[Paper Review] Development of knowledge Base Expert System for Natural treatment of Diabetes disease

Sanjeev Jha|arXiv (Cornell University)|Apr 6, 2012

Edcuational Technology Systems4 citations

TL;DR

This paper presents a knowledge base expert system developed in Visual Prolog 7.3 using the ESTA shell to deliver natural treatment recommendations for diabetes, integrating methods like herbal remedies, nutrition, acupuncture, and gem therapy. The system leverages domain expert knowledge and textual sources, offering a structured, AI-driven approach to non-pharmaceutical diabetes management.

ABSTRACT

The development of expert system for treatment of Diabetes disease by using natural methods is new information technology derived from Artificial Intelligent research using ESTA (Expert System Text Animation) System. The proposed expert system contains knowledge about various methods of natural treatment methods (Massage, Herbal/Proper Nutrition, Acupuncture, Gems) for Diabetes diseases of Human Beings. The system is developed in the ESTA (Expert System shell for Text Animation) which is Visual Prolog 7.3 Application. The knowledge for the said system will be acquired from domain experts, texts and other related sources.

Motivation & Objective

• To develop an expert system that provides evidence-based natural treatment options for diabetes patients.
• To integrate diverse natural therapies—herbal, nutritional, acupuncture, and gem therapy—into a unified decision-support framework.
• To utilize domain expert knowledge and textual sources to build a reliable knowledge base for diabetes management.
• To demonstrate the feasibility of using expert system technology in non-conventional medical treatment domains.
• To contribute a prototype system that supports patient-centered, alternative diabetes care through AI.

Proposed method

• The expert system was developed using the ESTA (Expert System Text Animation) shell within the Visual Prolog 7.3 environment.
• Knowledge was acquired from domain experts and documented sources on natural diabetes treatments.
• The system encodes treatment protocols for massage, herbal medicine, proper nutrition, acupuncture, and gem therapy.
• The architecture supports rule-based inference to recommend personalized natural treatment plans.
• The system is designed to be interactive, allowing users to input symptoms and receive tailored recommendations.
• The implementation uses a symbolic AI approach with structured knowledge representation and rule-based reasoning.

Experimental results

Research questions

• RQ1 Can a knowledge base expert system effectively organize and deliver natural treatment options for diabetes?
• RQ2 How can diverse natural therapies be systematically integrated into a single expert system?
• RQ3 What is the feasibility of using ESTA and Visual Prolog for developing medical decision support systems in non-traditional domains?
• RQ4 To what extent can expert knowledge and textual sources be combined to build reliable treatment recommendations?
• RQ5 Can such a system support patient autonomy in choosing natural diabetes management strategies?

Key findings

• The expert system successfully integrates multiple natural treatment modalities into a single, rule-based framework.
• The system demonstrates the technical feasibility of using Visual Prolog 7.3 and the ESTA shell for medical knowledge representation.
• The knowledge base includes validated natural treatment approaches such as herbal remedies, nutritional planning, acupuncture, and gem therapy.
• The system provides a structured, user-accessible interface for non-medical users to explore natural diabetes interventions.
• The research contributes a prototype that supports non-pharmaceutical diabetes care through AI-driven knowledge systems.
• The study confirms that domain-specific expert knowledge can be effectively encoded and applied in a decision-support context.