Matthieu Doutreligne

Matthieu Doutreligne

Auto-generated profile, based on publicly available information

Matthieu Doutreligne

Affiliations Soda Team, Inria Saclay, Palaiseau, France, Mission Data, Haute Autorité de Santé, Saint-Denis, France

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
6 July 2023 in PLOS Digital Health
Verified
Journal Article
Open access
PDF file
MDMatthieu Doutreligne
Matthieu Doutreligne
ADAdeline Degremont
Adeline Degremont
PJPierre-Alain Jachiet
Pierre-Alain Jachiet
ALAntoine Lamer
Antoine Lamer
XTXavier Tannier
Xavier Tannier
Real-world data (RWD) bears great promises to improve the quality of care. However, specific infrastructures and methodologies are required to derive robust knowledge and brings innovations to the patient. Drawing upon the national case study of the 32 French regional and university hospitals governance, we highlight key aspects of modern clinical data warehouses (CDWs): governance, transparency, types of data, data reuse, technical tools, documentation, and data quality control processes. Semi-structured interviews as well as a review of reported studies on French CDWs were conducted in a semi-structured manner from March to November 2022. Out of 32 regional and university hospitals in France, 14 have a CDW in production, 5 are experimenting, 5 have a prospective CDW project, 8 did not have any CDW project at the time of writing. The implementation of CDW in France dates from 2011 and accelerated in the late 2020. From this case study, we draw some general guidelines for CDWs. The actual orientation of CDWs towards research requires efforts in governance stabilization, standardization of data schema, and development in data quality and data documentation. Particular attention must be paid to the sustainability of the warehouse teams and to the multilevel governance. The transparency of the studies and the tools of transformation of the data must improve to allow successful multicentric data reuses as well as innovations in routine care.

17 October 2022 in JMIR Medical Informatics
Verified
Journal Article
Open access
ALAntoine Lamer
Antoine Lamer
MFMathilde Fruchart
Mathilde Fruchart
NPNicolas Paris
Nicolas Paris
BPBenjamin Popoff
Benjamin Popoff
APAnaïs Payen
Anaïs Payen
ECEmmanuel Chazard
Emmanuel Chazard
Background: Despite the many opportunities data reuse offers, its implementation presents many difficulties, and raw data cannot be reused directly. Information is not always directly available in the source database and needs to be computed afterwards with raw data for defining an algorithm. Objective: The main purpose of this article is to present a standardized description of the steps and transformations required during the feature extraction process when conducting retrospective observational studies. A secondary objective is to identify how the features could be stored in the schema of a data warehouse. Methods: This study involved the following 3 main steps: (1) the collection of relevant study cases related to feature extraction and based on the automatic and secondary use of data; (2) the standardized description of raw data, steps, and transformations, which were common to the study cases; and (3) the identification of an appropriate table to store the features in the Observation Medical Outcomes Partnership (OMOP) common data model (CDM). Results: We interviewed 10 researchers from 3 French university hospitals and a national institution, who were involved in 8 retrospective and observational studies. Based on these studies, 2 states (track and feature) and 2 transformations (track definition and track aggregation) emerged. “Track” is a time-dependent signal or period of interest, defined by a statistical unit, a value, and 2 milestones (a start event and an end event). “Feature” is time-independent high-level information with dimensionality identical to the statistical unit of the study, defined by a label and a value. The time dimension has become implicit in the value or name of the variable. We propose the 2 tables “TRACK” and “FEATURE” to store variables obtained in feature extraction and extend the OMOP CDM. Conclusions: We propose a standardized description of the feature extraction process. The process combined the 2 steps of track definition and track aggregation. By dividing the feature extraction into these 2 steps, difficulty was managed during track definition. The standardization of tracks requires great expertise with regard to the data, but allows the application of an infinite number of complex transformations. On the contrary, track aggregation is a very simple operation with a finite number of possibilities. A complete description of these steps could enhance the reproducibility of retrospective studies.

