BKBayrem Kaabachi

Bayrem Kaabachi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bayrem Kaabachi has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Evaluating Differentially Private Synthetic Data for Multi-Site Clinical Research: A Case Study from 5 Swiss University Hospitals

    by Bayrem Kaabachi, Jeremie Despraz, Jean Regina, Alessandro Mari, David Brüggemann, Paul Rolland, Federico Amato, Jean Louis Raisaro

    Multi-site clinical initiatives within infrastructures like the Swiss Personalized Health Network (SPHN) are essential for impactful research, but privacy regulations and significant inter-institutional heterogeneity pose major barriers to data sharing. The SPHN-LUCID NDS (National Data Stream) project, which creates a FAIR-principles-based cohort to monitor low-value care for medical inpatients across five Swiss university hospitals, exemplifies this real-world challenge. Our study investigates the viability of using Differentially Private (DP) synthetic data generation to create a high-fidelity, shareable version of this sensitive and complex dataset. We generated multiple synthetic cohorts using a range of privacy-loss budgets, allowing for a direct analysis of the trade-off between privacy guarantees and data utility. We evaluated the preservation of local, per-hospital heterogeneous data patterns, which is the key challenge for any federated analysis. This work provides a practical measure of the specific impact of the privacy budget on the statistical fidelity of a real-world, multi-site clinical dataset.

  • Open Access

    Tunable Privacy Risk Evaluation of Generative Adversarial Networks

    by Bayrem Kaabachi, Farah Briki, Bogdan Kulynych, Jérémie Despraz, Jean Louis Raisaro

    Generative machine learning models such as Generative Adversarial Networks (GANs) have been shown to be especially successful in generating realistic synthetic data in image and tabular domains. However, it has been shown that such generative models, as well as the generated synthetic data, can reveal information contained in their privacy-sensitive training data, and therefore must be carefully evaluated before being used. The gold standard method through which such privacy leakage can be estimated is simulating membership inference attacks (MIAs), in which an attacker attempts to learn whether a given sample was part of the training data of a generative model. The state-of-the art MIAs against generative models, however, rely on strong assumptions (knowledge of the exact training dataset size), or require a lot of computational power (to retrain many “surrogate” generative models), which make them hard to use in practice. In this work, we propose a technique for evaluating privacy risks in GANs which exploits the outputs of the discriminator part of the standard GAN architecture. We evaluate our attacks in terms of performance in two synthetic image generation applications in radiology and ophthalmology, showing that our technique provides a more complete picture of the threats by performing worst-case privacy risk estimation and by identifying attacks with higher precision than the prior work.


  • Open Access

    Accelerating Clinical Text Annotation in Underrepresented Languages: A Case Study on Text De-Identification

    by He A. Xu, Valentin Loftsson, Bogdan Kulynych, Bayrem Kaabachi, Jean Louis Raisaro

    Clinical notes contain valuable information for research and monitoring quality of care. Named Entity Recognition (NER) is the process for identifying relevant pieces of information such as diagnoses, treatments, side effects, etc., and bring them to a more structured form. Although recent advancements in deep learning have facilitated automated recognition, particularly in English, NER can still be challenging due to limited specialized training data. This exacerbated in hospital settings where annotations are costly to obtain without appropriate incentives and often dependent on local specificities. In this work, we study whether this annotation process can be effectively accelerated by combining two practical strategies. First, we convert usually passive annotation tasks into a proactive contest to motivate human annotators in performing a task often considered tedious and time-consuming. Second, we provide pre-annotations for the participants to evaluate how recall and precision of the pre-annotations can boost or deteriorate annotation performance. We applied both strategies to a text de-identification task on French clinical notes and discharge summaries at a large Swiss university hospital. Our results show that proactive contest and average quality pre-annotations can significantly speed up annotation time and increase annotation quality, enabling us to develop a text de-identification model for French clinical notes with high performance (F1 score 0.94).


  • Open Access

    Evaluating Synthetic Data Augmentation to Correct for Data Imbalance in Realistic Clinical Prediction Settings

    by Nina Wahler, Bayrem Kaabachi, Bogdan Kulynych, Jérémie Despraz, Christian Simon, Jean Louis Raisaro

    Predictive modeling holds a large potential in clinical decision-making, yet its effectiveness can be hindered by inherent data imbalances in clinical datasets. This study investigates the utility of synthetic data for improving the performance of predictive modeling on realistic small imbalanced clinical datasets. We compared various synthetic data generation methods including Generative Adversarial Networks, Normalizing Flows, and Variational Autoencoders to the standard baselines for correcting for class underrepresentation on four clinical datasets. Although results show improvement in F1 scores in some cases, even over multiple repetitions, we do not obtain statistically significant evidence that synthetic data generation outperforms standard baselines for correcting for class imbalance. This study challenges common beliefs about the efficacy of synthetic data for data augmentation and highlights the importance of evaluating new complex methods against simple baselines.