Adrien Coulet

Antoine Neuraz, Ghislain Vaillant, Camila Arias et al.

Phenotyping consists in applying algorithms to identify individuals associated with a specific, potentially complex, trait or condition, typically out of a collection of Electronic Health Records (EHRs). Because a lot of the clinical information of EHRs are lying in texts, phenotyping from text takes an important role in studies that rely on the secondary use of EHRs. However, the heterogeneity and highly specialized aspect of both the content and form of clinical texts makes this task particularly tedious, and is the source of time and cost constraints in observational studies. To facilitate the development, evaluation and reproductibility of phenotyping pipelines, we developed an open-source Python library named medkit. It enables composing data processing pipelines made of easy-to-reuse software bricks, named medkit operations. In addition to the core of the library, we share the operations and pipelines we already developed and invite the phenotyping community for their reuse and enrichment. medkit is available at https://github.com/medkit-lib/medkit

Elisa Castagnari, Lillian Muyama, Adrien Coulet

In practice, clinicians achieve a diagnosis by following a sequence of steps, such as laboratory exams, observations, or imaging. The pathways to reach diagnosis decisions are documented by guidelines authored by expert organizations, which guide clinicians to reach a correct diagnosis through these sequences of steps. While these guidelines are beneficial for following medical reasoning and consolidating medical knowledge, they have some drawbacks. They often fail to address patients with uncommon conditions due to their focus on the majority population, and are slow and costly to update, making them unsuitable for rapidly emerging diseases or new practices. Inspired by clinical guidelines, our study aimed to develop pathways similar to those that can be obtained in clinical guidelines. We tested three Large Language Models (LLMs) -Generative Pretrained Transformer 4 (GPT-4), Large Language Model Meta AI (LLaMA), and Mistral -on a synthetic yet realistic dataset to differentially diagnose anemia and its subtypes. By using advanced prompting techniques to enhance the decision-making process, we generated diagnostic pathways using these models. Experimental results indicate that LLMs hold huge potential in clinical pathway discovery from patient data, with GPT-4 exhibiting the best performance in all conducted experiments.

Alberto Marfoglia, Jong Ho Jhee, Adrien Coulet

The application of machine learning on healthcare data is often hindered by the lack of standardized and semantically explicit representation, leading to limited interoperability and reproducibility across datasets and experiments. The Medical Event Data Standard (MEDS) addresses these issues by introducing a minimal, event-centric data model designed for reproducible machine-learning workflows from health data. However, MEDS is defined as a data-format specification and does not natively provide integration with the Semantic Web ecosystem. In this article, we introduce MEDS-OWL, a lightweight OWL ontology that provides formal concepts and relations to enable representing MEDS datasets as RDF graphs. Additionally, we implemented meds2rdf, a Python conversion library that transforms MEDS events into RDF graphs, ensuring conformance with the ontology. We demonstrate the approach on a synthetic clinical dataset that describes patient care pathways for ruptured intracranial aneurysms and validate the resulting graph using SHACL constraints. The first release of MEDS-OWL comprises 13 classes, 10 object properties, 20 data properties, and 24 OWL axioms. Combined with meds2rdf, it enables data transformation into FAIR-aligned datasets, provenance-aware publishing, and interoperability of event-based clinical data. By bridging MEDS with the Semantic Web, this work contributes a reusable semantic layer for event-based clinical data and establishes a robust foundation for subsequent graph-based analytics.

Safa Alsaidi, Tomás Brogueira, Nizar Mahlaoui et al.

Activated PI3K8 Syndrome (APDS) is a rare genetic immune disorder caused by variants in PIK3CD or PIK3R1, with highly heterogeneous symptoms that often delay diagnosis. Early recognition is hampered by overlapping clinical presentations and limited clinician awareness, motivating systematic, data-driven approaches to detect APDS-associated phenotypic patterns in routine electronic health records. Traditional linear scoring systems cannot capture complex symptom interactions, while deep learning models, though expressive, often lack interpretability. To bridge this gap, we propose Shapley regression, a novel game-theoretic model replacing the linear predictor with a k-additive cooperative game, explicitly modeling co-occurrence of symptoms while maintaining the transparency and convexity of logistic regression. We carry out an empirical study of our lightweight method on eight public biomedical datasets, showing that a 2-additive model with $l_{2}$ regularization achieves an optimal trade-off between predictive power and noise robustness. We also apply it to a real-world cohort of 222 patients, on which Shapley regression accurately distinguished APDS cases from matched controls, confirming and validating phenotypes known to be associated with APDS, and facilitating the exploration of pairwise interactions between symptoms, validated by clinical experts.

