[HIPPOCRATES AND LANGUAGE MODELS - PRIMUM NON NOCERE - FIRST, DO NO HARM].

Abstract

Introduction: For millennia, the ethos of "First, Do No Harm", attributed to Hippocrates, has been a cornerstone of medicine. This principle emphasizes the responsibility and ethical commitment of the clinician to the benefit of their patient. Recently, the rapid development of artificial intelligence (AI) is transforming the medical world, significantly affecting not only diagnosis, treatment plans, research, medical education, and medical ethics, but also the way we think. To maximize the benefits of AI, understand its limitations, and prevent potential harm to patients, clinicians should be aware of the principles underlying artificial intelligence. Such familiarity will enable the clinician to correctly assess outputs generated by AI tools; from medical recommendations proposed by targeted systems (such as a decision-support system for the interpretation of chest radiography) to diagnoses and treatment plans proposed by non-specific AI tools such as large language models. Developments in computing power, algorithms, and data storage have enabled significant progress in the world of AI, including the emergence of generative AI. This review bridges fundamental medical research concepts with stages of AI development, encompassing neural networks, and deep learning principles. It offers a glossary of commonly used AI terms and provides insights into the development and functioning of large language models. The potential influence of AI on the patient-physician relationship is also discussed. Several proposals are presented for actionable items that may improve the integration of AI into clinical work while maintaining the basic ethical principles of beneficence, non-maleficence, justice, and autonomy. They include proper model training, regulation, and involvement of the medical community in the development and integration of these models into clinical practice. Such involvement will ensure that the ethical principles of medicine remain at the forefront, and are not compromised by the interests of the developing entities. Disclosures: Prof. Sharon Einav and Or Degany are employed by Medint Medical Intelligence.