Data and Technology in Healthcare
Full course description
This module is the first module within the learning line Data science in Healthcare. It is an introductory module on the foundations of data science and its technologies. It introduces students to an inferential and computational way of thinking and lays the basis for the following modules of the learning line. The module starts with a conceptual discussion about data science and the way it influences healthcare. What is the historical origin of this domain and what do the buzzwords mean (i.e. data science, data analytics, AI, algorithms, machine learning)? Students learn about data, data representation and data interoperability in the healthcare domain, the concepts of existing responsibility frameworks covering topics such as open science and the FAIR (=findable, accessible, interoperable, reusable) data principles. Besides learning about concepts, students are also introduced to common methods used within the field of data science and how it is used within healthcare.
Students learn to distinguish between traditional hypothesis-driven versus data-driven research. The so-called “data science lifecycle” is used to guide students through the different steps of conducting a data-driven approach. Students learn about data, standard data types, formats and their exchange. In this module, students also trained about data privacy and protection (using methods for anonymization and pseudonymisation).
Course objectives
The specific course objectives are:
Expert:
The student is able to:
- know the historical origin of data science
- explain data science buzzwords
- distinguish between data collection methods and data types
- know how health information is stored
- know about data collection and conducting experiments
- know how to tackle issues with regards to ethics, legal compliance, data quality, algorithmic fairness and diversity, transparency of data and algorithms, privacy, and data protection.
- explain the difference between a number of responsibility frameworks
- make their data more FAIR
- know about privacy-preserving approaches and techniques used for data protection (pseudo- and anonymization, data encryption)
- know how data science influences healthcare
Investigator
The student is able to:
- formulate research questions for data science problems
- query and exchange health data
- work with data types, collections, tables and data standards in Python
- set up data science experiments
- use visualisations for data science storytelling
- clean and manipulate datause privacy-preserving techniques and data encryption in practice