Big Data

Description

The digital universe is expanding continuously. This huge amount of information often referred to as Big Data has a huge potential to answer questions that could not be answered before. For example, in biomedical sciences, researchers increasingly make use of these Big Data, by pooling real-time data from multiple sources including electronic healthcare records in order to e.g. detect diseases at an early stage.

Spanning topics such as:

• Introduction to machine learning (ML)
• Automated ML
• Causal inference using big data and ML
• Natural language processing
• Data linkage

This will be embedded in medical research through numerous real-life examples and case-studies.

Target audience

The target group of this course includes advanced BSc and MSc students in biomedical sciences with a basic understanding of epidemiology and (medical) statistics.



A basics understanding of R or python programming languages is desirable; however self-study tutorials (~2 hours each) will be provided

Aim of the course

• Run and understand basic Python scripts to perform machine learning analyses of large datasets;
• Interpret results of a simple machine learning pipeline, including its design and performance;
• Understand and explain basic concepts of machine learning, including: supervised/unsupervised learning, overfitting, cross-validation, evaluation metrics, bias-variance tradeoffs, and benchmarking;
• Understand and explain basic concepts of deep learning;
• Understand and explain basic concepts of causal modelling;
• List several existing and potential applications of machine learning and AI in medical research.

Study load

Full time

Monday to Friday

From 10.00 to 17.00 hours

Tags

• big data