Aarhus University Seal / Aarhus Universitets segl

PhD defence: Simon Meyer Lauritsen

Machine learning based prediction of clinical deterioration in general wards

2022.01.26 | Graduate School of Health

Date Thu 10 Feb
Time 14:00 16:00
Location Auditoriet, Nye Nord Regionshospitalet Horsens, Sundvej 30, Horsens and online

On Thursday 10 February at 14:00, Simon Meyer Lauritsen defends his PhD dissertation entitled "Machine learning based prediction of clinical deterioration in general wards".

Acute clinical deterioration, if untreated, can lead to adverse events such as intensive care unit admission, organ failure or death. However, early signs of acute clinical deterioration are often present in the hours preceding these adverse events, which may provide a clinical opportunity to initiate treatment.

A PhD project from Aarhus University, Health, investigates how data-driven methods, such as machine learning, can be used to predict acute clinical deterioration, thereby supporting timely treatment. In the project, an advanced machine learning model has been developed, which is able to predict acute clinical deterioration with high accuracy, as well as to explain the decisions to the system end-users.

The project also focused on:

  1. the basic methodological aspects related to the development of risk prediction models.
  2. how risk prediction models are evaluated from a clinical perspective.
  3. how data-driven algorithms can be implemented in everyday clinical practice
  4. what scientific evidence exists for implemented machine learning models

The summary is written by the PhD student.

The defence is public and takes place in Auditoriet, Nye Nord Regionshospitalet Horsens, Sundvej 30, Horsens and online via Zoom. Please read the attached press release for more information.

Contact

PhD student Simon Meyer Lauritsen

Mail: sihl@clin.au.dk

Phone: (+45) 30554920

Read full press release

PhD defense, Public/Media, Graduate School of Health, Graduate School of Health, PhD students, Department of Clinical Medicine, Academic staff, Health