Causal Bayesian machine learning to assess treatment effect heterogeneity by dexamethasone dose for patients with COVID-19 and severe hypoxemia

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Dokumenter

  • Fulltext

    Forlagets udgivne version, 1,17 MB, PDF-dokument

The currently recommended dose of dexamethasone for patients with severe or critical COVID-19 is 6 mg per day (mg/d) regardless of patient features and variation. However, patients with severe or critical COVID-19 are heterogenous in many ways (e.g., age, weight, comorbidities, disease severity, and immune features). Thus, it is conceivable that a standardized dosing protocol may not be optimal. We assessed treatment effect heterogeneity in the COVID STEROID 2 trial, which compared 6 mg/d to 12 mg/d, using a causal inference framework with Bayesian Additive Regression Trees, a flexible modeling method that detects interactive effects and nonlinear relationships among multiple patient characteristics simultaneously. We found that 12 mg/d of dexamethasone, relative to 6 mg/d, was probably associated with better long-term outcomes (days alive without life support and mortality after 90 days) among the entire trial population (i.e., no signals of harm), and probably more beneficial among those without diabetes mellitus, that were older, were not using IL-6 inhibitors at baseline, weighed less, or had higher level respiratory support at baseline. This adds more evidence supporting the use of 12 mg/d in practice for most patients not receiving other immunosuppressants and that additional study of dosing could potentially optimize clinical outcomes.
OriginalsprogEngelsk
Artikelnummer6570
TidsskriftScientific Reports
Vol/bind13
Udgave nummer1
Antal sider10
ISSN2045-2322
DOI
StatusUdgivet - 2023

Bibliografisk note

Funding Information:
AG, MWM, MHM, and AP are affiliated with the Department of Intensive Care at Copenhagen University Hospital–Rigshospitalet, which has received funding for other projects from the Novo Nordisk Foundation, Sygeforsikringen “danmark”, Pfizer, and Fresenius Kabi, and conducts contract research for AM-Pharma. MSH reports receiving grants from the NIHR, MRC, EME, HTA, Huo Foundation, and highlights industry support for TRAITS research program (a Chief Scientists Office, Scotland funded time critical precision medicine in adult critically ill patients (TRAITS Program). Out with this work, MSH acknowledges that any income received from advisory boards and data safety monitoring board are paid directly to unrestricted university research funds. No other authors have conflict of interest.

Funding Information:
The COVID STEROID 2 trial was funded by Novo Nordisk Foundation and the Research Council of Rigshospitalet. The funders had no role in the design, conduct, analyses or reporting of the trial or this secondary study. MS-H is funded by a clinician scientist fellowship from the National Institute for Health Research [CS-2016-16-011]. FL and MOH are funded by the United States National Institutes of Health, National Heart, Lung, and Blood Institute (grant number R01-HL168202).

Publisher Copyright:
© 2023, The Author(s).

ID: 358791884