Faced with the challenges of patient confidentiality and scientific reproducibility, research on machine learning for health is turning towards the conception of synthetic medical databases. This article presents a brief overview of state-of-the-art machine learning methods for generating synthetic tabular and textual data, focusing their application to the automatic classification of trauma mechanisms, followed by our proposed methodology for generating high-quality, synthetic medical records combining tabular and unstructured text data. 1 Introduction

The article "Revelations: A Decidable Class of POMDP with Omega-Regular Objectives" won an Outstanding Paper Award at the AAAI 2025 conference, a prestigious international conference about artificial intelligence. This year, only three papers received such an award out of 3,000 accepted and 12,000 submitted! This recognition crowns the results of research initiated in Bordeaux (France) within the Synthèse team at the Bordeaux Computer Science Research Laboratory (LaBRI), where four of the authors work: Marius Belly, Nathanaël Fijalkow, Hugo Gimbert, and Pierre Vandenhove. The work also involved researchers from Paris (Florian Horn) and Antwerp (Guillermo A. Pérez). The article is freely available on arXiv, and this post outlines its main ideas.

Since the release of ChatGPT in November 2022, large language models (LLMs) have seen considerable success, including in the open-source community, with many open-weight models available. However, the requirements to deploy such a service are often unknown and difficult to evaluate in advance. To facilitate this process, we conducted numerous tests at the Centre Inria de l'Universit\'e de Bordeaux. In this article, we propose a comparison of the performance of several models of different sizes (mainly Mistral and LLaMa) depending on the available GPUs, using vLLM, a Python library designed to optimize the inference of these models. Our results provide valuable information for private and public groups wishing to deploy LLMs, allowing them to evaluate the performance of different models based on their available hardware. This study thus contributes to facilitating the adoption and use of these large language models in various application domains.

Characterizing anomalous diffusion is crucial in order to understand the evolution of complex stochastic systems, from molecular interactions to cellular dynamics. In this work, we characterize the performances regarding such a task of Bi-Mamba, a novel state-space deep-learning architecture articulated with a bidirectional scan mechanism. Our implementation is tested on the AnDi-2 challenge datasets among others. As such, our results indicate the potential practical use of the Bi-Mamba architecture for anomalousdiffusion characterization. Deep-learning methods for advanced microscopy have thus emerged as a promising change of paradigm [13].

This research embarked on a comparative exploration of the holistic segmentation capabilities of Convolutional Neural Networks (CNNs) in both 2D and 3D formats, focusing on cystic fibrosis (CF) lesions. The study utilized data from two CF reference centers, covering five major CF structural changes. Initially, it compared the 2D and 3D models, highlighting the 3D model's superior capability in capturing complex features like mucus plugs and consolidations. To improve the 2D model's performance, a loss adapted to fine structures segmentation was implemented and evaluated, significantly enhancing its accuracy, though not surpassing the 3D model's performance. The models underwent further validation through external evaluation against pulmonary function tests (PFTs), confirming the robustness of the findings. Moreover, this study went beyond comparing metrics; it also included comprehensive assessments of the models' interpretability and reliability, providing valuable insights for their clinical application.

This year's RoboCup kicked off on 4 July and will run until 10 July. Taking place in Bordeaux, the event will see around 2500 participants, from 45 different countries take part in competitions, training sessions, and a symposium. Find out what attendees have been up to in preparation for, and in the first half of, the event. The arenas are being prepared. Wishing all the best to Team ORIon-UTBMan as they compete at #RoboCup2023 in France!

Be part of our mission to disrupt the healthcare and democratize the data driven medicine! SOPHiA GENETICS is looking for a Data Management Intern to join the Clinical Operations (ClinOps) Team to support activities related to multimodal projects leveraging on the aggregation of clinical, biological, imaging and genomics data. Combining high-quality data for each individual to generate multimodal insights, SOPHiA GENETICS harnesses the power of advanced AI and machine learning models. You will gain and benefit from experience in clinical study management across a wide range of trainings and activities involvement (regulatory, data management, biostatistics, legal, quality, finance, etc). You will be joining an organisation with the patient at the heart of every decision and action, driven by purpose as we drive exponential growth.

To efficiently perform inference with neural networks, the underlying tensor programs require sufficient tuning efforts before being deployed into production environments. Usually, enormous tensor program candidates need to be sufficiently explored to find the one with the best performance. This is necessary to make the neural network products meet the high demand of real-world applications such as natural language processing, auto-driving, etc. Auto-schedulers are being developed to avoid the need for human intervention. However, due to the gigantic search space and lack of intelligent search guidance, current auto-schedulers require hours to days of tuning time to find the best-performing tensor program for the entire neural network. In this paper, we propose HARL, a reinforcement learning (RL) based auto-scheduler specifically designed for efficient tensor program exploration. HARL uses a hierarchical RL architecture in which learning-based decisions are made at all different levels of search granularity. It also automatically adjusts exploration configurations in real-time for faster performance convergence. As a result, HARL improves the tensor operator performance by 22% and the search speed by 4.3x compared to the state-of-the-art auto-scheduler. Inference performance and search speed are also significantly improved on end-to-end neural networks.

Would you like to join a dynamic and exciting health-tech company that uses cutting edge technologies to deliver a world changing solution that has a direct impact on the lives of cancer and rare disease patients worldwide? Join our growing team in Pessac (near Bordeaux, France) and use your exceptional abilities and knowledge skills to help us deliver on our mission of democratizing Data-Driven Medicine. We are looking for a talented and motivated Data Scientist / Biostatistician in Pessac (near Bordeaux, France)! SOPHiA GENETICS introduced the SOPHiA DDM platform height years ago. Today, the solution not only enables to integrate and visualize multiple data modalities, such as clinical, biological, genomics or medical-image data, but also to process relevant multimodal features and obtain multimodal insights using statistical learning.

In our journey to impact patient lives, we are looking for a Junior Data Scientist (6 months Internship) to join our Data Science-Radiomics Research team in Pessac (33, Bordeaux). SOPHiA GENETICS aims at developing Data-driven medicine, by delivering pathology and treatment-specific multimodal predictive signatures to help clinician making their decisions in the patient care path. This multimodal approach relies on the aggregation of different types of medical data and on advanced machine learning and deep learning models to process and analyze them. The Data Science – Radiomics Research teams, based in Pessac (Gironde, France), are involved in a key project about lung cancer, for the purpose of predicting treatment response and patient survival. In this context, an intern position is open for February 2023, to develop specific deep-learning-based algorithms for medical image automatic processing.