Clinical data quality checks

Step 01

Define and Align

Upload sample data, define your output schema, and provide feedback on the hardest cases.

Output schema

ReviewYes / No: Whether the record contains a consistency issue requiring review.
true
false
Issue typesChoose any: The consistency problems found; empty when none.
unit_mismatch
date_conflict
missing_value
source_disagreement
Affected fieldsList of values: Field names that need correction or verification.

app.sutro.sh/functions/clinical-data-quality-checks

Collecting feedback · 1/3

Flag consistency problems in synthetic clinical records for review.

Example 1 of 3

Unit mismatch

Model input

Synthetic record: height_cm = 1.75; source says height 1.75 meters.

Model output

Review

Issue typesMultiple values

Affected fieldsMultiple values

Why? Optional guidance

Step 02

Model Sweep

Compare quality and cost on your examples, then choose a model or use Sutro’s default.

Compare models on expert agreement and cost. The interactive chart uses illustrative measurements.

Illustrative sweep · select Value or Best to use that model in your function.

Step 03

Deployment

Call Sutro Functions like any other software. Swap the model as soon as something more performant is released.

Selected modelWaiting for sweep results.

Real-time

import sutro as so

input_data = {
    "text": "Synthetic record: height_cm = 1.75; source says height 1.75 meters."
}

result = so.run_function(
    "clinical-data-quality-checks",
    input_data,
)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/clinical-data-quality-checks/run" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "text": "Synthetic record: height_cm = 1.75; source says height 1.75 meters."
  }
}'

Batch

import sutro as so

job_id = so.batch_run_function(
    name="clinical-data-quality-checks",
    data="clinical_data_quality_checks.csv",
)
results = so.await_job_completion(job_id)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "clinical-data-quality-checks",
  "inputs": [
    {
      "text": "Synthetic record: height_cm = 1.75; source says height 1.75 meters."
    }
  ]
}'