Identifying clusters of people with Multiple Long-Term Conditions using Large Language Models: a population-based study

Abstract Identifying clusters of people with similar patterns of Multiple Long-Term Conditions (MLTC) could help healthcare services to tailor care. In this population-based study, we developed a pipeline incorporating a DeBERTa language model to generate gender-specific clusters. Our model, EHR-DeB...

Full description

Saved in:
Bibliographic Details
Main Authors: Alexander Smith, Thomas Beaney, Carinna Hockham, Bowen Su, Paul Elliott, Laura Downey, Spiros Denaxas, Payam Barnaghi, Abbas Dehghan, Ioanna Tzoulaki
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01806-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235645008969728
author Alexander Smith
Thomas Beaney
Carinna Hockham
Bowen Su
Paul Elliott
Laura Downey
Spiros Denaxas
Payam Barnaghi
Abbas Dehghan
Ioanna Tzoulaki
author_facet Alexander Smith
Thomas Beaney
Carinna Hockham
Bowen Su
Paul Elliott
Laura Downey
Spiros Denaxas
Payam Barnaghi
Abbas Dehghan
Ioanna Tzoulaki
author_sort Alexander Smith
collection DOAJ
description Abstract Identifying clusters of people with similar patterns of Multiple Long-Term Conditions (MLTC) could help healthcare services to tailor care. In this population-based study, we developed a pipeline incorporating a DeBERTa language model to generate gender-specific clusters. Our model, EHR-DeBERTa, was pre-trained on longitudinal sequences of diagnoses, medications and test results from primary care electronic health records of 5.8 million patients in the UK. EHR-DeBERTa was used to generate patient embeddings for males and females separately, and clusters were identified by K-Means. Fifteen clusters were identified in females and seventeen in males, categorized into low disease burden, mental health, cardiometabolic, respiratory and mixed diseases. Cardiometabolic and mental health conditions showed the strongest separation across clusters, with older patients in cardiometabolic clusters. Our approach demonstrates how LLMs can provide interpretable insights into disease patterns. Future work incorporating clinical outcomes could enhance risk prediction and support precision-medicine for people with MLTC.
format Article
id doaj-art-cbd8646f6fcb459eb970de2e7c61d7de
institution Kabale University
issn 2398-6352
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-cbd8646f6fcb459eb970de2e7c61d7de2025-08-20T04:02:44ZengNature Portfolionpj Digital Medicine2398-63522025-07-018111310.1038/s41746-025-01806-9Identifying clusters of people with Multiple Long-Term Conditions using Large Language Models: a population-based studyAlexander Smith0Thomas Beaney1Carinna Hockham2Bowen Su3Paul Elliott4Laura Downey5Spiros Denaxas6Payam Barnaghi7Abbas Dehghan8Ioanna Tzoulaki9Department of Epidemiology and Biostatistics, Imperial College LondonThe George Institute for Global Health, Imperial College LondonThe George Institute for Global Health, Imperial College LondonDepartment of Surgery & Cancer, Imperial College LondonDepartment of Epidemiology and Biostatistics, Imperial College LondonThe George Institute for Global Health, Imperial College LondonInstitute of Health Informatics, University College LondonDepartment of Brian Sciences, Imperial College LondonDepartment of Epidemiology and Biostatistics, Imperial College LondonDepartment of Epidemiology and Biostatistics, Imperial College LondonAbstract Identifying clusters of people with similar patterns of Multiple Long-Term Conditions (MLTC) could help healthcare services to tailor care. In this population-based study, we developed a pipeline incorporating a DeBERTa language model to generate gender-specific clusters. Our model, EHR-DeBERTa, was pre-trained on longitudinal sequences of diagnoses, medications and test results from primary care electronic health records of 5.8 million patients in the UK. EHR-DeBERTa was used to generate patient embeddings for males and females separately, and clusters were identified by K-Means. Fifteen clusters were identified in females and seventeen in males, categorized into low disease burden, mental health, cardiometabolic, respiratory and mixed diseases. Cardiometabolic and mental health conditions showed the strongest separation across clusters, with older patients in cardiometabolic clusters. Our approach demonstrates how LLMs can provide interpretable insights into disease patterns. Future work incorporating clinical outcomes could enhance risk prediction and support precision-medicine for people with MLTC.https://doi.org/10.1038/s41746-025-01806-9
spellingShingle Alexander Smith
Thomas Beaney
Carinna Hockham
Bowen Su
Paul Elliott
Laura Downey
Spiros Denaxas
Payam Barnaghi
Abbas Dehghan
Ioanna Tzoulaki
Identifying clusters of people with Multiple Long-Term Conditions using Large Language Models: a population-based study
npj Digital Medicine
title Identifying clusters of people with Multiple Long-Term Conditions using Large Language Models: a population-based study
title_full Identifying clusters of people with Multiple Long-Term Conditions using Large Language Models: a population-based study
title_fullStr Identifying clusters of people with Multiple Long-Term Conditions using Large Language Models: a population-based study
title_full_unstemmed Identifying clusters of people with Multiple Long-Term Conditions using Large Language Models: a population-based study
title_short Identifying clusters of people with Multiple Long-Term Conditions using Large Language Models: a population-based study
title_sort identifying clusters of people with multiple long term conditions using large language models a population based study
url https://doi.org/10.1038/s41746-025-01806-9
work_keys_str_mv AT alexandersmith identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT thomasbeaney identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT carinnahockham identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT bowensu identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT paulelliott identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT lauradowney identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT spirosdenaxas identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT payambarnaghi identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT abbasdehghan identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy
AT ioannatzoulaki identifyingclustersofpeoplewithmultiplelongtermconditionsusinglargelanguagemodelsapopulationbasedstudy