EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Step-by-step causal analysis of EHRs to ground decision-making

Matthieu Doutreligne iD, Tristan Struja, Judith Abecassis, Claire Morgand, Leo Anthony Celi, Gaël Varoquaux

PLOS Digital Health · 03.02.2025 · 4 (2) · e0000721

DOI: 10.1371/journal.pdig.0000721 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 03.02.2025. Verfasst von Matthieu Doutreligne und 5 weiteren Autor:innen. Beteiligte Einrichtung: Soda Team, Inria Saclay, Palaiseau, France. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 93 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIBIB NIH HHS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Autor:innen und Institutionen

  • Soda Team, Inria Saclay, Palaiseau, France.
  • Mission Data, Haute Autorité de Santé, Saint-Denis, France.
  • Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America.
  • Medical University Clinic, Division of Endocrinology, Diabetes & Metabolism, Kantonsspital Aarau, Aarau, Switzerland.
  • Agence Régionale de Santé Ile-de-France, Saint-Denis, France.
  • Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, United States of America.

ORCID-Profile: Matthieu Doutreligne

Förderung

  • NIBIB NIH HHS

Zitieren

APA

Doutreligne, M., Struja, T., Abecassis, J., Morgand, C., Celi, L. A., & Varoquaux, G. (2025). Step-by-step causal analysis of EHRs to ground decision-making. PLOS Digital Health, 4(2), e0000721. https://doi.org/10.1371/journal.pdig.0000721

Vancouver

Doutreligne M, Struja T, Abecassis J, Morgand C, Celi LA, Varoquaux G. Step-by-step causal analysis of EHRs to ground decision-making. PLOS Digital Health. 2025;4(2):e0000721. doi:10.1371/journal.pdig.0000721

BibTeX
@article{Doutreligne2025,
  author = {Doutreligne, Matthieu and Struja, Tristan and Abecassis, Judith and Morgand, Claire and Celi, Leo Anthony and Varoquaux, Gaël},
  title = {Step-by-step causal analysis of EHRs to ground decision-making},
  journal = {PLOS Digital Health},
  year = {2025},
  volume = {4},
  number = {2},
  pages = {e0000721},
  doi = {10.1371/journal.pdig.0000721}
}
Kostenlos starten →