6 ECTS credits
160 u studietijd

Aanbieding 1 met studiegidsnummer 4023340FNR voor alle studenten in het 2e semester met een gespecialiseerd master niveau.

Semester
2e semester
Inschrijving onder examencontract
Niet mogelijk
Beoordelingsvoet
Beoordeling (0 tot 20)
2e zittijd mogelijk
Ja
Onderwijstaal
Engels
Onder samenwerkingsakkoord
Onder interuniversitair akkoord mbt. opleiding
Faculteit
Faculteit Ingenieurswetenschappen
Verantwoordelijke vakgroep
Elektronica en Informatica
Onderwijsteam
Bart Jansen (titularis)
Nikolaos Deligiannis
Jef Vandemeulebroucke
Onderdelen en contacturen
36 contacturen Hoorcollege
24 contacturen Werkcolleges, practica en oefeningen
20 contacturen Zelfstudie en externe werkvormen
Inhoud

Position of the course  
The purpose of this course is to give students a detailed overview of how data from medical devices, wearables and clinical databases is acquired, stored, processed and visualized, in order to provide insights for clinicians, including medical doctors, nurses and paramedics.  
Focus will be on applications that combine software technologies, network technologies, semantic technologies and/or machine learning for usage in hospitals, nursing homes, but also in residential context for healthy living applications.  
The students will learn the technologies during the lectures (HOC) and will gain hands-on experience during the specific lab sessions (WPO) using real-life data sets and in project work (ZELF).


Contents  
The following topics will be covered during the lectures and will be available in the course notes: 
 
• From medical device/sensor/wearable to data • Health information systems • Network, cloud and software technologies to connect to medical devices, wearables and acquire data from these devices • Data extraction, databases and management of large scale datasets • Healthcare knowledge management Semantics / reasoning / ... • Introduction to machine learning and data mining technologies • Visualization of medical datasets • Data cleaning and preprocessing • Supervised (classification, regression) vs unsupervised (clustering) data mining 

Bijkomende info

Keywords  
Data analytics, machine learning, eHealth, big data, medical devices  

Initial competences  
Basic programming skills in Python, and basic knowledge of algorithms and data structures, signal processing and analysis of systems and signals. 

Leerresultaten

Final Competences

After completion of this course, the student will be able to  
• Being familiar with the basic concepts of health information systems and understanding how database systems work  • Understand network technologies and protocols tailored to connect medical devices,  wearables and databases • Having a comprehensive knowledge about the machine learning process where data 1 is transformed into information and knowledge • Understanding the details of and choice between supervised and unsupervised systems  • Interpreting and visualizing the results of a machine learning process or the content of medical datasets • Having a comprehensive knowledge of Python for data analytics purposes • Being able to select, for a given healthcare analytics problem, the most appropriate  method to achieve the defined goals 

Beoordelingsinformatie

De beoordeling bestaat uit volgende opdrachtcategorieën:
Examen Schriftelijk bepaalt 70% van het eindcijfer

Examen Andere bepaalt 30% van het eindcijfer

Binnen de categorie Examen Schriftelijk dient men volgende opdrachten af te werken:

  • Written exam met een wegingsfactor 1 en aldus 70% van het totale eindcijfer.

    Toelichting: Written closed book

Binnen de categorie Examen Andere dient men volgende opdrachten af te werken:

  • Pract+Project met een wegingsfactor 1 en aldus 30% van het totale eindcijfer.

    Toelichting: During semester: graded practicals/lab sessions and project work

Aanvullende info mbt evaluatie

Evaluation methods end-of-term evaluation and continuous assessment  
Examination methods in case of periodic evaluation during the first examination period Written examination  
Examination methods in case of periodic evaluation during the second examination period Written examination  
Examination methods in case of permanent evaluation Skills test, report  
Possibilities of retake in case of permanent evaluation examination during the second examination period is possible in modified form  

Extra information on the examination methods  
Written closed-book exam; 
 • During semester: graded practicals/lab sessions and project work.  
Calculation of the examination mark  
• 70% exam • 30% lab sessions/practicals and project 

Toegestane onvoldoende
Kijk in het aanvullend OER van je faculteit na of een toegestane onvoldoende mogelijk is voor dit opleidingsonderdeel.

Academische context

Deze aanbieding maakt deel uit van de volgende studieplannen:
Master in de ingenieurswetenschappen: toegepaste computerwetenschappen: Standaard traject
Master in de ingenieurswetenschappen: biomedische ingenieurstechnieken: Standaard traject
Master of Applied Sciences and Engineering: Applied Computer Science: Standaard traject (enkel aangeboden in het Engels)
Master of Biomedical Engineering: Startplan (enkel aangeboden in het Engels)
Master of Biomedical Engineering: Profiel Radiation Physics (enkel aangeboden in het Engels)
Master of Biomedical Engineering: Profiel Biomechanics and Biomaterials (enkel aangeboden in het Engels)
Master of Biomedical Engineering: Profiel Sensors and Medical Devices (enkel aangeboden in het Engels)
Master of Biomedical Engineering: Profiel Neuro-Engineering (enkel aangeboden in het Engels)
Master of Biomedical Engineering: Standaard traject (NIEUW) (enkel aangeboden in het Engels)