Digital Quality Metrics and AI/ML Analytics: Building a Continuous-Improvement Framework that Aligns with Regulatory Expectations

The life science industries, including pharmaceutical, medical device, biotechnology, biological, and tobacco and tobacco-related products continue to embrace new technology to improve delivery of quality products in compliance with FDA. Artificial Intelligence (AI), Machine Learning (ML) and Large Language Models (LLMs), such as ChatGPT are beginning to find a presence at these companies. As the pace of technological innovation becomes more intense, there is a critical need for computer system validation, 21 CFR Part 11 (Electronic Records and Electronic Signatures) compliance, and data integrity assurance to continue in environments where AI and ML are becoming more prevalent. Using real-time digital quality signals for metrics will optimize efficiency, quality, and compliance. AI/ML can be used to detect trends, deviations, anomalies, and drift early in a process, enabling quicker action to mitigate potential risk. Dashboards built for AI/ML tools support data integrity in metrics pipelines and aggregation layers, and also support Part 11 compliance and risk-based decision-making. The analytics can ultimately plug into the SDLC and GAMP®5 (Second Edition) control strategy. AI can hallucinate, and show bias and performance drift — AI solutions need human guardrails and expert oversight to make the right judgment calls for better outcomes and quality decisions. We'll provide an overview of validation, including CSV and Computer Software Assurance (CSA), and the latest GAMP®5, 2nd Edition that aligns with CSA, walking you through the Software Validation and Maintenance approach that will bring clarity to what FDA is looking for in terms of compliance. Code: FDB2847