Objectives
This curricular unit aims to analyse the concepts and methodologies associated with the big data area and its application to the health domain.
In addition to a theoretical approach, the main approaches and computational tools representing the state of the art will be presented, discussed and evaluated. Specifically, the problems associated with the collection, transformation, analysis, visualization and interpretation of large volumes of data in the health area will be addressed, with several case studies being carried out.
At the end of this course students will have: - knowledge of big data concepts and methodologies; - ability to apply the main methodologies, being aware of their potential and limitations; - ability to define big data strategies in the health area.
General characterization
Code
531011
Credits
6
Responsible teacher
Available soon
Hours
Weekly -
Available soon
Total -
Available soon
Teaching language
Portuguese
Prerequisites
Not applicable to
Bibliography
- Ghavam, Peter (2019) Big Data Analytics Methods: Analytics Techniques in Data Mining, Deep Learning and Natural Language Processing, Boston: deGruyter
- Strome, Trevor (2013) Healthcare Analytics for Quality and Performance Improvement. New Jersey: John Wiley & Sons, Inc. DOI:10.1002/9781118761946
- Takejuji, Yoshiyasu (2019) Open Source Machine Learning in Medicine.
- Zumel, N., Mount, J.,(2014). Practical Data Science. 2nd ed. Manning. (https://www.manning.com/books/practical-data-science-with[1]r-second-edition)
Teaching method
As a teaching methodology, a mixed approach will be made with theoretical presentations of the concepts complemented by concrete applications developed individually by the students.
Evaluation method
The evaluation will be carried out through the resolution of case studies, including its presentation and discussion before the teacher.
Subject matter
- Big Data: fundamentals and basic concepts;
- Big data in the health area: heterogeneous and semi-structured data (medical records, exams, IoT); ethical and legal issues;
- Main processes in big data analysis: collection, cleaning, transformation, analysis, visualization, interpretation;
- Automatic learning approaches for classification, grouping / clustering and identification of correlations in the data.
- Construction of explanatory and predictive models. - Solutions in the "cloud" and frameworks for "big data analysis"
- Case studies: analysis and implementation of solutions.
Programs
Programs where the course is taught:
