Patient Message Triage

Challenges Patient Message Triage addresses

Done by hand, patient communications means gathering inbound patient message, working through 6 separate passes over the same material, then producing triage, safety flags and draft reply. None of it is difficult and all of it is exacting, which is the combination people are worst at holding. The errors that matter are the ones a tired reader does not notice, and they surface later — in a reconciliation, or in somebody’s reply. It starts whenever something arrives, which means someone has to be watching for it to start at all. As volume grows the work does not get harder, only longer, and the first thing to go is the checking.

Patient Message Triage runs that same sequence end to end and returns the result as structured artefacts. What it cannot settle it hands over rather than guesses at, and your correction is kept: it asks “Would you have sent this?” after every run, and those answers become the set it is measured against. Nothing that moves money, alters a contract or reaches a customer executes without human approval, and every action is written to an audit log. The gain is in the volume that no longer has to be read, not in removing the judgement.

How it works

Step 1: Triaging the message

First of 6. It works from inbound patient message and feeds the step after it.

Key Tasks:

• Working from the run so far: This step takes inbound patient message and carries it toward step 2.
• Following the same rules each time: The behaviour is configuration rather than judgement made fresh per run, so patient communications is handled the same way every time.
• Surfacing what it cannot settle: Anything ambiguous is passed on as ambiguous rather than resolved silently.

Outcome:

• Passed on: The result passes to the next step, with anything unresolved carried forward as an open item rather than dropped.

Step 2: Looking up the patient record

Step 2 of 6. It takes what step 1 produced and hands its result to step 3.

Key Tasks:

• Covering the whole set: Every record in scope is examined, not a sample. The step before it narrowed the field; this one does not narrow it further by accident.
• Judging relevance by content: Whether something belongs in this run is decided from what it says rather than from where it was filed or how it was named.
• Discarding visibly: What is excluded is recorded as excluded, so "nothing found" can be distinguished from "nothing looked at".

Outcome:

• Relevant items found: They pass to the next step with the reason they were selected attached.
• Nothing relevant: The run reports that it found nothing and stops, rather than producing an empty artefact that reads like a failure.

Step 3: Checking the practice policy

Step 3 of 6. It takes what step 2 produced and hands its result to step 4.

Key Tasks:

• Running the checks in order: Every rule for patient communications is applied to every record, in the same order each run. A record is not skipped because it looks routine.
• Recording evidence, not verdicts: Each check stores what was expected and what was found, so a failure can be understood without re-running anything.
• Separating clear from unclear: A check the agent cannot settle is marked unresolved rather than passed, which keeps "checked" meaning checked.

Outcome:

• All checks pass: The record clears with its evidence attached, available if anyone asks later.
• A check fails: The record is held with the failing checks named and the rest shown as passed, so a reviewer sees the scope of the problem rather than only that there is one.

Step 4: Deciding how to handle it

Step 4 of 6. It takes what step 3 produced and hands its result to step 5.

Key Tasks:

• Handling how to handle it: The work at this step is how to handle it, scoped to that and not extended to anything the run has already settled.
• Leaving the record behind it: What this step did and what it decided are written down, so the result can be traced without re-running the step.
• Working from the run so far: This step takes what step 3 produced and carries it toward step 5.

Outcome:

• How to handle it handled: The result passes to the next step, with anything unresolved carried forward as an open item rather than dropped.

Step 5: Preparing the reply for approval

Step 5 of 6. It takes what step 4 produced and hands its result to step 6.

Key Tasks:

• Writing from the run, not from a template: The text is built from what this run actually found, so two patient communications outputs differ where the underlying records differ.
• Leading with what needs a decision: The exceptions come first and the routine detail follows, because the reader is deciding rather than reading.
• Staying inside the evidence: Nothing appears in the text that is not supported by a record the run examined. Gaps are stated as gaps.

Outcome:

• Draft ready: It is held for approval. Nothing reaches a customer, a calendar or a channel until a person releases it.
• Not enough to write from: It says so instead of producing something plausible from thin evidence, which is the failure that is hardest to catch on review.

Step 6: Mapping the triage decision to FHIR R4

Last of 6. It takes what step 5 produced and produces triage and safety flags.

Key Tasks:

• Following the same rules each time: The behaviour is configuration rather than judgement made fresh per run, so patient communications is handled the same way every time.
• Surfacing what it cannot settle: Anything ambiguous is passed on as ambiguous rather than resolved silently.
• Handling the triage decision to fhir r4: The work at this step is the triage decision to fhir r4, scoped to that and not extended to anything the run has already settled.

Outcome:

• The triage decision to fhir r4 handled: The result passes to the next step, with anything unresolved carried forward as an open item rather than dropped.

Step 7: Your review, and what it changes

The run ends with a person, not with a result being filed.

Key Tasks:

• Asking a specific question: It asks “Would you have sent this?” rather than for a rating. A question about this run is answerable; a score out of five is not.
• Keeping the correction: What you change is recorded against the case that produced it, so the disagreement is retrievable rather than absorbed.
• Building the evaluation set: Those cases become what the agent is measured on. It is scored against your judgement rather than against a general benchmark.

Outcome:

• A measured agent, not an assumed one: The cases Patient Message Triage handles well and the cases it does not are both visible, and the second list is the one that decides what changes. Nothing is retrained silently on the back of a single correction.

Why use Patient Message Triage?

• Answers from your own material: It retrieves from a knowledge base you populate — your policies, contracts and reference documents — so its decisions follow how your business actually operates rather than a general model’s assumptions. Sources are cited alongside the result.
• Nothing leaves without approval: Draft reply is drafted and held. A person releases them, so the agent's reach ends at your own review step.
• Every statement cites its source: Findings come back with the records behind them, so a reviewer can check a claim instead of deciding whether to trust it. An assertion with no source is the expensive kind to discover late.
• A batch is one run, not a hundred: It works the whole set in a single pass and returns a row per item with its verdict, so the volume that needs no attention never has to be opened.
• Machine-readable for whatever comes next: One of the artefacts is a structured payload, so this agent can sit in the middle of a pipeline rather than only at the end of one.