LatticeMLS
Menu

Module GLP-37 · Version 1.0

Using Large Language Models Safely in Laboratory Workflows

A working guide to using approved generative-AI tools for low-risk laboratory tasks: how to classify a use case by risk, what may and may not go into a prompt, how to catch a fabricated citation or number before it reaches a colleague, and how to build a defensible human-review and audit trail.

Your next section

Start section 1

Read without an account. Sign in to save.

Who this module is for

Medical laboratory scientists, laboratory technicians, and trainees who have access to an institutionally approved generative-AI tool and need to know what it may and may not be used for.

Learning objectives

  • Classify a proposed AI use case by patient, analytical, regulatory, privacy, and automation risk
  • Write a prompt that requests a source-backed, bounded output without entering PHI, proprietary methods, credentials, or confidential event data
  • Verify a generated claim, calculation, citation, or procedure against a primary source or a local controlled document before it is used

How completion works

Mark every required section done and answer every knowledge check in those sections correctly. The final save completes the module automatically.

Sources

15 sources

  1. 1. NIST. Artificial Intelligence Risk Management Framework (AI RMF 1.0), NIST AI 100-1. January 2023.

    Source note · federal guidance

  2. 2. NIST. Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile, NIST AI 600-1. July 26, 2024.

    Source note · federal guidance

  3. 3. FDA. Artificial Intelligence-Enabled Medical Devices, list page, updated periodically.

    Source note · federal guidance

  4. 4. FDA. Clinical Decision Support Software: Guidance for Industry and Food and Drug Administration Staff. Final guidance, January 2026.

    Source note · federal guidance

  5. 5. FDA. Marketing Submission Recommendations for a Predetermined Change Control Plan for Artificial Intelligence-Enabled Device Software Functions. Final guidance, August 2025.

    Source note · federal guidance

  6. 6. HHS Office for Civil Rights. Guidance on HIPAA & Cloud Computing; Is a Software Vendor a Business Associate? FAQ; 45 CFR 164.312 Technical safeguards; 45 CFR 164.504 Organizational requirements (eCFR).

    Source note · federal regulation

  7. 7. ISO. ISO/DIS 24051-1, Medical laboratories - Part 1: General principles for the application of artificial intelligence in medical laboratories. Draft status record.

    Source note · consensus standard

  8. 8. Chen A, et al. "Accuracy of Chatbots in Citing Journal Articles." JAMA Network Open. 2023;6(8):e2327647.

    Source note · peer-reviewed literature

  9. 9. "Evaluation and Comparison of Ophthalmic Scientific Abstracts and References by Current Artificial Intelligence Chatbots." JAMA Ophthalmology. 2023.

    Source note · peer-reviewed literature

  10. 10. Albert C. "Working out AI validation and implementation." CAP TODAY. December 2025.

    Source note · professional society guidance

  11. 11. Clarke B, Bunch D, Pagaduan J, Schuler E, Tacker D, Wiencek J. "Artificial Intelligence in Laboratory Medicine." ADLM Policy Report. July 10, 2026.

    Source note · professional society guidance

  12. 12. College of American Pathologists. Laboratory General Checklist, requirement GEN.43875 (autoverification validation), with CLSI AUTO10-A and AUTO15-Ed1:2019 references.

    Source note · accreditation standard

  13. 13. 42 CFR 493.1250, 493.1253, 493.1256, 493.1407 (Cornell LII eCFR text); CMS QSO-25-10 CLIA interpretive guidance.

    Source note · federal regulation

  14. 14. Goddard K, Roudsari A, Wyatt JC. "Automation bias: a systematic review of frequency, effect mediators, and mitigators." J Am Med Inform Assoc. 2012;19(1):121-127.

    Source note · peer-reviewed literature

  15. 15. CLSI. Collection of Diagnostic Venous Blood Specimens, PRE02, 8th edition. February 2025. Replaces GP41/H3.

    Source note · consensus standard