Pre-operative fear of falling is associated with worse 3-year mobility and quality of life in elderly hip fracture patients: a post-hoc analysis of a prospective cohort.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that profoundly impairs memory and cognition []. As the global burden of AD rises, large-scale studies have generated multi-modal data across neuroimaging, genomics, and clinical domains []. These datasets have revealed key biomarkers and mechanisms of AD, yet efficiently integrating the massive literature and databases remains challenging. Information retrieval (IR) is an important tool that focuses on the identification and extraction of relevant information from vast datasets or document collections []. In the context of AD research, IR plays a pivotal role by enabling efficient access to critical data, thereby supporting a wide array of research applications. For instance, IR facilitates the retrieval of biomarker data, such as beta-amyloid plaque levels or tau protein concentrations, which provide valuable insights into disease mechanisms and enhance early diagnostic capabilities []. Additionally, IR is instrumental in accessing medical imaging data from repositories, allowing researchers to track and analyze patterns of brain atrophy and functional changes over time []. Furthermore, IR aids in identifying genetic studies [], which could include those investigating APOE polymorphisms, which are strongly linked to AD risk. Therefore, IR is essential for navigating the growing body of AD research, ensuring that crucial data is accessible for advancing our understanding and treatment of AD. Large Language Models (LLMs) are advanced tools in natural language processing (NLP) that have demonstrated remarkable capabilities across various domains. These models, such as the GPT (Generative Pre-trained Transformer) series and Llama, are designed to understand and generate human-like text, which makes them particularly effective for addressing challenges in IR []. In particular, LLM-based IR can streamline the process of retrieving complex biomedical databases, such as clinical records that focus on the relationships between various phenotypes and genotypes, making it an invaluable tool for AD researchers []. Although LLMs have demonstrated broad applicability in IR within the medical domain [–], they also exhibit several critical limitations. One of the most significant concerns is their propensity for hallucination, a phenomenon in which models generate responses that appear confident yet are factually incorrect or nonsensical []. This issue becomes particularly pronounced in tasks requiring domain-specific expertise, such as medical and legal inquiries, where LLMs frequently produce fabricated information presented with unwarranted certainty []. Beyond hallucination, LLMs often fall short in providing depth and comprehensiveness, particularly in specialized contexts. While models like ChatGPT can generate largely accurate responses, they are frequently criticized for their lack of nuanced understanding. For instance, in the field of epilepsy, LLM-generated content is often superficial, failing to capture the intricacies of the condition []. Similarly, in genetics, empirical evaluations suggest that ChatGPT’s performance is comparable to that of human respondents, offering no clear advantage in accuracy or insight []. These limitations largely stem from the models’ constrained exposure to medical-domain knowledge and their inherent difficulty in navigating the complexities of clinical reasoning.