GenAI in healthcare: technologies, applications and evaluation

Generative Artificial Intelligence (GenAI) is a relatively new type of Artificial Intelligence (AI), capable of generating text, images, videos, and other data or content. GenAI has captured massive global attention thanks to the remarkable success of tools like ChatGPT, Google Gemini, Claude, and DeepSeek. It is already having a profound and transformative impact in entertainment industries such as gaming, movies, literature and music and all other key industries such as finance, marketing, retail and software. In healthcare, GenAI is being applied as well to automate administration, assist in clinical decision-making, and personalize patient care. Seemingly permitted under strict regulatory conditions, it can help healthcare providers by writing summaries of radiology and pathology reports or electronic health records (EHRs), creating patient-facing chatbots empowered with the latest medical knowledge, creating synthetic data based on privacy-sensitive real data, and much more. In this Research Topic, we have created an overview of applications and evaluations of GenAI in healthcare, using, for example, large language/vision models (LLMs/LVMs), generative adversarial networks (GAN) and retrieval-augmented generation (RAG). We present several examples of successful implementations and evaluations of GenAI in healthcare, and its way toward deployment, but, since this area of research is developing fast, we also look at its possibilities and necessities in the (near) future. As healthcare has a high stake in patient safety, privacy and diagnostic accuracy, some manuscripts also discuss risks and pitfalls around GenAI in healthcare, and the possible solutions for these issues.