Regulating Artificial Intelligence in Clinical Medicine: Governance Framework Principles for Safe and Accountable Implementation

Abstract

Artificial intelligence (AI) is transforming the field of clinical medicine at a fast rate. AI is being used in the field of clinical medicine in areas such as diagnostic imaging, prediction, documentation, and large language model-based clinical reasoning tools such as ChatGPT. Algorithm-based triage tools are also being used in clinical settings such as hospitals. Radiology departments are also using AI-based detection tools. However, the rate at which AI is transforming the field of clinical medicine is much higher than the rate at which the regulatory bodies are keeping pace with the developments in the field. Even though the Food and Drug Administration (FDA) has developed a pathway to regulate AI-based Software as a Medical Device (SaMD) and machine learning-based technologies, the current system that is in place to ensure the safety and efficacy of these technologies was developed to ensure the safety and efficacy of static technologies and not those that have the capability to learn. The rate at which AI is being incorporated in the field of clinical medicine is much higher than the rate at which these technologies are being regulated. The issue of clinical AI governance is not about the regulation of AI; it is about patient safety. This article outlines the need for a structured framework of five principles of safety, accountability, fairness, explainability, and adaptive oversight.