Objective:

To explore how AI can enhance not only diagnostic accuracy but also the organization, documentation, and sustainability of pathology workflows, particularly addressing non-diagnostic challenges.

Key Findings:

• Traditional LIS models led to inefficiencies, including duplicated work and delays in report processing.
• AI integration transformed documentation from free text to structured information, improving data reuse and workflow efficiency, particularly through real-time analysis.
• The new LIS eliminated the need for manual transcription, allowing pathologists to review and release reports directly, enhancing turnaround times.

Interpretation:

The integration of AI into LIS can significantly streamline pathology workflows, addressing bottlenecks that arise from traditional documentation practices and structural limitations.

Limitations:

• The study is based on a single institution's experience, which may not be generalizable to all pathology laboratories.
• Potential challenges in AI implementation and user adaptation, such as training and system integration, were not extensively addressed.

Conclusion:

AI has the potential to reshape pathology workflows by enhancing documentation processes and reducing backlogs, ultimately improving clinical communication and efficiency, while addressing structural inefficiencies.