This research project is associated with IntelliLung project which aims to reduce lung injuries by
providing automated suggestions to clinicians for mechanically ventilated patients in the ICU.
Biased datasets can degrade the performance of the trained algorithms. Considering the
importance of safety for this application, it is critical to identify these biases, discover their
source and develop strategies to mitigate them. Also the aim is to discover biases that can help
us structure and reduce complexity of the algorithms. This project is supported by
interdisciplinary teams and aims to identify biases not only from the Machine Learning (ML) /
Reinforcement Learning (RL) perspective but also using the domain knowledge provided by
clinicians.

Your responsibilities

• Data analysis of the existing datasets (e.g. MIMIC-IV) to identify any issues that might
  affect the performance of the algorithms.
• Identify detectable biases within the project’s context and develop methods leveraging
  knowledge from ML/RL algorithms to uncover and address them.
• Translate clinicians’ expertise into a set of actionable rules for detecting biases from a
  medical standpoint.
• Identify and utilize appropriate tools and methodologies (e.g. statistical methods,
  explainable AI) to support the project’s objectives.
• Leverage insights from the analysis to enhance offline evaluation processes.

Qualifications

• Enrolled in a Master program in computer science or related field
• Already extensive experience with data preparation, analysis, visualization and relevant
  tools
• Good knowledge of ML algorithms and tools (i.e pytorch, numpy, pandas etc),
  knowledge of RL is a plus
• Good written and verbal communication skills (in English)
• Motivated to do independent research

In case of any questions or interest, please contact us by sending your CV and study transscript. It may also be possible to work on the project as a research project or as part of a seminar thesis.