master Assignment
Personalized risk prediction for asthma deterioration in children
Type: Master
Student: Unassigned
Duration: TBD
If you are interested please contact:
Data type(s): Tabular data, Time series (lung function), Text data (clinical notes), eHealth data
Description: Childhood asthma affects about 7% of Dutch children and can have a lasting impact on their development and quality of life. In clinical practice, it is often challenging to determine which combination of factors, such as medication adherence, symptom perception, or environmental triggers like weather, pollen, or viral exposure, drives asthma deterioration in individual patients. As a result, many children are labeled as having difficult-to-treat asthma and receive a generic treatment plan. This project aims to leverage AI to identify patient-specific risk factors and improve personalized care.
Goal: Optimize an AI model to predict asthma deterioration in children by increasing sensitivity through improved input data and applying advanced data science techniques, ultimately supporting a personalized, AI-driven asthma care pathway.
Supervisors: Dr. B. Thio (MST), dr. M. van de Kamp (MST), T. Ruuls (MST/UT), dr. J. Mikhal (UT).