Lillian Muyama, Antoine Neuraz, Adrien Coulet

Background: Clinical diagnosis is typically reached by following a series of steps recommended by guidelines authored by colleges of experts. Accordingly, guidelines play a crucial role in rationalizing clinical decisions but suffer from limitations as they are built to cover the majority of the population and fail at covering patients with uncommon conditions. Moreover, their updates are long and expensive, making them unsuitable for emerging diseases and practices. Methods: Inspired by guidelines, we formulate the task of diagnosis as a sequential decision-making problem and study the use of Deep Reinforcement Learning (DRL) algorithms to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from Electronic Health Records (EHRs). We apply DRL on synthetic, but realistic EHRs and develop two clinical use cases: Anemia diagnosis, where the decision pathways follow the schema of a decision tree; and Systemic Lupus Erythematosus (SLE) diagnosis, which follows a weighted criteria score. We particularly evaluate the robustness of our approaches to noisy and missing data since these frequently occur in EHRs. Results: In both use cases, and in the presence of imperfect data, our best DRL algorithms exhibit competitive performance when compared to the traditional classifiers, with the added advantage that they enable the progressive generation of a pathway to the suggested diagnosis which can both guide and explain the decision-making process. Conclusion: DRL offers the opportunity to learn personalized decision pathways to diagnosis. We illustrate with our two use cases their advantages: they generate step-by-step pathways that are self-explanatory; and their correctness is competitive when compared to state-of-the-art approaches.

Thibaut Fabacher, Erik-André Sauleau, Emmanuelle Arcay et al.

Objective: To evaluate the accuracy, computational cost and portability of a new Natural Language Processing (NLP) method for extracting medication information from clinical narratives. Materials and Methods: We propose an original transformer-based architecture for the extraction of entities and their relations pertaining to patients' medication regimen. First, we used this approach to train and evaluate a model on French clinical notes, using a newly annotated corpus from Hôpitaux Universitaires de Strasbourg. Second, the portability of the approach was assessed by conducting an evaluation on clinical documents in English from the 2018 n2c2 shared task. Information extraction accuracy and computational cost were assessed by comparison with an available method using transformers. Results: The proposed architecture achieves on the task of relation extraction itself performance that are competitive with the state-of-the-art on both French and English (F-measures 0.82 and 0.96 vs 0.81 and 0.95), but reduce the computational cost by 10. End-to-end (Named Entity recognition and Relation Extraction) F1 performance is 0.69 and 0.82 for French and English corpus. Discussion: While an existing system developed for English notes was deployed in a French hospital setting with reasonable effort, we found that an alternative architecture offered end-to-end drug information extraction with comparable extraction performance and lower computational impact for both French and English clinical text processing, respectively. Conclusion: The proposed architecture can be used to extract medication information from clinical text with high performance and low computational cost and consequently suits with usually limited hospital IT resources

Pierre Epron, Adrien Coulet, Mehwish Alam

Despite their strong linguistic capabilities, Large Language Models (LLMs) are computationally demanding and require substantial resources for fine-tuning, which is unadapted to privacy and budget constraints of many healthcare settings. To address this, we present an experimental analysis focused on Biomedical Named Entity Recognition using lightweight LLMs, we evaluate the impact of different output formats on model performance. The results reveal that lightweight LLMs can achieve competitive performance compared to the larger models, highlighting their potential as lightweight yet effective alternatives for biomedical information extraction. Our analysis shows that instruction tuning over many distinct formats does not improve performance, but identifies several format consistently associated with better performance.

Safa Alsaidi, Marc Vincent, Olivia Boyer et al.

In this paper, we address the challenge of patient-note identification, which involves accurately matching an anonymized clinical note to its corresponding patient, represented by a set of related notes. This task has broad applications, including duplicate records detection and patient similarity analysis, which require robust patient-level representations. We explore various embedding methods, including Hierarchical Attention Networks (HAN), three-level Hierarchical Transformer Networks (HTN), LongFormer, and advanced BERT-based models, focusing on their ability to process mediumto-long clinical texts effectively. Additionally, we evaluate different pooling strategies (mean, max, and mean_max) for aggregating wordlevel embeddings into patient-level representations and we examine the impact of sliding windows on model performance. Our results indicate that BERT-based embeddings outperform traditional and hierarchical models, particularly in processing lengthy clinical notes and capturing nuanced patient representations. Among the pooling strategies, mean_max pooling consistently yields the best results, highlighting its ability to capture critical features from clinical notes. Furthermore, the reproduction of our results on both MIMIC dataset and Necker hospital data warehouse illustrates the generalizability of these approaches to real-world applications, emphasizing the importance of both embedding methods and aggregation strategies in optimizing patient-note identification and enhancing patient-level modeling.

