Projects per year
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.
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.
| Original language | English |
|---|---|
| Publication status | Published - 2023 Sept |
| Event | European Emergency Medicine Congress 2023 - Barcelona, Spain Duration: 2023 Sept 17 → 2023 Sept 20 |
Conference
| Conference | European Emergency Medicine Congress 2023 |
|---|---|
| Country/Territory | Spain |
| City | Barcelona |
| Period | 2023/09/17 → 2023/09/20 |
Subject classification (UKÄ)
- Cardiac and Cardiovascular Systems
Free keywords
- artificial intelligence
- AI
- Dyspnea
Access to Document
Fingerprint
Dive into the research topics of 'Design of an AI Support for Diagnosis of Dyspneic Adults at Time of Triage in the Emergency Department'. Together they form a unique fingerprint.Projects
- 2 Active
-
Resource Management in the Emergency Department by using Machine Learning
Tolestam Heyman, E., Khoshnood, A., Ekelund, U., Björk, J., Ohlsson, M., Lingman, M. & Dahlén Holmqvist, L.
2021/02/01 → …
Project: Dissertation
-
AIR Lund: AIR Lund - Artificially Intelligent use of Registers
Björk, J., Ohlsson, M., Melander, O., Ekelund, U., Larsson, S., Mattsson, T., Mokhtari, A., de Vries, K., Nilsson, A., Lingman, M., Pashami, S., Ottosson, F., Larsson, A. E., Henriksen, A., Högberg, C., Olsson, M., Nyström, A., Olsson de Capretz, P., Björkelund, A., Nilsson, A., Åkesson, A., Nordberg, A., Ekström, M., Tolestam Heyman, E., Lundager Forberg, J., Berg, J., Johansson, A., Amirahmadi, A., Eriksson, T., Khoshnood, A., Mäkinen, M., Müllerová, P. & Nilsson, T. N.
2018/07/01 → 2024/12/31
Project: Research
Activities
- 1 Supervision of PhD students
-
Resource management in the emergency department by using machine learning
Ardavan Khoshnood (First/primary/lead supervisor), Ulf Ekelund (Second supervisor), Mattias Ohlsson (Joint second supervisor), Jonas Björk (Joint second supervisor) & Markus Lingman (Joint second supervisor)
2021 Feb 1 → …Activity: Examination and supervision › Supervision of PhD students