Chiedozie, ChiamakaVuyyuru, Gayathri2026-01-132026-01-132025https://go.griffith.ie/handle/123456789/687This study investigates the integration of artificial intelligence (AI) and machine learning (ML) systems in regulatory compliance and audit processes within oncology clinical trials. Through a quantitative survey of 102 clinical research professionals, the research evaluates current adoption patterns, effectiveness, and challenges of AI/ML implementation in compliance monitoring. The findings reveal that while 47.1% of organizations currently use AI/ML tools for compliance, adoption remains fragmented and transitional. Natural Language Processing (19.6%) emerged as the most commonly used technology, primarily for documentation management. AI/ML systems demonstrated moderate effectiveness in detecting protocol deviations (28.4% rating them moderately effective) and reducing data discrepancies (46.1% reporting improvements). Risk assessment (28.4%) and compliance monitoring (28.4%) were identified as the most improved aspects following AI/ML adoption. However, significant barriers persist. Key challenges include data privacy concerns (23.5%), lack of regulatory clarity (21.6%), and technical complexity (20.6%). Only 41.2% of respondents believed their AI/ML tools were adequately validated for regulatory compliance, while 25.5% perceived these systems as lacking transparency. The study revealed role-based differences in perceptions, with technical professionals expressing greater confidence in AI/ML systems compared to regulatory and quality assurance staff. Despite demonstrable benefits in error reduction (63.7% reported decreased human error) and audit efficiency, only 32.4% of respondents recommended wider adoption. This cautious stance reflects ongoing concerns about validation standards, explainability, and regulatory acceptance. The research concludes that while AI/ML offers significant potential for enhancing oncology trial compliance, successful integration requires clearer regulatory frameworks, improved system transparency, and cross-functional alignment between technical and compliance teams. These findings provide crucial insights for organizations navigating the complex landscape of AI/ML adoption in regulated clinical research environments.Thesis