Boris Delange

Boris Delange

Auto-generated profile, based on publicly available information

Boris Delange

Univ Rennes, CHU Rennes, INSERM, LTSI-UMR 1099, Rennes, France

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2024 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
ALAntoine Lamer
Antoine Lamer
BPBenjamin Popoff
Benjamin Popoff
BDBoris Delange
Boris Delange
MDMatthieu Doutreligne
Matthieu Doutreligne
ECEmmanuel Chazard
Emmanuel Chazard
PQPaul Quindroit
Paul Quindroit

10 March 2025 in International Journal of Medical Informatics
Verified
Journal Article
Closed access
BDBoris Delange
Boris Delange
BPBenjamin Popoff
Benjamin Popoff
TSThibault Séité
Thibault Séité
ALAntoine Lamer
Antoine Lamer
APAdrien Parrot
Adrien Parrot

13 June 2025 in Intensive Care Medicine
Verified
Journal Article
Closed access
PDF file
BPBenjamin Popoff
Benjamin Popoff
ABAlexandre Bourgeois
Alexandre Bourgeois
BDBoris Delange
Boris Delange
MPMichael Poette
Michael Poette
APAdrien Parrot
Adrien Parrot

22 August 2024
Verified
Book Chapter
Open access
PDF file
BDBoris Delange
Boris Delange
GBGuillaume Bouzille
Guillaume Bouzille
IGIsabelle Gouin
Isabelle Gouin
YLYoann Launey
Yoann Launey
AMAlexandre Mansour
Alexandre Mansour
AMAdel Maamar
Adel Maamar
Continuous unfractionated heparin is widely used in intensive care, yet its complex pharmacokinetic properties complicate the determination of appropriate doses. To address this challenge, we developed machine learning models to predict over- and under-dosing, based on anti-Xa results, using a monocentric retrospective dataset. The random forest model achieved a mean AUROC of 0.80 [0.77-0.83], while the XGB model reached a mean AUROC of 0.80 [0.76-0.83]. Feature importance was employed to enhance the interpretability of the model, a critical factor for clinician acceptance. After prospective validation, machine learning models such as those developed in this study could be implemented within a computerized physician order entry (CPOE) as a clinical decision support system (CDSS).

15 May 2025
Verified
Book Chapter
Open access
PDF file
CPCarlos Luis Parra-Calderón
Carlos Luis Parra-Calderón
CACelia Alvarez-Romero
Celia Alvarez-Romero
MGMaría González-López
María González-López
SRSilvia Rodríguez-Mejías
Silvia Rodríguez-Mejías
KCKirsten Colpaert
Kirsten Colpaert
CJChristian Jung
Christian Jung
This work aims to identify the Key Research Areas for building and deploying the semantic interoperability framework for the Intensive Medicine Data Space in Europe. A set of European experts defined four research areas and associated challenges: i) to characterize the value of Common Data Models, vocabularies and standardized data elements for creating the foundation for the standardization of Intensive Care Unit (ICU) data sets, ii) to derive the Common Data Model ensuring seamless data interoperability supporting the querying and access to high-quality, multi-modal data located on federated nodes according to the FAIR principles, iii) to define and support the data standardization process enabling efficient secondary use of ICU data set during the execution of key decision support use cases through the Intensive Medicine Data Space in Europe and beyond, and iv) to define requirements for anonymization and pseudonymization for the good balance between data protection and innovation.

26 March 2026 in JMIR Medical Informatics
Verified
Journal Article
Open access
CDChuanming Dong
Chuanming Dong
BDBoris Delange
Boris Delange
APAlex Poiron
Alex Poiron
MAMohamed El Azzouzi
Mohamed El Azzouzi
CFClément François
Clément François
SCSandie Cabon
Sandie Cabon
Background: Clinical data warehouses store large volumes of unstructured text containing valuable information about patients’ medical status. Traditional extraction systems based on named entity recognition (NER) identify medical terms but often fail to capture the contextual cues needed for accurate interpretation. Existing approaches to context-aware extraction differ in their reliance on expert annotation, computational power, and lexical resources, leading to uneven feasibility across institutions. Combined with heterogeneity in documentation practices and data-sharing restrictions, these limitations hinder the scalability and reuse of trained models. There is thus a need for practical frameworks that can be deployed and adapted locally within medical institutions. Objective: This study aimed to introduce the Medical Status Extraction Pipeline (MSEP) , a methodological framework that extracts patients’ medical status from clinical narratives through sentence classification and supports the local deployment of hybrid extractors, illustrated through an institutional case study. Methods: MSEP extracts medical status by classifying sentences into predefined categories (presence , absence, or unknown) for each targeted condition. The pipeline combines modules for data selection, expert annotation, and model development, with parameters customizable to different settings. It was applied within our institutional environment on 6 conditions: smoking, hypertension, diabetes, heart failure, chronic obstructive pulmonary disease, and family history of cancer, using 12,119 manually annotated sentences from the eHOP Clinical Data Warehouse (Rennes University Hospital). Three types of extractors were compared: fine-tuned CamemBERT, large language model (LLM) prompt, and a rule-based baseline, evaluated through stratified 3-fold cross-validation, measuring precision, recall, specificity, macro F -score, balanced accuracy, as well as manual annotation time and model inference speed. Results: Among the tested approaches, the CamemBERT-based extractor achieved the best overall performance, with macro F -scores above 0.94 for 5 of the 6 medical conditions. The study also highlights that when a medical status is very sparsely represented in the training data, rule-based extractors can outperform learned models (average macro F -score 0.94 vs 0.73 for family history of cancer). This shows the pragmatic value of choosing the extraction method according to data availability. Manual annotation time per sentence ranged from 1.2 to 2.9 seconds within the pipeline (2.23 to 4.25 seconds for informative sentences), compared with 7.8 to 16.5 seconds for named entity recognition–based systems. In our institutional experiments, the minimum time to complete all pipeline modules, from dataset construction to final extractor refinement, was 8 hours. Conclusions: In our institutional case study, MSEP enabled rapid construction of datasets and extractors across multiple clinical conditions while reducing the effort required for local development. Its modular and configurable design allowed the adoption of hybrid extraction approaches and adaptation to different resource settings. These features highlight MSEP’s value as a research tool and upstream component that facilitates local deployment of clinical information extraction workflows.