> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mirobody.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Standardization

> How every write becomes coded, unit-normalized, FHIR-mirrored data — OCR → extraction → LOINC → UCUM → FHIR.

Health data arrives messy — "血糖(空腹)", "FBG", "Glucose, fasting" are the same measurement in three costumes, with units to match. Mirobody's data plane standardizes **every write** so that the agent (and your queries) see one coherent, coded dataset. This page explains the pipeline; you never call it directly — it runs inside [`POST /v1/data`](/en/api-reference/data), [`POST /v1/files`](/en/api-reference/files), and [`POST /v1/extract`](/en/api-reference/extract).

## The pipeline

```text theme={null}
document / record
   │
   ├─ 1. OCR & text extraction        PDF / image → text; Excel → structured rows
   │
   ├─ 2. LLM reading extraction       schema-constrained: {indicator, value, unit, measured_at}
   │                                  (documents only — structured /v1/data records skip this)
   ├─ 3. LOINC resolution             deterministic name → code: curated corpus + embedding
   │                                  retrieval. The LLM is NEVER asked to guess a code —
   │                                  no confident match means loinc_code = null, not a wrong code.
   ├─ 4. UCUM unit normalization      "mg/dl" → mg/dL, value parsed to a number
   │
   └─ 5. FHIR mirror                  a FHIR R4 Observation per reading (fhir_resource_id)
```

The critical design choice is step 3: **codes are resolved deterministically, not generated.** Free-text indicator names are matched against a curated LOINC corpus via embedding retrieval with a confidence threshold. LLMs are great at *reading* documents (step 2) and terrible at *reciting* code systems — a hallucinated LOINC code is worse than none, so an unconfident match returns `null` and keeps the raw name.

## Before / after

What you send (or what a lab PDF says) vs. what the store holds:

|               | Before (as written)                         | After (standardized)                                                                         |
| ------------- | ------------------------------------------- | -------------------------------------------------------------------------------------------- |
| Indicator     | `"血糖(空腹)"` / `"FBG"` / `"Glucose, fasting"` | `loinc_code: "1558-6"`, `canonical_name: "Fasting glucose [Mass/volume] in Serum or Plasma"` |
| Value         | `"5.4 mmol/L"` (one string)                 | `parsed_value: "5.4"`, `parsed_unit: "mmol/L"` (UCUM)                                        |
| Unit spelling | `"mg/dl"`, `"MG/DL"`, `"mg/dL"`             | `"mg/dL"` (one UCUM form)                                                                    |
| Interop       | free text                                   | FHIR R4 Observation (`fhir_resource_id`)                                                     |
| Original      | —                                           | **kept**: `value` stays the human-readable string; raw names/units preserved                 |

Three spellings of the same test become **one series** — trend queries, the agent's data tools, and your own analytics all see it as one indicator.

## Where you see it

| Surface                                               | What surfaces                                                                                                                    |
| ----------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- |
| [`POST /v1/data`](/en/api-reference/data)             | Response counts `standardized` alongside `ingested`.                                                                             |
| [`GET /v1/data`](/en/api-reference/data#read-records) | Every row carries `parsed_value` / `parsed_unit` / `loinc_code` / `canonical_name` / `fhir_resource_id`.                         |
| [`POST /v1/extract`](/en/api-reference/extract)       | The whole pipeline as a synchronous call — **dry-run by default**, so you can inspect standardization before committing a write. |
| The agent                                             | Grounded answers query the standardized series — which is why "how's my glucose?" finds records written as "FBG".                |

## Cookbook: one call, report → structured data

```bash theme={null}
# Inspect first (nothing persisted) …
curl https://mirobody-api.thetahealth.ai/v1/extract \
  -H "Authorization: Bearer $MIROBODY_API_KEY" \
  -F "user=alice" -F "file=@lab_report.pdf"

# … then commit the same extraction
curl https://mirobody-api.thetahealth.ai/v1/extract \
  -H "Authorization: Bearer $MIROBODY_API_KEY" \
  -F "user=alice" -F "file=@lab_report.pdf" \
  -F "store=true" -F "retention=permanent"
```

See [Extract](/en/api-reference/extract) for the full row shape (`indicator_raw`, `loinc_code`, `confidence`, …).