The aim is to let the student acquire specific skills in automatic training techniques for the classification and prediction of data of interest in the biomedical and clinical fields. Also, to let the student be able to apply these skills to solve problems in the relevant sector, through implementation using computational and programming tools.
teacher profile teaching materials
Programme
This course will use a problem-based learning approach to provide students with an understanding of recent advances in biomedical engineering, with a focus on the design of clinical decision support systems. Students will be provided with elements of theory associated with the use of the main machine learning techniques, exploring aspects of supervised and unsupervised learning, and exploring the application of these techniques to the general context of health care. Students will be taught to implement these techniques in commonly used programming environments (Python/MATLAB). The students will then work in groups and use the acquired theoretical knowledge and programming skills to solve a project of interest in the field of biomedical engineering, also referring to available databases (MIMIC, Physionet, ...). Using the acquired competences in theoretical elements and on the basis of the practical activities performed, students will then be able to concretely validate solutions to real biomedical engineering problems of clinical relevance.Core Documentation
There is no official textbook. For consultation, material made available on the university platform is used (lecture slides, A/V recordings, guided exercises, project examples).Attendance
40% of the activities have a project nature, so attendance to the course is highly recommended.Type of evaluation
Development, drafting, presentation and discussion of a project developed around a diagnostic or therapy/treatment question. The drafting of the project includes the writing of the code needed to solve the question.