A Diagnosis and Treatment of Liver Diseases: Integrating Batch Processing, Rule-Based Event Detection and Explainable Artificial Intelligence

Medical guidelines ensure trustworthy AI decisions: The system was built using rules derived from the National Viral Hepatitis Control Program (NVHCP) guidelines rather than purely data-driven approaches, making the diagnostic recommendations more aligned with established medical standards and easier for clinicians to validate.

Explainability is central to clinical AI: The researchers specifically integrated Explainable Artificial Intelligence (XAI) into their system, allowing doctors to understand why the AI made specific diagnostic suggestions rather than treating it as a "black box"—a critical requirement for responsible deployment in healthcare settings.

Transparent rule-based reasoning over opaque machine learning: By converting medical guidelines into explicit, interpretable rules (using SWRL) rather than relying solely on complex machine learning models, the system provides clear decision pathways that clinicians can audit, challenge, and explain to patients.

Batch processing enables systematic oversight: The use of Apache Jena framework for batch processing rule-based event detection allows healthcare institutions to review diagnostic recommendations systematically before they reach patients, rather than making real-time decisions without oversight.

Ontology-based design supports accountability: By structuring patient data and medical knowledge using formal ontologies (BFO and PCD), the system creates a standardized, documented representation of how medical concepts relate to each other, making it easier to identify and correct potential biases or errors in the AI system.