Matic Zadobov\u0161ek, Primo\u017e Kocuvan and Matja\u017e Gams<\/p>\n
Abstract<\/strong>
The escalating workload demands on healthcare professionals
are leading to systemic overload, resulting in a decline in the
efficiency of public health services. This situation necessitates
the development of solutions that can alleviate the burden on
physicians while ensuring comprehensive patient care. Recent
advancements in generative artificial intelligence, particularly
in the field of medicine, have demonstrated that large language
models (LLMs) can outperform doctors in specific tasks, high-
lighting their potential as valuable tools for reducing the strain
on healthcare providers. This study focuses on the development
of the HomeDOCtor application, which integrates additional val-
idated medical knowledge into the GPT-4o LLM. The objective of
this application and the enhanced LLM is to offer users reliable
access to a medical chatbot capable of providing accurate and
timely responses to health-related inquiries. The chatbot\u2019s be-
havior has been meticulously tested and refined in collaboration
with a team of physicians. The findings of this research offer
insights into the development of such systems and explore their
potential application within the Slovenian healthcare system.<\/p>\n\n\n\n