Clinical Document Summary

Challenges Clinical Document Summary addresses

Done by hand, clinical documentation means gathering clinical document and summary settings, working through 4 separate passes over the same material, then producing encounter, summary and problems and diagnoses. 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 waits until someone remembers it, which is usually the point at which it has become urgent. As volume grows the work does not get harder, only longer, and the first thing to go is the checking.

Clinical Document Summary 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 hand this summary to a colleague?” 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: Extracting the document text

First of 4. It works from clinical document and summary settings and feeds the step after it.

Key Tasks:

• Locating the material: It works from clinical document and summary settings, so nothing has to be forwarded, re-keyed or renamed first.
• Handling the format it arrives in: Scanned pages, native documents, spreadsheets and message bodies are all read the same way, including layouts where the relevant figure sits inside a table rather than a labelled field.
• Pulling the fields that matter: Only the fields the rest of the run needs are extracted. What cannot be read confidently is recorded as unread rather than filled in with a best guess.

Outcome:

• Fields extracted: The fields are available to the steps that follow, with anything unreadable listed rather than silently defaulted — which is what stops a bad extraction becoming a confident wrong answer three steps later.

Step 2: Reading the record

Step 2 of 4. It takes what step 1 produced and hands its result to step 3.

Key Tasks:

• Reading the record specifically: This pass is scoped to the record rather than to the document as a whole, so a field that appears in more than one place is taken from the one that governs.
• Keeping the original alongside: Each extracted value stays linked to where it was found, so a figure that looks wrong can be checked against the source rather than re-entered.
• Locating the material: It works from what step 1 produced, so nothing has to be forwarded, re-keyed or renamed first.

Outcome:

• The record captured: The fields are available to the steps that follow, with anything unreadable listed rather than silently defaulted — which is what stops a bad extraction becoming a confident wrong answer three steps later.

Step 3: Writing the summary

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

Key Tasks:

• Working from the extracted values: Figures come from what step 2 produced rather than from a re-keyed copy, which removes the transcription step where arithmetic errors usually originate.
• Applying your rules: Bands, rates and rounding are configuration. The same inputs produce the same figures on every run.
• Keeping the components: Each total is returned with the parts that produced it, so a figure that looks wrong can be traced rather than recomputed.

Outcome:

• Figures that reconcile: Figures that reconcile to their own components — the totals shown and the lines above them agree, which is the property that makes a number safe to quote onward.

Step 4: Mapping to FHIR R4

Last of 4. It takes what step 3 produced and produces encounter and summary.

Key Tasks:

• Working from the run so far: This step takes what step 3 produced and carries it toward encounter and summary.
• Following the same rules each time: The behaviour is configuration rather than judgement made fresh per run, so clinical documentation 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 5: 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 hand this summary to a colleague?” 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 Clinical Document Summary 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 Clinical Document Summary?

• Checks are evidenced, not asserted: Each check records what was expected and what was found. A failure can be understood — and argued with — without re-running anything.
• 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.
• Takes documents as they arrive: Scanned pages, native files and awkward layouts are read as they are. Nothing has to be renamed, re-keyed or converted into a template before a run.
• Corrected by the people using it: After each run it asks “Would you hand this summary to a colleague?”. Those answers become the evaluation set, which means it is measured against your judgement rather than ours.