Alexandra Maertens ¹ Steve Brykman ² Thomas Hartung ^1,3 Andrei Gafita ⁴ Harrison Bai ⁵ David Hoelzer ⁶ Ed Skoudis ⁶ Channing Judith Paller ^7*

• ¹ Bloomberg School of Public Health, Johns Hopkins University, Baltimore, Maryland, United States
• ² GYN Studios, Boston, United States
• ³ University of Konstanz, Konstanz, Baden-Württemberg, Germany
• ⁴ Johns Hopkins Medicine, Johns Hopkins University, Baltimore, Maryland, United States
• ⁵ Department of Radiology and Radiological Sciences, The Johns Hopkins Hospital, Johns Hopkins Medicine, Baltimore, Maryland, United States
• ⁶ SANS Institute, Rockville, United States
• ⁷ Department of Oncology, Johns Hopkins Medicine, Johns Hopkins University, Baltimore, Maryland, United States

In response to the increasing significance of artificial intelligence (AI) in healthcare, there has been increased attention -including a Presidential executive order to create an AI Safety Institute -to the potential threats posed by AI. While much attention has been given to the conventional risks AI poses to cybersecurity, and critical infrastructure, here we provide an overview of some unique challenges of AI for the medical community. Above and beyond obvious concerns about vetting algorithms that impact patient care, there are additional subtle yet equally important things to consider: the potential harm AI poses to its own integrity and the broader medical information ecosystem. Recognizing the role of healthcare professionals as both consumers and contributors to AI training data, this article advocates for a proactive approach in understanding and shaping the data that underpins AI systems, emphasizing the need for informed engagement to maximize the benefits of AI while mitigating the risks.Just days after President Biden signed an executive order to protect against threats posed by AI, Vice President Harris announced the formation of an AI Safety Institute, noting that AI also has the potential to cause profound harm. So far, most of the discussion around AI safety has focused around the most obvious risks in areas of biotechnology, cybersecurity, and critical infrastructure (Biden, 2023). However, there are several risks of AI that are unique to the medical community. Cybersecurity threats are already an issue for health care delivery and have already negatively impacted patient care (Neprash et al., 2023). Even cyberattacks that do not adversely impact patient care are costly -for example, the Irish National Orthopedic Register was able to avoid impacting patient care by reverting to a paper-only system, but at a cost of 2850 additional person-hours for data reconciliation. (Russell et al., 2023) The frequency and Style Definition: Normal (Web)