ClinQueryAgent: A Conversational Agent for Population Health Management
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918510028914688 |
|---|---|
| author | Boyle, Joseph S. Dranfield, Anthony O'Neil, Mike Liakata, Maria Smithard, Alison Q. |
| author_facet | Boyle, Joseph S. Dranfield, Anthony O'Neil, Mike Liakata, Maria Smithard, Alison Q. |
| contents | In this paper we introduce ClinQueryAgent, a system for translating natural language population health questions into executable database queries using agents with access to both local and external knowledge bases. Our novel architecture enables the use of powerful cloud-based language models whilst ensuring that no patient data leaves the secure environment. To combat inaccuracies over the course of longer dialogues due to context rot, information retrieval is delegated to a sub-agent. We deploy the system via a chat window embedded within an existing population health management platform where it has been used by 128 staff from 15 healthcare practices covering a total of 148,319 patients in the UK's National Health Service (NHS). We evaluate the system's capacity to autonomously handle a range of health informatics tasks on a constructed dataset and via a beta-testing phase. Our results show that both analysts and clinicians are able to easily generate actionable information from patient health records using natural language requests requiring no programming expertise to verify. We make a public demo of the system available at: https://demo-899965260288.europe-west1.run.app/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18768 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ClinQueryAgent: A Conversational Agent for Population Health Management Boyle, Joseph S. Dranfield, Anthony O'Neil, Mike Liakata, Maria Smithard, Alison Q. Information Retrieval Human-Computer Interaction Multiagent Systems In this paper we introduce ClinQueryAgent, a system for translating natural language population health questions into executable database queries using agents with access to both local and external knowledge bases. Our novel architecture enables the use of powerful cloud-based language models whilst ensuring that no patient data leaves the secure environment. To combat inaccuracies over the course of longer dialogues due to context rot, information retrieval is delegated to a sub-agent. We deploy the system via a chat window embedded within an existing population health management platform where it has been used by 128 staff from 15 healthcare practices covering a total of 148,319 patients in the UK's National Health Service (NHS). We evaluate the system's capacity to autonomously handle a range of health informatics tasks on a constructed dataset and via a beta-testing phase. Our results show that both analysts and clinicians are able to easily generate actionable information from patient health records using natural language requests requiring no programming expertise to verify. We make a public demo of the system available at: https://demo-899965260288.europe-west1.run.app/ |
| title | ClinQueryAgent: A Conversational Agent for Population Health Management |
| topic | Information Retrieval Human-Computer Interaction Multiagent Systems |
| url | https://arxiv.org/abs/2605.18768 |