Integrating Large Language Models into Clinical Decision Support Systems: A Novel Approach to UTI Diagnosis and Treatment

Abstract

Background:
Urinary tract infections (UTIs) are among the most common bacterial infections globally, leading to significant healthcare expenditures and frequent misdiagnoses. In the U.S., UTIs account for approximately 380,600 preventable adult inpatient stays annually, costing $2.55 billion. Current Clinical Decision Support Systems (CDSS) are often static, lack personalized recommendations, and do not incorporate real-time clinician feedback. AI-driven CDSS, leveraging large language models (LLMs), offer the potential to enhance diagnostic precision, optimize antibiotic use, and improve workflow efficiency. While existing systems remain limited in adaptability and clinician engagement, the concept demonstration prototype system offers superior adaptability and capability.

Methods:                                                                                                       
We developed 3RDI, an AI-driven CDSS for UTI management, utilizing the DETNQ (Diagnosis, Evidence, Treatment Plan, Notes, Quality) framework to structure outputs. The system was trained on a comprehensive UTI dataset including patient medical history, symptoms, lab results, and medication records. 3RDI integrates a day-wise iterative process for continuous feedback, allowing clinicians to refine the system's recommendations. The model is being evaluated through pilot implementations integrated with Epic EHR, focusing on metrics such as diagnostic accuracy, time-to-treatment, and clinician satisfaction.

Findings:
While a complete clinical evaluation remains pending, initial development showcases the feasibility of integrating an adaptable, clinician-driven feedback mechanism within the CDSS. The system demonstrated effective structuring of patient data in the DETNQ format and adaptability to specific clinical contexts. Preliminary results suggest the potential for reduced diagnostic errors, optimized resource utilization, and enhanced clinical workflow efficiency. The iterative design allows clinicians to tailor recommendations to institutional practices, fostering greater trust and system usability.

Interpretation:
3RDI demonstrates significant potential in transforming UTI management by enhancing diagnostic precision, reducing costs, and improving clinician workflows. Its continuous learning system (CLS) ensures adaptability to clinical feedback, fostering greater clinician trust and adoption. Future expansions aim to extend its application to other infectious diseases and establishing a scalable framework for AI-driven clinical decision support.