Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Apr 9;331(14):1195-1204.
doi: 10.1001/jama.2024.2933.

Individualized Treatment Effects of Oxygen Targets in Mechanically Ventilated Critically Ill Adults

Kevin G Buell  1 , Alexandra B Spicer  2 , Jonathan D Casey  3 , Kevin P Seitz  3 , Edward T Qian  3 , Emma J Graham Linck  2 , Wesley H Self  4   5 , Todd W Rice  3   5 , Pratik Sinha  6   7 , Paul J Young  8   9   10   11 , Matthew W Semler  3   5 , Matthew M Churpek  2
Affiliations

Individualized Treatment Effects of Oxygen Targets in Mechanically Ventilated Critically Ill Adults

Kevin G Buell et al. JAMA. .

Abstract

Importance: Among critically ill adults, randomized trials have not found oxygenation targets to affect outcomes overall. Whether the effects of oxygenation targets differ based on an individual's characteristics is unknown.

Objective: To determine whether an individual's characteristics modify the effect of lower vs higher peripheral oxygenation-saturation (Spo2) targets on mortality.

Design, setting, and participants: A machine learning model to predict the effect of treatment with a lower vs higher Spo2 target on mortality for individual patients was derived in the Pragmatic Investigation of Optimal Oxygen Targets (PILOT) trial and externally validated in the Intensive Care Unit Randomized Trial Comparing Two Approaches to Oxygen Therapy (ICU-ROX) trial. Critically ill adults received invasive mechanical ventilation in an intensive care unit (ICU) in the United States between July 2018 and August 2021 for PILOT (n = 1682) and in 21 ICUs in Australia and New Zealand between September 2015 and May 2018 for ICU-ROX (n = 965).

Exposures: Randomization to a lower vs higher Spo2 target group.

Main outcome and measure: 28-Day mortality.

Results: In the ICU-ROX validation cohort, the predicted effect of treatment with a lower vs higher Spo2 target for individual patients ranged from a 27.2% absolute reduction to a 34.4% absolute increase in 28-day mortality. For example, patients predicted to benefit from a lower Spo2 target had a higher prevalence of acute brain injury, whereas patients predicted to benefit from a higher Spo2 target had a higher prevalence of sepsis and abnormally elevated vital signs. Patients predicted to benefit from a lower Spo2 target experienced lower mortality when randomized to the lower Spo2 group, whereas patients predicted to benefit from a higher Spo2 target experienced lower mortality when randomized to the higher Spo2 group (likelihood ratio test for effect modification P = .02). The use of a Spo2 target predicted to be best for each patient, instead of the randomized Spo2 target, would have reduced the absolute overall mortality by 6.4% (95% CI, 1.9%-10.9%).

Conclusion and relevance: Oxygenation targets that are individualized using machine learning analyses of randomized trials may reduce mortality for critically ill adults. A prospective trial evaluating the use of individualized oxygenation targets is needed.

PubMed Disclaimer

Conflict of interest statement

Conflict of Interest Disclosures: Ms Spicer reported being an employee of the University of Wisconsin Data Science Laboratory in the Department of Medicine, which is supported by grants from the Department of Defense and the National Institute of General Medical Sciences outside the submitted work. Dr Casey reported receiving travel support from Fisher & Paykel outside the submitted work. Dr Qian reported receiving speaker fees from Karl Storx Endoscopy outside the submitted work. Dr Graham Linck reported receiving a training grant from the National Institutes of Health during the conduct of the study. Dr Rice reported receiving personal fees for serving as director of medical affairs of Cumberland Pharmaceuticals Inc, as a member of the data and safety monitoring board of Sanofi, and as a consultant for Cytovale Inc outside the submitted work. Dr Sinha reported receiving personal fees from AstraZeneca and Prenosis Inc outside the submitted work. Dr Semler reported receiving personal fees for serving on the advisory board of Baxter International outside the submitted work. Dr Churpek reported receiving grants from the Department of Defense and the National Institute of General Medical Sciences outside the submitted work, having patent 11,410,777 to the University of Chicago for eCART (electronic cardiac arrest risk triage), an early warning score not used in this work, with royalties from the University of Chicago. No other disclosures were reported.

Figures

Figure 1.
Figure 1.. Predicted Individualized Treatment Effects of Lower vs Higher Oxygen-Saturation Targets on Mortality
A, The y-axis displays the effect of treatment with a lower vs a higher peripheral oxygen-saturation (Spo2) target on 28-day mortality in the Intensive Care Unit Randomized Trial Comparing Two Approaches to Oxygen Therapy (ICU-ROX) trial. For 100 of the 965 patients in the ICU-ROX trial, a colored line displays how the treatment effect predicted for that patient changed from the average treatment effect (point estimate and 95% CI at the far left) to the final predicted individualized treatment effect (point estimate at the far right) with the sequential addition of the patient’s values for the each of the 10 most-important baseline patient characteristics. B, Displays the distribution of predicted individualized treatment effects for all 965 patients in the ICU-ROX trial.
Figure 2.
Figure 2.. Absolute Risk Difference in 28-Day Mortality Between the Lower and Higher Spo2 Target Groups by Predicted Individualized Treatment Effect
A, Displays the value of the predicted individualized treatment effect generated by the model derived from the Pragmatic Investigation of Optimal Oxygen Targets (PILOT) trial for each of the 965 patients in the Intensive Care Unit Randomized Trial Comparing Two Approaches to Oxygen Therapy (ICU-ROX) trial. Patients were ranked from the lowest value on the left to the highest value on the right. B, For patients in the lower third, middle third, and upper third of predicted individualized treatment effect, the absolute risk difference in the incidence of 28-day mortality between patients randomized to the lower Spo2 group and the higher Spo2 group is shown (colored dots) with 95% CIs (whiskers). The predicted individualized treatment effect (lower, middle, or higher third) modified the effect of randomized Spo2 group assignment on the incidence of 28-day mortality (P value for interaction = .02).
See this image and copyright information in PMC

Comment in

References

    1. Schjørring OL, Klitgaard TL, Perner A, et al. ; HOT-ICU Investigators . Lower or higher oxygenation targets for acute hypoxemic respiratory failure. N Engl J Med. 2021;384(14):1301-1311. doi:10.1056/NEJMoa2032510 - DOI - PubMed
    1. Semler MW, Casey JD, Lloyd BD, et al. ; PILOT Investigators and the Pragmatic Critical Care Research Group . Oxygen-saturation targets for critically ill adults receiving mechanical ventilation. N Engl J Med. 2022;387(19):1759-1769. doi:10.1056/NEJMoa2208415 - DOI - PMC - PubMed
    1. Mackle D, Bellomo R, Bailey M, et al. ; ICU-ROX Investigators and the Australian and New Zealand Intensive Care Society Clinical Trials Group; ICU-ROX Investigators the Australian and New Zealand Intensive Care Society Clinical Trials Group . Conservative oxygen therapy during mechanical ventilation in the ICU. N Engl J Med. 2020;382(11):989-998. doi:10.1056/NEJMoa1903297 - DOI - PubMed
    1. Girardis M, Busani S, Damiani E, et al. . Effect of conservative vs conventional oxygen therapy on mortality among patients in an intensive care unit: the oxygen-ICU randomized clinical trial. JAMA. 2016;316(15):1583-1589. doi:10.1001/jama.2016.11993 - DOI - PubMed
    1. Schmidt H, Kjaergaard J, Hassager C, et al. . Oxygen targets in comatose survivors of cardiac arrest. N Engl J Med. 2022;387(16):1467-1476. doi:10.1056/NEJMoa2208686 - DOI - PubMed

Publication types