Predict Codes

Predict medical codes from provided context.

This is a stateless endpoint, designed to predict ICD-10-CM, ICD-10-PCS, ICD-10-UK and CPT codes based on input text string or documentId.

More than one code system may be defined in a single request.

Code prediction requests have two possible values for context:
- text: One set of code prediction results will be returned based on all input text defined.
- documentId: Code prediction will be based on that defined document only.

The response includes two sets of results:
- Codes: Codes predicted by the model.
- Candidates: Lower-confidence codes the model considered potentially relevant but excluded from the predicted set.

All predicted code results are based on input context defined in the request only (not other external data or assets associated with an interaction).

POST /tools/coding

cURL

cURL

curl --request POST \
  --url https://api.{environment}.corti.app/v2/tools/coding/ \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'Tenant-Name: <tenant-name>' \
  --data '
{
  "system": [
    "icd10cm-outpatient",
    "cpt"
  ],
  "context": [
    {
      "type": "text",
      "text": "Short arm splint applied in ED for pain control."
    }
  ]
}
'

200

{
  "codes": [
    {
      "system": "icd10cm-outpatient",
      "code": "R1030",
      "display": "Lower abdominal pain, unspecified",
      "evidences": [
        {
          "contextIndex": 0,
          "text": "Example text mentioning lower abdominal pain",
          "start": 0,
          "end": 44
        }
      ],
      "alternatives": [
        {
          "code": "R1010",
          "display": "Upper abdominal pain, unspecified"
        },
        {
          "code": "R1032",
          "display": "Left lower quadrant pain"
        }
      ]
    }
  ],
  "candidates": [
    {
      "system": "icd10cm-outpatient",
      "code": "R509",
      "display": "Fever, unspecified",
      "evidences": [
        {
          "contextIndex": 1,
          "text": "Example text mentioning fever",
          "start": 0,
          "end": 29
        }
      ],
      "alternatives": [
        {
          "code": "R502",
          "display": "Drug induced fever"
        },
        {
          "code": "R5082",
          "display": "Postprocedural fever"
        }
      ]
    }
  ],
  "usageInfo": {
    "creditsConsumed": 123
  }
}

Authorizations

Authorization · string · header · required

Input your token

Headers

Tenant-Name · string · required

Identifies a distinct entity within Corti's multi-tenant system. Ensures correct routing and authentication of the request.

Example:

"base"

Body

application/json

system · enum<string>[] · required

List of coding systems for prediction

Required array length: 1 - 8 elements

Available options: icd10cm-inpatient, icd10cm-outpatient, icd10pcs, cpt, icd10int-inpatient, icd10int-outpatient, icd10uk-inpatient, icd10uk-outpatient

Example:

["icd10cm-outpatient", "cpt"]

context · (Text · object | DocumentID · object)[] · required

Select either text or documentId as input context to the model for code prediction. Evidence indices in the response map to this array.

Text

DocumentID

Show child attributes

filter · object

Optional filter to restrict predicted codes.

Show child attributes

Response

200

application/json

List of predicted codes and candidate codes per system defined in the request, including evidence supporting the code prediction.

codes · object[] · required

Codes predicted by the model.

Show child attributes

candidates · object[] · required

Lower-confidence codes the model considered potentially relevant but excluded from the predicted set.

Show child attributes

usageInfo · object · required

Credits consumed for this request.

Show child attributes