Jong Ho Jhee, Alberto Megina, Pacôme Constant Dit Beaufils et al.

Background: With the increasing availability of healthcare data, predictive modeling finds many applications in the biomedical domain, such as the evaluation of the level of risk for various conditions, which in turn can guide clinical decision making. However, it is unclear how knowledge graph data representations and their embedding, which are competitive in some settings, could be of interest in biomedical predictive modeling. Method: We simulated synthetic but realistic data of patients with intracranial aneurysm and experimented on the task of predicting their clinical outcome. We compared the performance of various classification approaches on tabular data versus a graph-based representation of the same data. Next, we investigated how the adopted schema for representing first individual data and second temporal data impacts predictive performances. Results: Our study illustrates that in our case, a graph representation and Graph Convolutional Network (GCN) embeddings reach the best performance for a predictive task from observational data. We emphasize the importance of the adopted schema and of the consideration of literal values in the representation of individual data. Our study also moderates the relative impact of various time encoding on GCN performance.

Lillian Muyama, Estelle Lu, Geoffrey Cheminet et al.

Clinical diagnostic guidelines outline the key questions to answer to reach a diagnosis. Inspired by guidelines, we aim to develop a model that learns from electronic health records to determine the optimal sequence of actions for accurate diagnosis. Focusing on anemia and its sub-types, we employ deep reinforcement learning (DRL) algorithms and evaluate their performance on both a synthetic dataset, which is based on expert-defined diagnostic pathways, and a real-world dataset. We investigate the performance of these algorithms across various scenarios. Our experimental results demonstrate that DRL algorithms perform competitively with state-of-the-art methods while offering the significant advantage of progressively generating pathways to the suggested diagnosis, providing a transparent decision-making process that can guide and explain diagnostic reasoning.

Lillian Muyama, Antoine Neuraz, Adrien Coulet

Clinical diagnosis guidelines aim at specifying the steps that may lead to a diagnosis. Inspired by guidelines, we aim to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from electronic health records. We apply various deep reinforcement learning algorithms to this task and experiment on a synthetic but realistic dataset to differentially diagnose anemia and its subtypes and particularly evaluate the robustness of various approaches to noise and missing data. Experimental results show that the deep reinforcement learning algorithms show competitive performance compared to the state-of-the-art methods with the added advantage that they enable the progressive generation of a pathway to the suggested diagnosis, which can both guide and explain the decision process.

Emmanuel Bresso, Pierre Monnin, Cédric Bousquet et al.

Adverse Drug Reactions (ADRs) are characterized within randomized clinical trials and postmarketing pharmacovigilance, but their molecular mechanism remains unknown in most cases. Aside from clinical trials, many elements of knowledge about drug ingredients are available in open-access knowledge graphs. In addition, drug classifications that label drugs as either causative or not for several ADRs, have been established. We propose to mine knowledge graphs for identifying biomolecular features that may enable reproducing automatically expert classifications that distinguish drug causative or not for a given type of ADR. In an explainable AI perspective, we explore simple classification techniques such as Decision Trees and Classification Rules because they provide human-readable models, which explain the classification itself, but may also provide elements of explanation for molecular mechanisms behind ADRs. In summary, we mine a knowledge graph for features; we train classifiers at distinguishing, drugs associated or not with ADRs; we isolate features that are both efficient in reproducing expert classifications and interpretable by experts (i.e., Gene Ontology terms, drug targets, or pathway names); and we manually evaluate how they may be explanatory. Extracted features reproduce with a good fidelity classifications of drugs causative or not for DILI and SCAR. Experts fully agreed that 73% and 38% of the most discriminative features are possibly explanatory for DILI and SCAR, respectively; and partially agreed (2/3) for 90% and 77% of them. Knowledge graphs provide diverse features to enable simple and explainable models to distinguish between drugs that are causative or not for ADRs. In addition to explaining classifications, most discriminative features appear to be good candidates for investigating ADR mechanisms further.

Walid Hafiane, Joel Legrand, Yannick Toussaint et al.

