Our research team aims to innovate in the area of methodology for medical sciences including preclinical, clinical and social health sciences. Different projects focus on medical statistics, medical informatics and statistical and modelling algorithms
The current projects where team members are involved in are:
PROMoting Informed and Shared decisions about E-Health solutions for older adults with cognitive impairments and their informal caregivers (PROMISE)
S. Dequanter, M. Fobelets & R. Buyl
The number of older adults with cognitive impairments (MCI, dementia) is growing in fast pace. The development of technologies dedicated to health and well-being (e-Health) offers potential to support these older adults and their informal caregivers, but is not always adapted to their needs and preferences. This FWO funded bilateral collaborative Flanders-Québec project supports these groups in making informed and shared decisions about e-Health solutions to improve their health and well-being and to facilitate aging in place. The research project includes qualitative research methods as well as systematic literature reviews and ultimately, the development of an electronic decision support tool.
End-to-end errors in the Belgian electronic prescription
S. Van Laere & R. Buyl
The Belgian electronic prescription has found its entry in Belgium in 2007. Since 2013, pilot tests have been set up and in 2014 the Recip-e project has found its entrance to the broad Belgian public. One of the biggest changes came in 2017 in this project by means of a unique Recip-e ID (RID) barcode printed on top of each proof of electronic prescription to facilitate the pharmacist. In this project we investigate possible errors in the workflow between the traditional 3 Ps (prescriber, patient and pharmacist) and the tarification service.
Random neural network forests decision support for markerless stereotactic body radiotherapy
C. Raets & K. Barbé
In the field of dosimetry, clinicians define the correct dose of radiotherapy to treat cancer patients. In this project, we examine and design the potential of random forests for the dose calculation. By acknowledging that neural networks allow modelling complex relationships; we wish to combine random forests and neural networks such that an ensemble of 'simpler' neural networks, yet with random weights, can be obtained to alleviate potential overfitting leading to more precise dose calculations.
Fractional-order Wiener-Hammerstein systems for bio-impedance spectroscopy
H. Shaikh & K. Barbé
Wiener-Hammerstein models are a popular class of nonlinear dynamic time series as a simple type of nonlinear Volterra model. The Volterra model holds the same properties as what is observed in linear time series for nonlinear time series. As a result, the nonlinear system is decomposed into a purely linear and purely nonlinear part. In this project, we allow the linear dynamics to show fractional behaviour specifically of interest in the field of (bio)spectroscopy. Moreover, the project aims for algorithmic innovations which speeds up the training of the Wiener-Hammerstein model considerably.
Akritas-Arnold tests to assess nanoParticles to Activate immune Responses against Cancer
O. Olarte & K. Barbé
Contrast tests achieve a high power but unfortunately non-parametric contrast tests are limited to the Jonckheere-Terpstra test. Emerging tests of the Akritas-Arnold type is not fully understood and explored. This family of tests can be positioned within the rank randomization tests. In this project, we aim at a better understanding of the mathematical properties of the Akritas-Arnold tests which will be validated on a preclinical study on immunotherapy against cancer.
Towards a noncentral χ-distributed modelling approach for parallel fMRI
S. Blotwijk & K. Barbé
Functional Magnetic Resonance Imaging (fMRI) is a non-invasive scanning technique which allows to observe the body in action. It has been used to study the functioning of various systems in the body, such as joints and the heart, but it is most well-known for its role in studying brain activity. Currently, the brain still acts considerably faster, than traditional fMRI-scanners, which take several seconds to perform a single scan. A prominent technique that can speed up fMRI-scanning is parallel imaging (PI), but it does so at the expense of the quality of the signal. In this project, we intend to develop a mathematical and statistical framework to keep drawing correct and reliable conclusions, even at these lower signal-to-noise ratios.