A method for the quantification of the decision-making process in a computer-oriented medical world

Area of Science:

• Medical Informatics
• Artificial Intelligence in Medicine
• Clinical Decision Support Systems

Background:

• Computer-oriented medical records are increasingly used in clinical settings.
• Effective decision-making support is crucial for accurate medical diagnoses.
• Existing diagnostic methods may not fully capture the complexity of clinical reasoning.

Purpose of the Study:

• To propose an original approach for enhancing decision-making within computer-based medical records.
• To develop and evaluate novel algorithms for differential diagnosis in general medicine.
• To compare the performance of new algorithms against physician decisions and Bayes Rule.

Main Methods:

• Implementation of two distinct algorithms: one based on symbolic reasoning with score variables (AI-related).
• Development of a second algorithm utilizing fuzzy-set theory to handle qualitative expressions.
• Comparative analysis of algorithm performance, physician judgment, and Bayes Rule in a hospital setting.

Main Results:

• The study introduces and compares AI and fuzzy-set algorithms for medical decision support.
• Performance evaluation of the proposed algorithms against established methods is conducted.
• The algorithms demonstrate potential for capturing complex diagnostic reasoning steps.

Conclusions:

• The developed algorithms offer a promising approach to computer-assisted medical decision-making.
• The implementation is suitable for departmental use and educational purposes in hospitals.
• Further research is needed to address parameter sensitivity in advanced diagnostic steps.