3 February 2025 in PLOS Digital Health
Verified
Journal Article
Open access
PDF file
MDMatthieu Doutreligne
Matthieu Doutreligne
TSTristan Struja
Tristan Struja
JAJudith Abecassis
Judith Abecassis
CMClaire Morgand
Claire Morgand
LCLeo Anthony Celi
Leo Anthony Celi
GVGaël Varoquaux
Gaël Varoquaux
Causal inference enables machine learning methods to estimate treatment effects of medical interventions from electronic health records (EHRs). The prevalence of such observational data and the difficulty for randomized controlled trials (RCT) to cover all population/treatment relationships make these methods increasingly attractive for studying causal effects. However, researchers should be wary of many pitfalls. We propose and illustrate a framework for causal inference estimating the effect of albumin on mortality in sepsis using an Intensive Care database (MIMIC-IV) and comparing various sensitivity analyses to results from RCTs as gold-standard. The first step is study design, using the target trial concept and the PICOT framework: Population (patients with sepsis), Intervention (combination of crystalloids and albumin for fluid resuscitation), Control (crystalloids only), Outcome (28-day mortality), Time (intervention start within 24h of admission). We show that too large treatment-initiation times induce immortal time bias. The second step is selection of the confounding variables based on expert knowledge. Increasingly adding confounders enables to recover the RCT results from observational data. As the third step, we assess the influence of multiple models with varying assumptions, showing that a doubly robust estimator (AIPW) with random forests proved to be the most reliable estimator. Results show that these steps are all important for valid causal estimates. A valid causal model can then be used to individualize decision making: subgroup analyses showed that treatment efficacy of albumin was better for patients >60 years old, males, and patients with septic shock. Without causal thinking, machine learning is not enough for optimal clinical decision on an individual patient level. Our step-by-step analytic framework helps avoiding many pitfalls of applying machine learning to EHR data, building models that avoid shortcuts and extract the best decision-making evidence.

6 January 2025 in GigaScience
Verified
Journal Article
Open access
MDMatthieu Doutreligne
Matthieu Doutreligne
GVGaël Varoquaux
Gaël Varoquaux
Background: We investigate which procedure selects the most trustworthy predictive model to explain the effect of an intervention and support decision-making. Methods: We study a large variety of model selection procedures in practical settings: finite samples settings and without a theoretical assumption of well-specified models. Beyond standard cross-validation or internal validation procedures, we also study elaborate causal risks. These build proxies of the causal error using “nuisance” reweighting to compute it on the observed data. We evaluate whether empirically estimated nuisances, which are necessarily noisy, add noise to model selection and compare different metrics for causal model selection in an extensive empirical study based on a simulation and 3 health care datasets based on real covariates. Results: Among all metrics, the mean squared error, classically used to evaluate predictive modes, is worse. Reweighting it with a propensity score does not bring much improvement in most cases. On average, the $R\text{-risk}$, which uses as nuisances a model of mean outcome and propensity scores, leads to the best performances. Nuisance corrections are best estimated with flexible estimators such as a super learner. Conclusions: When predictive models are used to explain the effect of an intervention, they must be evaluated with different procedures than standard predictive settings, using the $R\text{-risk}$ from causal inference.

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

21 August 2023 in medRxiv
Verified
Preprint
Open access
PDF file
ARAdam Remaki
Adam Remaki
BPBenoît Playe
Benoît Playe
PBPaul Bernard
Paul Bernard
SVSimon Vittoz
Simon Vittoz
MDMatthieu Doutreligne
Matthieu Doutreligne
RBRomain Bey
Romain Bey
Objectives To propose a new method to account for time-dependent data missingness caused by the increasing digitization of health records in the analysis of large-scale clinical data. Materials and Methods Following a data-driven approach we modeled the progressive adoption of a common electronic health record in 38 hospitals. To this end, we analyzed data collected between 2013 and 2022 and made available in the clinical data warehouse of the Greater Paris University Hospitals. Depending on the category of data, we worked either at the hospital, department or unit level. We evaluated the performance of this model with a retrospective cohort study. We measured the temporal variations of some quality and epidemiological indicators by successively applying two methods, either a naive analysis or a novel complete-source-only analysis that accounts for digitization-induced missingness. Results Unrealistic temporal variations of quality and epidemiological indicators were observed when a naive analysis was performed, but this effect was either greatly reduced or disappeared when the complete-source-only method was applied. Discussion We demonstrated that a data-driven approach can be used to account for missingness induced by the progressive digitization of health records. This work focused on hospitalization, emergency department and intensive care units records, along with diagnostic codes, discharge prescriptions and consultation reports. Other data categories may require specific modeling of their associated data sources. Conclusions Electronic health records are constantly evolving and new methods should be developed to debias studies that use these unstable data sources.