Relation extraction (RE) consists in identifying and structuring automatically relations of interest from texts. Recently, BERT improved the top performances for several NLP tasks, including RE. However, the best way to use BERT, within a machine learning architecture, and within a transfer learning strategy is still an open question since it is highly dependent on each specific task and domain. Here, we explore various BERT-based architectures and transfer learning strategies (i.e., frozen or fine-tuned) for the task of biomedical RE on two corpora. Among tested architectures and strategies, our *BERT-segMCNN with finetuning reaches performances higher than the state-of-the-art on the two corpora (1.73 % and 32.77 % absolute improvement on ChemProt and PGxCorpus corpora respectively). More generally, our experiments illustrate the expected interest of fine-tuning with BERT, but also the unexplored advantage of using structural information (with sentence segmentation), in addition to the context classically leveraged by BERT.

Pierre Monnin, Chedy Raïssi, Amedeo Napoli et al.

Knowledge graphs are freely aggregated, published, and edited in the Web of data, and thus may overlap. Hence, a key task resides in aligning (or matching) their content. This task encompasses the identification, within an aggregated knowledge graph, of nodes that are equivalent, more specific, or weakly related. In this article, we propose to match nodes within a knowledge graph by (i) learning node embeddings with Graph Convolutional Networks such that similar nodes have low distances in the embedding space, and (ii) clustering nodes based on their embeddings, in order to suggest alignment relations between nodes of a same cluster. We conducted experiments with this approach on the real world application of aligning knowledge in the field of pharmacogenomics, which motivated our study. We particularly investigated the interplay between domain knowledge and GCN models with the two following focuses. First, we applied inference rules associated with domain knowledge, independently or combined, before learning node embeddings, and we measured the improvements in matching results. Second, while our GCN model is agnostic to the exact alignment relations (e.g., equivalence, weak similarity), we observed that distances in the embedding space are coherent with the ``strength'' of these different relations (e.g., smaller distances for equivalences), letting us considering clustering and distances in the embedding space as a means to suggest alignment relations in our case study.

Pierre Monnin, Emmanuel Bresso, Miguel Couceiro et al.

Features mined from knowledge graphs are widely used within multiple knowledge discovery tasks such as classification or fact-checking. Here, we consider a given set of vertices, called seed vertices, and focus on mining their associated neighboring vertices, paths, and, more generally, path patterns that involve classes of ontologies linked with knowledge graphs. Due to the combinatorial nature and the increasing size of real-world knowledge graphs, the task of mining these patterns immediately entails scalability issues. In this paper, we address these issues by proposing a pattern mining approach that relies on a set of constraints (e.g., support or degree thresholds) and the monotonicity property. As our motivation comes from the mining of real-world knowledge graphs, we illustrate our approach with PGxLOD, a biomedical knowledge graph.

Pierre Monnin, Miguel Couceiro, Amedeo Napoli et al.

An increasing number of data and knowledge sources are accessible by human and software agents in the expanding Semantic Web. Sources may differ in granularity or completeness, and thus be complementary. Consequently, they should be reconciled in order to unlock the full potential of their conjoint knowledge. In particular, units should be matched within and across sources, and their level of relatedness should be classified into equivalent, more specific, or similar. This task is challenging since knowledge units can be heterogeneously represented in sources (e.g., in terms of vocabularies). In this paper, we focus on matching n-ary tuples in a knowledge base with a rule-based methodology. To alleviate heterogeneity issues, we rely on domain knowledge expressed by ontologies. We tested our method on the biomedical domain of pharmacogenomics by searching alignments among 50,435 n-ary tuples from four different real-world sources. Results highlight noteworthy agreements and particularities within and across sources.

Stephen Pfohl, Ben Marafino, Adrien Coulet et al.

Guidelines for the management of atherosclerotic cardiovascular disease (ASCVD) recommend the use of risk stratification models to identify patients most likely to benefit from cholesterol-lowering and other therapies. These models have differential performance across race and gender groups with inconsistent behavior across studies, potentially resulting in an inequitable distribution of beneficial therapy. In this work, we leverage adversarial learning and a large observational cohort extracted from electronic health records (EHRs) to develop a "fair" ASCVD risk prediction model with reduced variability in error rates across groups. We empirically demonstrate that our approach is capable of aligning the distribution of risk predictions conditioned on the outcome across several groups simultaneously for models built from high-dimensional EHR data. We also discuss the relevance of these results in the context of the empirical trade-off between fairness and model performance.