Philippe Fortemps

Classifying subtypes of primary progressive aphasia (PPA) from connected speech presents significant diagnostic challenges due to overlapping linguistic markers. This study benchmarks the performance of traditional machine learning models with various feature extraction techniques, transformer-based models, and large language models (LLMs) for PPA classification. Our results indicate that while transformerbased models and LLMs exceed chance-level performance in terms of balanced accuracy, traditional classifiers combined with contextual embeddings remain highly competitive. Notably, SVM using RoBERTa’s embeddings achieves the highest classification accuracy. These findings underscore the potential of machine learning in enhancing the automatic classification of PPA subtypes.

In this paper, we focus on the resource perspective in the context of process mining. Most process mining techniques focus on the control-flow to uncover problems related to performance or compliance. However, the behavior of resources (e.g., employees) influences the effectiveness and efficiency of processes and should not be considered as secondary. We aim to identify resources exhibiting similar behavioral patterns that go beyond just looking at the mix of activities performed. We want to be able to identify subgroups of resources that perform similar activities but in a different order. We also provide a comparison between existing ways of grouping resources into roles and our resource-centered approach that takes into account the order in which work is performed. We will compare the results of clustering based only on the activities performed and clustering based on local process models that identify work patterns. Experiments are considered on synthetic and real data.

One-class Classification (OCC) is an area of machine learning which addresses prediction based on unbalanced datasets. Basically, OCC algorithms achieve training by means of a single class sample, with potentially some additional counter-examples. The current OCC models give satisfaction in terms of performance, but there is an increasing need for the development of interpretable models. In the present work, we propose a one-class model which addresses concerns of both performance and interpretability. Our hybrid OCC method relies on density estimation as part of a tree-based learning algorithm, called One-Class decision Tree (OC-Tree). Within a greedy and recursive approach, our proposal rests on kernel density estimation to split a data subset on the basis of one or several intervals of interest. Thus, the OC-Tree encloses data within hyper-rectangles of interest which can be described by a set of rules. Against state-of-the-art methods such as Cluster Support Vector Data Description (ClusterSVDD), One-Class Support Vector Machine (OCSVM) and isolation Forest (iForest), the OC-Tree performs favorably on a range of benchmark datasets. Furthermore, we propose a real medical application for which the OC-Tree has demonstrated its effectiveness, through the ability to tackle interpretable diagnosis aid based on unbalanced datasets.

Attention Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder that has heavy consequences on a child’s wellbeing, especially in the academic, psychological and relational planes. The current evaluation of the disorder is supported by clinical assessment and written tests. A definitive diagnosis is usually made based on the DSM-V criteria. There is a lot of ongoing research on ADHD, in order to determine the neurophysiological basis of the disorder and to reach a more objective diagnosis. The advent of Machine Learning (ML) opens up promising prospects for the development of systems able to predict a diagnosis from phenotypic and neuroimaging data. This was the reason why the ADHD-200 contest was launched a few years ago. Based on the publicly available ADHD-200 collection, participants were challenged to predict ADHD with the best possible predictive accuracy. In the present work, we propose instead a ML methodology which primarily places importance on the explanatory power of a model. Such an approach is intended to achieve a fair trade-off between the needs of performance and interpretability expected from medical diagnosis aid systems. We applied our methodology on a data sample extracted from the ADHD-200 collection, through the development of decision trees which are valued for their readability. Our analysis indicates the relevance of the limbic system for the diagnosis of the disorder. Moreover, while providing explanations that make sense, the resulting decision tree performs favorably given the recent results reported in the literature.

We consider the risk of adverse drug events caused by antibiotic prescriptions. Antibiotics are the second most common cause of drug related adverse events and one of the most common classes of drugs associated with medical malpractice claims. To cope with this serious issue, physicians rely on guidelines, especially in the context of hospital prescriptions. Unfortunately such guidelines do not offer sufficient support to solve the problem of adverse events. To cope with these issues our work proposes a clinical decision support system based on expert medical knowledge, which combines semantic technologies with multiple criteria decision models. Our model links and assesses the adequacy of each treatment through the toxicity risk of side effects, in order to provide and explain to physicians a sorted list of possible antibiotics. We illustrate our approach through carefully selected case studies in collaboration with the EpiCURA Hospital Center in Belgium.