Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Assessing Risk for Nocturnal Hypoglycemia after Physical Activity in Children with Type 1 Diabetes
This thesis aims to work on the research question of whether nocturnal hypoglycemia can be detected based on data collected during the day. The exact focus can be determined together, for example:
• Addressing missing data in time series
• Concentrate on feature engineering, e.g. calculation of hand-crafted features and comparison of feature selection approaches
**1 Background**
Type 1 Diabetes (T1D) affects more than 8 million people worldwide, 1.5 million of them being younger than 20 years of age (Gregory et al., 2022; Patterson et al., 2019). T1D results from autoimmune destruction of pancreatic beta cells leading to insulin deficiency. The missing hormone insulin needs to be replaced several times a day, either with subcutaneous injections or an insulin pump. Good blood glucose control is important to avoid acute and long-term complications (Diabetes Control and Complications Trial Research Group, 1993). However, especially for young children and adolescents, this represents an everyday challenge (Foster et al., 2019). Low blood sugar (hypoglycemia) is the most feared and common acute complication of T1D (Glocker et al., 2022; Nordfeldt and Ludvigsson, 2005), and the constant risk of hypoglycemia represents a great burden, in particular for children and their caregivers (Patton et al., 2020).
**2 Project Description**
In collaboration with physicians from the University Children’s Hospital Basel (UKBB), we collected longitudinal data from children with T1D over one week. Data consist of continuous glucose measurements (CGM), information about insulin doses and carbohydrate intake, and physiological data such as heart rate, heart rate variability, and physical activity. The vision of this project is to simplify and improve type 1 diabetes management for children and their parents to prevent hypoglycemia, reduce associated anxiety and psychological stress and thus increase the quality of life and well-being of all involved. As a first step, the classification and prediction of nocturnal hypoglycemia will be addressed, considering the availability of missing data.
**3 Requirements**
A suitable candidate should be motivated to work on a new and interesting topic and should fulfill the following requirements:
Solid background in machine learning
Familiar with approaches for time series data
Proficiency in Python and experience with the Pandas package
Ability to independently read and understand publications in the area of machine learning and medical data science
**1 Background**
Type 1 Diabetes (T1D) affects more than 8 million people worldwide, 1.5 million of them being younger than 20 years of age (Gregory et al., 2022; Patterson et al., 2019). T1D results from autoimmune destruction of pancreatic beta cells leading to insulin deficiency. The missing hormone insulin needs to be replaced several times a day, either with subcutaneous injections or an insulin pump. Good blood glucose control is important to avoid acute and long-term complications (Diabetes Control and Complications Trial Research Group, 1993). However, especially for young children and adolescents, this represents an everyday challenge (Foster et al., 2019). Low blood sugar (hypoglycemia) is the most feared and common acute complication of T1D (Glocker et al., 2022; Nordfeldt and Ludvigsson, 2005), and the constant risk of hypoglycemia represents a great burden, in particular for children and their caregivers (Patton et al., 2020).
**2 Project Description**
In collaboration with physicians from the University Children’s Hospital Basel (UKBB), we collected longitudinal data from children with T1D over one week. Data consist of continuous glucose measurements (CGM), information about insulin doses and carbohydrate intake, and physiological data such as heart rate, heart rate variability, and physical activity. The vision of this project is to simplify and improve type 1 diabetes management for children and their parents to prevent hypoglycemia, reduce associated anxiety and psychological stress and thus increase the quality of life and well-being of all involved. As a first step, the classification and prediction of nocturnal hypoglycemia will be addressed, considering the availability of missing data.
**3 Requirements**
A suitable candidate should be motivated to work on a new and interesting topic and should fulfill the following requirements:
Solid background in machine learning
Familiar with approaches for time series data
Proficiency in Python and experience with the Pandas package
Ability to independently read and understand publications in the area of machine learning and medical data science
This thesis aims to work on the research question of whether nocturnal hypoglycemia can be detected based on data collected during the day. The exact focus can be determined together, for example:
• Addressing missing data in time series
• Concentrate on feature engineering, e.g. calculation of hand-crafted features and comparison of feature selection approaches
The thesis must contain a detailed description of all developed and used algorithms as well as a profound result evaluation and discussion. The implemented code has to be documented and provided. Extended research on literature, existing patents, and related work in the corresponding areas has to be performed.
This thesis aims to work on the research question of whether nocturnal hypoglycemia can be detected based on data collected during the day. The exact focus can be determined together, for example:
• Addressing missing data in time series
• Concentrate on feature engineering, e.g. calculation of hand-crafted features and comparison of feature selection approaches
The thesis must contain a detailed description of all developed and used algorithms as well as a profound result evaluation and discussion. The implemented code has to be documented and provided. Extended research on literature, existing patents, and related work in the corresponding areas has to be performed.
If you are interested in the project, please contact Heike Leutheuser (heike.leutheuser@inf.ethz.ch), send your transcript and CV, and explain your motivation for the project in 3-4 sentences. I am looking forward to hearing from you!
If you are interested in the project, please contact Heike Leutheuser (heike.leutheuser@inf.ethz.ch), send your transcript and CV, and explain your motivation for the project in 3-4 sentences. I am looking forward to hearing from you!