Development and prospective validation. Date not confirmed. A 2023 study of 17,378 referrals found 53.8 percent agreement with the category given.
Austin Hospital, Melbourne, with the University of Melbourne	AI-supported triage for long gynaecology waits	Pilot. Undated.
Te Whatu Ora Waitemata	AI decision support for GP referrals to cardiology	Proposed approach, NZMJ viewpoint, 2025
Auckland researchers	AI-assisted triage of colonoscopy referrals. Clinicians keep control.	National validation study, invitation July 2026
East Suffolk and North Essex NHS, England	Three robotic process automation bots watch incoming e-Referral Service referrals	Live. Date not confirmed.
Allina Health with Qventus, US	A joint agent build, with specialty referrals as the first focus	Plan announced December 2025 [vendor]
Hyro at Tampa General, Intermountain Health and Sutter Health, US	Phone and chat agents for scheduling and routing	Live. Tampa General reports call abandonment down from 34 percent to 14.9 percent [vendor].
Epic agents, US	Art for clinicians and Emmie for patients	Live at US sites in 2026 [vendor]. Not confirmed in Australia.
Heidi II, Australia and New Zealand	Drafts referrals and follow-ups. A clinician reviews before anything is sent. Uses read-only screen control where there is no EMR connector.	Launched 28 September 2026. Primary care first. No Australian public hospital site found [vendor].

Who: ReferralAI, Logan ENT, Metro South Health
What: Suggests an urgency category for ENT referrals. Clinicians decide.
Status and date: Development and prospective validation. Date not confirmed. A 2023 study of 17,378 referrals found 53.8 percent agreement with the category given.

Who: Austin Hospital, Melbourne, with the University of Melbourne
What: AI-supported triage for long gynaecology waits
Status and date: Pilot. Undated.

Who: Te Whatu Ora Waitemata
What: AI decision support for GP referrals to cardiology
Status and date: Proposed approach, NZMJ viewpoint, 2025

Who: Auckland researchers
What: AI-assisted triage of colonoscopy referrals. Clinicians keep control.
Status and date: National validation study, invitation July 2026

Who: East Suffolk and North Essex NHS, England
What: Three robotic process automation bots watch incoming e-Referral Service referrals
Status and date: Live. Date not confirmed.

Who: Allina Health with Qventus, US
What: A joint agent build, with specialty referrals as the first focus
Status and date: Plan announced December 2025 [vendor]

Who: Hyro at Tampa General, Intermountain Health and Sutter Health, US
What: Phone and chat agents for scheduling and routing
Status and date: Live. Tampa General reports call abandonment down from 34 percent to 14.9 percent [vendor].

Who: Epic agents, US
What: Art for clinicians and Emmie for patients
Status and date: Live at US sites in 2026 [vendor]. Not confirmed in Australia.

Who: Heidi II, Australia and New Zealand
What: Drafts referrals and follow-ups. A clinician reviews before anything is sent. Uses read-only screen control where there is no EMR connector.
Status and date: Launched 28 September 2026. Primary care first. No Australian public hospital site found [vendor].

No Australian or New Zealand public hospital was found running an agent that takes in, chases and books referrals.

Where this sits

The four questions place this agent.

Role. It coordinates. The domain is health referrals.
Permissions. These are what its own credentials let it do. It reads referrals, identity details, results and clinic slots. It writes referral tasks, waiting list entries and bookings. It sends secure messages and SMS from templates. It cannot set urgency, decline a referral, or create or merge a patient.
Autonomy. It is designed and permitted for delegated tasks (A2) on the autonomy contract. A clerk reviews its output, and fixed rules release routine steps. Urgency and eligibility drop to assisted (A1), where the clinician decides.
Impact. It touches none of the four deterministic zones. The rule for decisions about people applies. Urgency, decline and booking out of order shape a decision about a person's health. A named person makes each one. A wrong patient match cannot be undone once the data is seen.

It is Tier 3 (strict), because it reaches regulated health data. It reads untrusted input from outside faxes and messages. It reaches health data, and it sends messages out. That is all three parts of the Rule of Two. So it stays at A2, and it sends only approved templates. Letting templates go without review is a change, so the risk profile is scored again.

Its learning level is fixed (L0). It does not learn from cases. People change its rules and templates at the change stage of the agent lifecycle.

Two of the seven capabilities carry most of the control. Identity and policy gives the agent its own identity (ID2) on the delegation chain. Policy is enforced outside the model: the PAS account refuses any write beyond status, waiting list and bookings. Observability and audit trail keeps every step where the agent cannot touch it.

Measure the result

Compare with the current hub on past referrals first, then in a live trial. Measure these:

Time from receipt to ready for triage.
Requests sent per referral, and replies that answered them.
Wrong patient matches and duplicate bookings. The target is none.
Clerk overrides.
Cost per referral that reaches a booking or a clear decline. The value and investment page sets out that cost.

Report patient and GP complaints separately. Do not read clinical benefit into booking speed.

Start with a trial

Pick one clinic and one channel, such as the e-referral form. Run the agent on past referrals and compare with what the clerks did. Then run it live with a clerk approving every step. Register the agent with a named sponsor and owner before go-live. Move a step to a fixed rule only when its error rate is known.

Evidence and limits

The steps come from known practice in Australian and New Zealand referral hubs. Step times are typical, unsourced. Volumes exist only as a state total and for single services.

Triage suggestion models are at validation stage. The ReferralAI agreement figure comes from a 2023 study. Vendor results are as the vendor reported them.

Two checks come before a build. Confirm the TGA position before showing any model-suggested category. Confirm the HI Service rules before a vendor hosts an agent that looks up identifiers.

Next step

Follow the patient after discharge on care follow-up. Or go back to the hospital estate.

Explore this topic

Research for this page was done on 15 October 2026.

Standards. HL7 FHIR separates the request, the work and the booking. The R4 ServiceRequest resource holds the request. The R4 Task resource tracks the work. The R4 Appointment resource holds the booking. IHE 360X closed-loop referral closes the loop back to the referrer. These are integration references, not evidence that an agent is safe. Confirm the version and local profiles your systems support.

Sources.

AMA Queensland, public outpatients working group, August 2026.
Queensland Health, specialist appointments performance, accessed 15 October 2026.
PMC10642163, AI in referral triage on Clinical Prioritisation Criteria, 2023.
Metro South Health, ReferralAI abstract, undated. The PDF refused the fetch. Figures come from the search summary.
Health Research Council, Waikato dermatology e-referrals, 2024.
University of Melbourne, AI in the waitlist, undated.
NZMJ, making GP referrals suitable for AI, volume 138, 2025.
NZSG, national validation study of AI-assisted colonoscopy triage, July 2026.
digitalhealth.net, East Suffolk and North Essex virtual workers, undated. Not opened.
HC Innovation Group, Allina Health and Qventus, December 2025 [vendor].
Becker's, health systems expanding agentic AI, undated. MedCity News, Sutter Health AI agent, September 2025.
HIT Consultant, Epic at HIMSS 2026, 10 March 2026.
The Medical Republic, Heidi II agents, 30 September 2026.