# Condition Stories

URL: https://docs.clinia.com/docs/context-assembly/condition-stories

> Pre-computed longitudinal narratives that give AI agents full clinical context for a condition in a single read.

A condition story is a pre-computed Markdown narrative for a single clinical condition. It assembles all relevant information from the knowledge graph (onset, medications, labs, complications, monitoring status) into a single readable document. The relationships between conditions, medications, and labs are inferred by the [clinical knowledge base](https://docs.clinia.com/docs/get-started/patient-graph#how-facts-and-events-are-related).

## Why condition stories? [#why-condition-stories]

A condition like Type 2 Diabetes Mellitus doesn't exist in isolation. Understanding it requires knowing:

- When it was first diagnosed and across which sources
- Which medications are currently treating it
- Which labs monitor its control
- Whether there are complications (CKD, neuropathy, retinopathy)
- Whether those complications are being adequately monitored

This information is distributed across multiple nodes in the graph. A condition story assembles it once so an agent can get a complete and coherent portrait of the condition in a single place.

## Example [#example]

```markdown
# Type 2 Diabetes Mellitus

**Status:** Active since 2016-03
**Codes:** SNOMED 44054006 · ICD-10 E11.9
**Sources:** 3 sources (FHIR Bundle, Summary_20230907.xml, Labs_2023.xml)

## Current Treatment

| Medication    | Dose       | Since   |
| ------------- | ---------- | ------- |
| Metformin     | 1000mg BID | 2016-04 |
| Empagliflozin | 10mg QD    | 2020-08 |

## Monitoring Labs

| Lab             | Latest    | Date       | In Range |
| --------------- | --------- | ---------- | -------- |
| HbA1c           | 7.1%      | 2023-09-07 | ✓        |
| eGFR            | 52 mL/min | 2023-08-15 | ⚠ Low    |
| Fasting glucose | 118 mg/dL | 2023-09-07 | ✓        |

## Complications

- **Chronic Kidney Disease (Stage 3b)**: active since 2021
  - Complication of: Type 2 Diabetes Mellitus
  - Monitored by: eGFR, urine albumin/creatinine ratio
  - Last eGFR: 52 mL/min (below target of ≥60)
```

## Patient-reported context [#patient-reported-context]

When a `symptom` [memory](https://docs.clinia.com/docs/learned-memory/overview) has been matched against the condition, the story includes a `## Patient-Reported` section built from those relationships:

```markdown
## Patient-Reported

### Conflicts with record

- "My blood sugar readings have actually been running closer to 180 some mornings"

### Corroborations

- "My fasting sugars have been running around 120 most mornings"
```

Entries are grouped by relationship type (conflicts, corroborations, additional context) and rendered from the memory's content. This section only appears when at least one matching memory exists; it never contains an empty header. `adherence` memories, which relate to medications rather than conditions, surface the same way on the medication's own file instead. See [How Interactions Become Memory](https://docs.clinia.com/docs/learned-memory/overview) for how memories are generated and matched to facts.

## Source narratives [#source-narratives]

When a [narrative](https://docs.clinia.com/docs/get-started/patient-graph#how-text-from-documents-becomes-narratives) has been adjudicated against the condition, the story ends with a `## Narratives` section linking each one:

```markdown
## Narratives

- [Insulin started](_narratives/2023-07-01_nar_k5f2c8a1bq7wz3m0xh4r9dny.md) — conflicts
- [Early diabetes review](_narratives/2019-03-14_nar_p9b7d0e34vt2lg8sc6ju1ofa.md) — corroborates
```

Every line carries the narrative's title, the path to it, and the verdicts it holds against this condition (`corroborates`, `enriches`, `conflicts`) — so a contradiction in the record is one read away from the reasoning behind it. Paths are relative to the condition's own directory.

That read gives you the reasoning, not the note. A narrative's summary and its quote are on neither the leaf nor its `structured` form: they paraphrase the passage rather than the condition, and a budgeted read spends its last bytes there. For the wording a clinician recorded, read the document under [`/sources/`](https://docs.clinia.com/api/vfs-paths#sources).

The section appears only when at least one narrative links to the condition, and only in `narrative` format; `compact` omits it. The `_narratives/` directory is listed whenever the condition is browsed either way, reporting `0 narratives` when nothing links there. See [VFS Paths](https://docs.clinia.com/api/vfs-paths).

## Token budget [#token-budget]

Condition stories respect the `token_budget` parameter. The story is rendered in full and then cut from the end — no section is selected over another — so the order sections appear in is the order a budget keeps them:

1. Status, onset, and codes
2. Progression timeline
3. Active and discontinued medications
4. Monitoring labs
5. Complications and related conditions
6. Encounters
7. Patient-reported memories
8. Links to the source narratives

The order is chosen so that cutting from the end costs the least: a low budget keeps the clinical picture and drops the cross-references that point at it. A `compact` format gives a one-paragraph overview; `narrative` gives the full story with tables.

## Accessing condition stories [#accessing-condition-stories]

Via MCP (see [`read_patient`](https://docs.clinia.com/api/mcp/tools/read-patient)):

```
read_patient("/patient/{id}/conditions/active/{condition}/_story.md")
read_patient("/patient/{id}/conditions/active/{condition}/_story.md", format="compact")
```

Via REST (see [REST API reference](https://docs.clinia.com/api/rest/get-patients-patientId-read)):

```bash
GET /v1/patients/{patientId}/read?path=/conditions/active/type_2_diabetes_mellitus/_story.md&format=narrative
```

See [Read a Condition Story](https://docs.clinia.com/docs/context-assembly/read-condition-story) for a practical walkthrough.