Related Experiment Video
Updated: Jun 10, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
The Potential of Using Generative AI/NLP to Identify and Analyse Critical Incidents in a Critical Incident Reporting
Carlos Ramon Hölzing1, Sebastian Rumpf1, Stephan Huber2
1Department of Anaesthesiology, Intensive Care, Emergency and Pain Medicine, University Hospital Würzburg, Oberdürrbacher Str. 6, 97080 Würzburg, Germany.
Generative Artificial Intelligence and Natural Language Processing (AI/NLP) show potential in analyzing Critical Incident Reporting Systems (CIRS) cases, performing comparably to human reviewers. This technology can help improve healthcare patient safety by enhancing incident reporting analysis.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Patient Safety Research
Background:
- Underreporting in Critical Incident Reporting Systems (CIRS) hinders healthcare patient safety.
- Evaluating novel methods for analyzing CIRS data is crucial for improving reporting systems.
Purpose of the Study:
- To assess the effectiveness of generative AI/NLP in reviewing CIRS cases.
- To compare AI/NLP performance against human reviewers in analyzing CIRS data.
- To determine AI/NLP's capability in categorizing CIRS cases into relevant topics.
Main Methods:
- A case-control feasibility study utilized German CIRS-Anaesthesiology cases.
- Cases were reviewed by both human experts and an AI/NLP model (ChatGPT-3.5).
- Two independent CIRS experts blindly assessed review quality using Likert scales.
Main Results:
- Human experts misclassified 45.8% of AI reviews as human-generated.
- AI and human reviews showed comparable performance in linguistic quality, expertise, logical derivability, and overall quality (p > 0.39).
- The AI model successfully categorized cases into relevant topics autonomously.
Conclusions:
- Generative AI/NLP demonstrates significant potential for analyzing and categorizing CIRS cases.
- AI/NLP application in CIRS analysis could enhance healthcare incident reporting.
- Further research is needed to validate and broaden these findings.
Related Concept Videos
Types of Reports II: Incident or Occurrence Report
Purposes:
In the healthcare industry, reports play a crucial role in documenting incidents within an agency. The primary objective of these reports is to ensure patient safety, uphold the...
Nursing Clinical Information System
A Nursing Clinical Information System (NCIS) is a specialized type of healthcare information system tailored to meet the unique needs of nursing practice. It incorporates the principles of nursing informatics to streamline information management and improve the quality of care delivery.
Critical attributes of NCIS include:
Steps in Outbreak Investigation
Critical Thinking I
Patient-centered Care
Critical Thinking II

