Current applications and challenges in large language models for patient care: a systematic review

The introduction of large language models (LLMs) into clinical practice promises to improve patient education and empowerment, thereby personalizing medical care and broadening access to medical knowledge. Despite the popularity of LLMs, there is a significant gap in systematized information on their use in patient care. Therefore, this systematic review aims to synthesize current applications and limitations of LLMs in patient care. We systematically searched 5 databases for qualitative, quantitative, and mixed methods articles on LLMs in patient care published between 2022 and 2023. From 4349 initial records, 89 studies across 29 medical specialties were included. Quality assessment was performed using the Mixed Methods Appraisal Tool 2018. A data-driven convergent synthesis approach was applied for thematic syntheses of LLM applications and limitations using free line-by-line coding in Dedoose. We show that most studies investigate Generative Pre-trained Transformers (GPT)-3.5 (53.2%, n = 66 of 124 different LLMs examined) and GPT-4 (26.6%, n = 33/124) in answering medical questions, followed by patient information generation, including medical text summarization or translation, and clinical documentation. Our analysis delineates two primary domains of LLM limitations: design and output. Design limitations include 6 second-order and 12 third-order codes, such as lack of medical domain optimization, data transparency, and accessibility issues, while output limitations include 9 second-order and 32 third-order codes, for example, non-reproducibility, non-comprehensiveness, incorrectness, unsafety, and bias. This review systematically maps LLM applications and limitations in patient care, providing a foundational framework and taxonomy for their implementation and evaluation in healthcare settings. Large language models (LLMs) are computer programs that can generate human-like text. They promise to improve patient education and expand access to medical information by helping patients better understand health conditions and treatment options. However, more information is needed about how these tools are used in patient care and the challenges they present. In this review, researchers analyzed 89 studies from 2022 to 2023 covering 29 medical specialties. These studies explored ways LLMs are used: for example, answering patient questions, summarizing or translating medical texts, and supporting clinical paperwork. While these tools show potential, the review highlights limitations. Many LLMs are not optimized for medical use, lack transparency about data use, and can be difficult for some users to access. Additionally, the text they generate may sometimes be inaccurate, incomplete, or biased, raising safety concerns. Busch et al. discuss large language models in patient healthcare. This systematic review analyzes current literature for utilization of these models and limitations of use and implementation.