Description
The project aims to develop decision support based on advanced statistical methods, machine learning (ML) and data from large health care registers, to optimize patient care in the emergency department.The project is part of the AIR Lund (https://www.lupop.lu.se/airlund) which is a collaboration between Lund University, University of Halmstad, Region Skåne and Region Halland around register research using artificial intelligence (AI).
In Sweden, there is a unique opportunity to research various registers in health care. These registers have not been used to the extent possible with regard to the development of decision support based on statistical models or ML. Such decision support has enormous potential to improve diagnostics and treatment of patients seeking the emergency department. With refined and more individualized predictions, emergency department care could be better tailored to each patient. This in turn has the potential to increase patient safety and optimize resource utilization.
Period | 2021 Feb 1 → 2024 Nov 21 |
---|---|
Examinee/Supervised person | Ellen Tolestam Heyman |
Examination/Supervision held at | |
Degree of Recognition | International |
UKÄ subject classification
- Clinical Medicine
- Medical and Health Sciences
Free keywords
- Artificial intelligence
- Emergency Medicine
- Emergency Department
- Ai
- Machine learning
Related content
-
Research output
-
Interpretable AI diagnostics for dyspnea in the emergency department by deep learning and a massive regional health care dataset
Research output: Contribution to conference › Poster
-
A novel interpretable deep learning model for diagnosis in emergency department dyspnoea patients based on complete data from an entire health care system
Research output: Contribution to journal › Article › peer-review
-
Improving Machine Learning 30-Day Mortality Prediction by Discounting Surprising Deaths
Research output: Contribution to journal › Article › peer-review
-
Design of an AI Support for Diagnosis of Dyspneic Adults at Time of Triage in the Emergency Department
Research output: Contribution to conference › Poster
-
How does an AI diagnose dyspnoea in ED triage without human guidance?
Research output: Contribution to conference › Poster
-
Likelihood of admission to hospital from the emergency department is not universally associated with hospital bed occupancy at the time of admission
Research output: Contribution to journal › Article › peer-review
-
Projects
-
AIR Lund - Artificially Intelligent use of Registers
Project: Research
-
Resource Management in the Emergency Department by using Machine Learning
Project: Dissertation