Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Using AI to determine optimal cost-effective diagnostic pathways for chronic breathlessness

Olsson, Max LU orcid ; Ahmed, Rafsan LU orcid ; Ekstrand, Joakim ; Blomberg, Anders ; Jernberg, Tomas ; Börjesson, Mats ; Evans, Rachael A ; Malinovschi, Andrei LU ; Sandberg, Jacob LU orcid and Sköld, Magnus , et al. (2026) In npj Primary Care Respiratory Medicine 36(1).
Abstract

Breathlessness is a common symptom in clinical practice, yet evidence for cost-effective strategies to diagnose the underlying health conditions causing breathlessness remains limited. Using Swedish population data with individuals with moderate to severe breathlessness, we developed an artificial intelligence (AI) reinforcement learning model to identify optimal, low-cost diagnostic pathways for breathlessness tailored to subgroups based on sex and smoking exposure. Sixteen clinically relevant conditions were defined, along with their diagnostic tests and standard healthcare costs. The AI-based approach successfully produced efficient and low-cost diagnostic pathways for breathlessness with high diagnostic yield. The optimal sequences... (More)

Breathlessness is a common symptom in clinical practice, yet evidence for cost-effective strategies to diagnose the underlying health conditions causing breathlessness remains limited. Using Swedish population data with individuals with moderate to severe breathlessness, we developed an artificial intelligence (AI) reinforcement learning model to identify optimal, low-cost diagnostic pathways for breathlessness tailored to subgroups based on sex and smoking exposure. Sixteen clinically relevant conditions were defined, along with their diagnostic tests and standard healthcare costs. The AI-based approach successfully produced efficient and low-cost diagnostic pathways for breathlessness with high diagnostic yield. The optimal sequences were overall similar between the subgroups. For all participant subgroups, the AI-derived pathways initially identified (or order of effectiveness in relation to costs) clinical evaluations of body mass index, anxiety and depression, physical activity levels, and spirometry. Subsequent steps included diffusing capacity measurements, chest computer tomography, and hemoglobin assessment. Overall, investigations of the lungs were prioritized ahead of investigations of the heart. This strategy has the potential to streamline the evaluation of breathlessness, reduce unnecessary testing, lead to an earlier diagnosis at lower cost, and support more targeted clinical management.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Humans, Dyspnea/diagnosis, Cost-Benefit Analysis, Artificial Intelligence, Female, Cost-Effectiveness Analysis, Male, Chronic Disease, Sweden, Middle Aged, Spirometry
in
npj Primary Care Respiratory Medicine
volume
36
issue
1
article number
57
publisher
Nature Publishing Group
external identifiers
  • pmid:42595763
ISSN
2055-1010
DOI
10.1038/s41533-026-00548-9
language
English
LU publication?
yes
additional info
© 2026. The Author(s).
id
19590150-2b29-4824-aef4-69e66e5d7ba1
date added to LUP
2026-08-17 09:11:53
date last changed
2026-08-17 15:30:37
@article{19590150-2b29-4824-aef4-69e66e5d7ba1,
  abstract     = {{<p>Breathlessness is a common symptom in clinical practice, yet evidence for cost-effective strategies to diagnose the underlying health conditions causing breathlessness remains limited. Using Swedish population data with individuals with moderate to severe breathlessness, we developed an artificial intelligence (AI) reinforcement learning model to identify optimal, low-cost diagnostic pathways for breathlessness tailored to subgroups based on sex and smoking exposure. Sixteen clinically relevant conditions were defined, along with their diagnostic tests and standard healthcare costs. The AI-based approach successfully produced efficient and low-cost diagnostic pathways for breathlessness with high diagnostic yield. The optimal sequences were overall similar between the subgroups. For all participant subgroups, the AI-derived pathways initially identified (or order of effectiveness in relation to costs) clinical evaluations of body mass index, anxiety and depression, physical activity levels, and spirometry. Subsequent steps included diffusing capacity measurements, chest computer tomography, and hemoglobin assessment. Overall, investigations of the lungs were prioritized ahead of investigations of the heart. This strategy has the potential to streamline the evaluation of breathlessness, reduce unnecessary testing, lead to an earlier diagnosis at lower cost, and support more targeted clinical management.</p>}},
  author       = {{Olsson, Max and Ahmed, Rafsan and Ekstrand, Joakim and Blomberg, Anders and Jernberg, Tomas and Börjesson, Mats and Evans, Rachael A and Malinovschi, Andrei and Sandberg, Jacob and Sköld, Magnus and Wollmer, Per and Östgren, Carl Johan and Engström, Gunnar and Björkelund, Anders J and Ekström, Magnus}},
  issn         = {{2055-1010}},
  keywords     = {{Humans; Dyspnea/diagnosis; Cost-Benefit Analysis; Artificial Intelligence; Female; Cost-Effectiveness Analysis; Male; Chronic Disease; Sweden; Middle Aged; Spirometry}},
  language     = {{eng}},
  month        = {{08}},
  number       = {{1}},
  publisher    = {{Nature Publishing Group}},
  series       = {{npj Primary Care Respiratory Medicine}},
  title        = {{Using AI to determine optimal cost-effective diagnostic pathways for chronic breathlessness}},
  url          = {{http://dx.doi.org/10.1038/s41533-026-00548-9}},
  doi          = {{10.1038/s41533-026-00548-9}},
  volume       = {{36}},
  year         = {{2026}},
}