dr. Alexander Decruyenaere (MD)

As the demand for data sharing peaks, so too do the legal obstacles to accessing privacy-sensitive health data. Synthetic data have recently been proposed as a promising alternative. These are artificially generated data that attempt to replicate the statistical properties of the original data without disclosing individual records. While synthetic data hold great promise for privacy protection, their statistical analysis poses significant challenges that necessitate innovative solutions. The use of deep generative models for synthetic data generation is known to induce considerable bias and imprecision into synthetic data analyses, compromising their inferential utility as opposed to original data analyses. This bias and uncertainty can be substantial enough to impede statistical convergence rates, even in seemingly straightforward analyses like mean calculation. This complicates fundamental calculations like p-values and confidence intervals, with no straightforward remedy currently available.

In response to these challenges, we develop new strategies that target synthetic data created by deep generative models for specific data analyses. These strategies contribute to advancing the reliability and applicability of synthetic data in statistical inference.
 

Alexander Decruyenaere graduated as a medical doctor in 2016 at Ghent University and was board certified in medical oncology in 2022. He also obtained a master's degree in statistical data analysis from Ghent University in 2019. Alexander is currently working as a medical oncologist at the department of Medical Oncology in Ghent University Hospital with clinical focus on genitourinary cancers. His research focus lies at the intersection of oncology and data science, with special interest in synthetic data generation and causal (machine) learning.

He is pursuing doctoral research (PhD) on synthetic health data generation under the direction of prof. Stijn Vansteelandt (department of Applied Mathematics, Computer Science and Statistics, Ghent University), prof. Thomas Demeester (Internet Technology and Data Science Lab, Ghent University - imec) and prof. Sylvie Rottey (department of Basic and Applied Medical Sciences, Ghent University) at the SYNDARA (SYNthetic DAta for Research Acceleration) collaborative research unit.

Alexander is a member of the Belgian Society of Medical Oncology (BSMO) and its Young Oncologists Committee (YOC), the European Society of Medical Oncology (ESMO), the Royal Statistical Society of Belgium (RSSB), and the Quetelet Society.
 

• Lab address: SYNDARA research unit, Nobel I, Ghent University Hospital
• Bio UZ Ghent
• LinkedIn  
• Google scholar  
• Alexander Decruyenaere is interested to receive invitations for presentations or talks