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

# MedDRA

> Medical Dictionary for Regulatory Activities. The international standard for coding adverse events in clinical trials and pharmacovigilance

**Medical Dictionary for Regulatory Activities (MedDRA)** is maintained by the ICH (International Council for Harmonisation). It is the international standard for coding adverse events, medical history, and indications in clinical trials and post-marketing surveillance. MedDRA is organized in a five-level hierarchy: System Organ Class (SOC), High Level Group Term (HLGT), High Level Term (HLT), Preferred Term (PT), and Lowest Level Term (LLT).

## Quick start

System identifiers: `meddra-en` · `meddra-de` · `meddra-es` · `meddra-fr` · `meddra-no` · `meddra-se` · `meddra-it`

<CodeGroup>
  ```ts title="JavaScript" expandable theme={null}
  const codes = await client.codes.predict({
    system: ["meddra-en"],
    context: [
      {
        type: "text",
        text: "Patient developed severe nausea and vomiting three days after starting metformin. Reported feeling dizzy and fatigued.",
      },
    ],
  });
  ```

  ```csharp title="C# .NET" expandable theme={null}
  var codes = await client.Codes.PredictAsync(
      new CodesGeneralPredictRequest
      {
          System = [CommonCodingSystemEnum.MeddraEn],
          Context =
          [
              new CommonTextContext
              {
                  Type = new CommonTextContext.TypeLiteral(),
                  Text = "Patient developed severe nausea and vomiting three days after starting metformin. Reported feeling dizzy and fatigued.",
              },
          ],
      }
  );
  ```

  ```python title="Python" theme={null}
  import requests

  # Replace these with your values
  ENVIRONMENT = "<eu-or-us>"
  TENANT = "<your-tenant-name>"
  TOKEN = "<your-access-token>"

  response = requests.post(
      f"https://api.{ENVIRONMENT}.corti.app/v2/tools/coding/",
      headers={
          "Authorization": f"Bearer {TOKEN}",
          "Tenant-Name": TENANT,
          "Content-Type": "application/json",
      },
      json={
          "system": ["meddra-en"],
          "context": [{"type": "text", "text": "Patient developed severe nausea and vomiting three days after starting metformin. Reported feeling dizzy and fatigued."}],
      },
  )
  response.raise_for_status()
  print(response.json())
  ```

  ```bash title="cURL" theme={null}
  # Replace these with your values
  ENVIRONMENT="<eu-or-us>"
  TENANT="<your-tenant-name>"
  TOKEN="<your-access-token>"

  curl -X POST "https://api.${ENVIRONMENT}.corti.app/v2/tools/coding/" \
    -H "Authorization: Bearer ${TOKEN}" \
    -H "Tenant-Name: ${TENANT}" \
    -H "Content-Type: application/json" \
    -d '{
      "system": ["meddra-en"],
      "context": [{"type": "text", "text": "Patient developed severe nausea and vomiting three days after starting metformin. Reported feeling dizzy and fatigued."}]
    }'
  ```
</CodeGroup>

[API reference →](/api-reference/codes/predict-codes)

## Language support

MedDRA prediction is available in seven languages, each with its own system identifier:

| Language | System identifier |
| :- | :- |
| English | `meddra-en` |
| German | `meddra-de` |
| Spanish | `meddra-es` |
| French | `meddra-fr` |
| Norwegian | `meddra-no` |
| Swedish | `meddra-se` |
| Italian | `meddra-it` |

<Note>
  MedDRA is in Beta because we do not have real-world benchmark datasets for it. The model has only been evaluated on synthetic data, and performance may not reflect real-world clinical trial or pharmacovigilance workflows. We encourage you to evaluate it against your own data and use case. If you notice anything that doesn't look right, please [let us know](https://www.corti.ai/contact-us?products=medical-coding,api) so we can improve it.
</Note>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.