Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Design of an AI Support for Diagnosis of Dyspneic Adults at Time of Triage in the Emergency Department

Tolestam Heyman, Ellen LU orcid ; Ashfaq, Awais ; Ekelund, Ulf LU orcid ; Ohlsson, Mattias LU orcid ; Björk, Jonas LU ; Khoshnood, Ardavan M. LU orcid and Lingman, Markus (2023) European Emergency Medicine Congress 2023
Abstract
We created an AI support for diagnosis in dyspneic adults at time of triage in the emergency department.

Complete data from an entire regional health care system was analyzed, to find AI-derived, unknown, important diagnostic predictors. Most important were prior diagnoses of heart failure or COPD, daily smoking, atrial fibrillation/flutter, life difficulties and maternal care.

Sensitivity for AHF, eCOPD and pneumonia was 75%, 93%, and 54%, respectively, with a specificity above 75%.

Each patient visit received an individual graph with the AI´s underlying decision basis.
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to conference
publication status
published
subject
keywords
artificial intelligence, AI, Dyspnea, Artificiell intelligens, AI, Dyspne
conference name
European Emergency Medicine Congress 2023
conference location
Barcelona, Spain
conference dates
2023-09-17 - 2023-09-20
project
Resource Management in the Emergency Department by using Machine Learning
AIR Lund - Artificially Intelligent use of Registers
language
English
LU publication?
yes
id
9ba953a5-a331-4703-9a33-bcd45d86516e
date added to LUP
2023-09-05 00:01:15
date last changed
2024-02-14 15:12:03
@misc{9ba953a5-a331-4703-9a33-bcd45d86516e,
  abstract     = {{We created an AI support for diagnosis in dyspneic adults at time of triage in the emergency department.<br/><br/>Complete data from an entire regional health care system was analyzed, to find AI-derived, unknown, important diagnostic predictors. Most important were prior diagnoses of heart failure or COPD, daily smoking, atrial fibrillation/flutter, life difficulties and maternal care.<br/><br/>Sensitivity for AHF, eCOPD and pneumonia was 75%, 93%, and 54%, respectively, with a specificity above 75%. <br/><br/>Each patient visit received an individual graph with the AI´s underlying decision basis.}},
  author       = {{Tolestam Heyman, Ellen and Ashfaq, Awais and Ekelund, Ulf and Ohlsson, Mattias and Björk, Jonas and Khoshnood, Ardavan M. and Lingman, Markus}},
  keywords     = {{artificial intelligence; AI; Dyspnea; Artificiell intelligens; AI; Dyspne}},
  language     = {{eng}},
  title        = {{Design of an AI Support for Diagnosis of Dyspneic Adults at Time of Triage in the Emergency Department}},
  url          = {{https://lup.lub.lu.se/search/files/157237007/Eposter_Dyspnea.pdf}},
  year         = {{2023}},
}