An Advanced Knowledge-Based Expert System for Clinical Diagnosis and Species Classification of Malaria: A Neural-Logic Engineering Approach

Title: An Advanced Knowledge-Based Expert System for Clinical Diagnosis and Species Classification of Malaria: A Neural-Logic Engineering Approach Author: Dr. Mustafa Omer Shoieb Mohammed Overview: This research presents a high-precision Knowledge-Based Expert System (KBES) for the automated differential diagnosis of malaria species (P. falciparum, P. malariae, P. vivax, and P. ovale). It bridges the gap between clinical morphology and symbolic reasoning to provide a robust decision-support tool for tropical medicine. Technical Architecture: Inference Engine: Developed using Prolog (Logic Programming), employing Backward Chaining to simulate specialist-level deductive reasoning. § - Knowledge Engineering: Integrates clinical symptoms, fever cycles, and laboratory biomarkers (BFFT/ICT) into a modular production rule-based framework. § - Neural-Logic Integration: Utilizes heuristic weighting and the Warren Abstract Machine (WAM) architecture to ensure rapid, auditable, and transparent diagnostic paths. Key Contributions: Achieved expert-level diagnostic correlation through precise classification of morphological features (e.g., Maurer’s dots). § - Standardized treatment protocols through automated, rule-based logic. § -Scalable "Digital Guardian" framework optimized for resource-limited clinical environments.