Utilization of a HIPAA-compliant large language model chatbot in an academic pediatric medical center.

Abstract

Despite growing interest in LLM chatbots, little evidence exists on usage patterns in hospital systems. This paper presents a mixed-methods case study of "InternalGPT," a HIPAA-compliant LLM chatbot made available to employees of the institution. Survey responses and 14 months of system utilization data were analyzed across diverse professional roles in the institution. Of approximately 15,800 hospital employees, 2,149 (13.6%) requested InternalGPT access. Motivations for sign-up aligned with professional roles: operations professionals prioritized administrative automation, clinicians focused on clinical augmentation, and scientists on research and coding. Among InternalGPT users, 52.8% recorded at least one token use; 33.6% never logged-in, and 13.7% logged-in but never used the tool. The top 20% of users consumed 69.4% of tokens. Key barriers to engagement among non-users included limited time for exploration (51.4%) and difficulty using (21.8%), integrating (15.5%), or accessing (9.2%) InternalGPT. Among a small group of employees with sustained InternalGPT use (n = 461), a subset who responded to a self-report survey (n = 92) indicated a mean productivity gain of 30%, corresponding to an exploratory perceived productivity value of $6.3M to $18.9M under varying extrapolation assumptions. Although most hospital employees never used the HIPAA-compliant LLM chatbot, a small minority who utilized it regularly reported substantial productivity improvements, highlighting both the value proposition of LLMs in healthcare and potential for increased engagement. Implementation and knowledge challenges were more frequently cited than AI-feature and performance concerns as key barriers to adoption. These findings underscore that successful LLM implementation in healthcare hinges not only on advanced AI technology, but also on robust system capacity building including investments in user education and technical integration.