AI-Augmented Risk Scoring in Cybersecurity Healthcare Software Testing

This paper presents a hybrid AI-enhanced risk scoring framework designed to improve the efficiency and effectiveness of software testing in modern healthcare systems. The proposed approach integrates artificial intelligence and machine learning to dynamically assess and prioritize risks, enabling smarter test case selection and execution strategies. Building on prior advancements in cybersecurity-integrated quality assurance (QA) for healthcare applications, this study introduces an ML-driven risk prioritization model within the software testing lifecycle. The model evaluates risk areas based on threat intelligence, historical defect patterns, and clinical task sensitivity, allowing for more accurate ranking of potential vulnerabilities. The framework was implemented and evaluated in a clinical task scheduling system, where it demonstrated significant reductions in undetected vulnerabilities and measurable improvements in compliance traceability and test coverage. These findings underscore the real-world applicability of AI-augmented approaches in secure healthcare software engineering and highlight their role in advancing quality assurance practices for critical systems.