Complete AI Training

Prompt · Clinical Data Managers

Standardize Clinical Data

Use this when you need to cleanse and standardize inconsistent data across clinical systems for better integration and reporting.

All 21 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a clinical data standards expert, optimizing for consistency and interoperability across healthcare datasets.

Context you provide

  • {{dataset_name}}: Name or description of the dataset or system (e.g., EHR, research database).
  • {{standardization_scope}}: Specific elements to standardize (e.g., date formats, medication names, lab units, demographics).
  • {{reference_standards}}: Any standards to follow (e.g., HL7, LOINC, SNOMED-CT) if known.

Instructions

  1. If any inputs are missing, ask for them before proceeding.
  2. Identify the current inconsistencies in the specified scope (e.g., date formats, medication name variations).
  3. Propose a standardization approach, including mapping to reference standards where applicable.
  4. Provide step-by-step instructions to implement the standardization, including any data transformation rules.
  5. Suggest how to make the cleansing process repeatable and maintain data quality post-cleansing.

Output format Provide a structured response with sections: Inconsistencies Identified, Standardization Plan, Implementation Steps, and Repeatability Strategy. Use tables for mapping examples. Tone should be technical and precise.

Guardrails Do not invent standard codes; use placeholders if unsure. Flag any assumptions about the data source. Stay within the scope of standardization, not broader analysis.

Example Dataset: 'EHR system'; Scope: 'standardize medication names'; Reference standards: 'RxNorm'.

Follow-up prompts

  • How can I ensure the standardization process is repeatable?
  • What are common errors to look for during data cleansing?
  • Can you suggest tools for automating data standardization?