The ability of large language models (LLMs) to transform, interpret, and comprehend vast quantities of heterogeneous data presents a significant opportunity to enhance data-driven care delivery. However, the sensitive nature of protected health information (PHI) raises valid concerns about data privacy and trust in remote LLM platforms. In addition, the cost associated with cloud-based artificial intelligence (AI) services continues to impede widespread adoption. To address these challenges, we propose a shift in the LLM execution environment from opaque, centralized cloud providers to a decentralized and dynamic fog computing architecture. By executing open-weight LLMs in more trusted environments, such as the user's edge device or a fog layer within a local network, we aim to mitigate the privacy, trust, and financial challenges associated with cloud-based LLMs. We further present SpeziLLM, an open-source framework designed to facilitate rapid and seamless leveraging of different LLM execution layers and lowering barriers to LLM integration in digital health applications. We demonstrate SpeziLLM's broad applicability across six digital health applications, showcasing its versatility in various healthcare settings.

The healthcare sector, particularly tertiary-care hospitals, face an ever-increasing amount of pressure due to evolving demands aided by the growing population and unforeseen pandemics. Mounting healthcare needs directly impact patients' overall experience; including prolonged waiting periods, delayed appointments, mired level of services, and hindered ability to provide proper care. With the unprecedented global health crisis we have faced in recent years, the international healthcare system has been pushed to reform and transform. In this light, artificial intelligence (AI) and emerging technology have become increasingly prevalent, propelling efforts to improve patient care, solutions, and overall healthcare outcomes. Furthermore, the wider acceptance, and even promotion of smart technology, amongst clinicians, as a tool for informed clinical decisions has helped streamline operations, improve outcomes, and improve patient and staff satisfaction.

There are several established healthcare companies and startups in the Femtech space, which use disruptive technology including artificial intelligence, machine learning, big data, and the Internet of Things to develop interactive digital health applications for women's health. The majority of spending on other diseases has a male-specific research focus and this is separate from the research spending on male-specific conditions such as prostate cancer, which accounts for 2% of overall funding. Yet women today make up 49.6% of the total population and the economic burden for women's diseases is currently more than $500 billion. Additionally, with healthcare increasingly becoming personalized and patient-centric, now is the time to address the fundamental question of whether care delivery and management should be gender neutral. For several decades, healthcare products and solutions were designed, developed, and delivered without much attention to the fact that healthcare needs are different for men and women, considering their physiological differences.