Machine learning for lung protective ventilation
How to Apply
[ML Assistant]
Required Materials
- What you are studying (e.g. "Bachelor in Applied Data Science")
- A short list of which relevant skills you have and which you would like to acquire
- A list of courses you have taken and corresponding grades
- Known programming languages and experience
- Possible start date
Offer
- 40h/month or 80h/month position as research assistant.
- Start date: immediately
- Necessary skills
- Python programming (basic to intermediate)
- Some statistical and/or machine learning background
- Ability to work in teams and together with clinical partners
- Why work on this project?
- Chance to gather experience in a medical AI project with real data
- Extend skills in: data management and probabilistic/causal models
- Gather experience in interdisciplinary research together with machine learning researchers and clinicians.
Background
Mechanical ventilation is the most important supportive and life-sustaining measure for severe acute respiratory failure in patients with Acute Respiratory Distress Syndrome (ARDS). Conservative estimates suggest that about 150.000 patients per year suffer from ARDS in Europe alone. Ensuring pulmonary gas exchange buys time to treat the underlying cause of the disease. The COVID-19 pandemic led to a massive increase in ARDS cases worldwide and has highlighted the possibilities, but also the limitations and problems associated with mechanical ventilation. The concept of lung protective ventilation aims at preventing injurious side effects while enhancing protection by monitoring several variables that captured during mechanical ventilation such as the tidal volume, the peak airway pressure or positive end-expiratory pressure (PEEP). However, current therapeutic approaches, often only addressing a few variables, do not sufficiently account for treatment corridors to be specified for the setting of mechanical ventilation and thus fail to adapt to personalized mechanical ventilation for the individual patient.
Project Description
Here we aim to preprocess and integrate existing clinical data from patients as well as data from pig experiments in order to develop statistical models to investigate the complex interactions amongst clinical ventilation parameters to predict the success of mechanical ventilation and predict pending risk for individual patients. These models will be the first step towards an (causal) model for personalized ventilation settings.
The goals of the project is to (a) ingest the data into a format that allows statistical modeling and (b) establish baseline models that will form the basis for more advanced learning algorithms.