Application of the EXPERT consultation system to accelerated laboratory testing and interpretation

Area of Science:

• Medical Informatics
• Artificial Intelligence in Medicine
• Clinical Laboratory Science

Background:

• Laboratory testing interpretation can be complex, requiring sequential analysis of multiple parameters.
• Conventional programming methods may not efficiently handle complex rule-based diagnostic systems.
• Optimizing laboratory resource utilization is crucial for cost-effective healthcare.

Purpose of the Study:

• To develop and evaluate an AI-based laboratory consultation system for sequential testing and interpretation.
• To enhance the efficiency of laboratory diagnostics using a knowledge-based system.
• To demonstrate the application of the EXPERT system-building tool in a clinical setting.

Main Methods:

• Utilized the EXPERT consultation system-building tool, a knowledge-based AI program.
• Developed a system that requests specific secondary and tertiary tests based on initial results.
• Employed a hierarchical network of rules for interpreting collected laboratory findings.

Main Results:

• The system effectively facilitated sequential laboratory testing and interpretation for outpatients.
• Implementation led to maximized effective use of laboratory resources and elimination of unnecessary tests.
• The AI system provided patients with low-cost laboratory information.

Conclusions:

• AI-driven consultation systems can significantly improve the efficiency and cost-effectiveness of laboratory diagnostics.
• The EXPERT system provides an efficient production system for complex rule-based interpretations.
• This approach optimizes laboratory workflows and enhances patient care through accessible data.