Skip to main content
POST
/
tools
/
coding
/
Predict Codes
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",
    "cpt"
  ],
  "context": [
    {
      "type": "text",
      "text": "Short arm splint applied in ED for pain control."
    }
  ],
  "maxCandidates": 5
}'
{
  "codes": [
    {
      "system": "icd10cm",
      "code": "R1030",
      "display": "Lower abdominal pain, unspecified",
      "evidences": [
        {
          "contextIndex": 0,
          "text": "Example text mentioning lower abdominal pain"
        }
      ]
    }
  ],
  "candidates": [
    {
      "system": "icd10cm",
      "code": "R509",
      "display": "Fever, unspecified",
      "evidences": [
        {
          "contextIndex": 1,
          "text": "Example text mentioning fever"
        }
      ]
    }
  ]
}

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:

"copiloteu"

Body

application/json
system
enum<string>[]
required

List of coding systems for prediction

Required array length: 1 - 3 elements
Example:
["icd10cm", "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
maxCandidates
integer

Maximum number of code candidates to include in the response (per system).

Required range: 1 <= x <= 50

Response

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

codes
object[]
required

Highest confidence bundle of codes, preselected by the code prediction model

candidates
object[]
required

Full list of candidate codes as predicted by the model, rank sorted by model confidence

usageInfo
object

Credits consumed for this request.

I