Femke De Backere

Stéphanie Carlier, Femke De Backere, Filip De Turck

Serious games and gamification (SGG) have shown to have positive effects on health outcomes of eHealth applications. However, research has shown that a shift towards a personalized approach is needed, considering the diversity of users. This introduces new challenges to the domain of SGG as research is needed on how such personalization is achieved. A literature search was conducted to provide an overview of personalization strategies. In total, 50 articles were identified, 35 reported on a serious game and 15 focused on gamification. We introduce a three-tiered classification model, including a model level, a personalization paradigm level, and algorithmic framework level to synthesize how personalization is implemented. Data-driven approaches are most common overall (22/50), with knowledge-driven and hybrid methods more prevalent in rehabilitation, reflecting safety and explainability requirements. Popular modeling choices include Hexad-based player modeling and ontologies for expert knowledge integration. Despite encouraging results, reusability remains limited, impeding comparison and knowledge transfer. This review outlines opportunities for progress:shareable knowledge assets, swap-friendly personalization engines, and clinically bounded hybrid approaches, alongside cautious use of generative AI to accelerate design while maintaining safety and explainability. This classification framework and synthesis aims to guide more modular, comparable, and clinically aligned personalized SGG.

Gilles Vandewiele, Isabelle Dehaene, György Kovács et al.

Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Recently, a large number of studies have reported near-perfect results to distinguish between recordings of patients that will deliver term or preterm using a public resource, called the Term/Preterm Electrohysterogram database. However, we argue that these results are overly optimistic due to a methodological flaw being made. In this work, we focus on one specific type of methodological flaw: applying over-sampling before partitioning the data into mutually exclusive training and testing sets. We show how this causes the results to be biased using two artificial datasets and reproduce results of studies in which this flaw was identified. Moreover, we evaluate the actual impact of over-sampling on predictive performance, when applied prior to data partitioning, using the same methodologies of related studies, to provide a realistic view of these methodologies' generalization capabilities. We make our research reproducible by providing all the code under an open license.