Autonomous Oxygen Titration for Maintaining Normoxemia in Acutely Ill Adults: The SAVE-O2 AI Randomized Clinical Trial.

Authors

David J Douin, John D Rice, Mengli Xiao, Laurel E Beaty, Claire J Guo, Cori Withers, Amy Sullivan, Erin L Anderson, Alex C Cheng, Mary K Banasiewicz, Matthew W Semler, Bradley D Lloyd, Amelia W Maiga, Kevin W Gibbs, Gregory R Stettler, Akram Khan, Mitchell B Sally, Franklin L Wright, Arek J Wiktor, Neil R Aggarwal, Vikhyat S Bebarta, Adit A Ginde, SAVE-O AI Investigators

Published in

JAMA internal medicine. Aug 03, 2026. Epub Aug 03, 2026.

Abstract

For acutely ill adults who are hospitalized with hypoxemia, supplemental oxygen is titrated to maintain normoxemia. In current practice, clinicians intermittently titrate oxygen, potentially exposing patients to hypoxemia and hyperoxemia between assessments. Autonomous oxygen titration may address these challenges by independently titrating supplemental oxygen flow to maintain peripheral oxygen saturation (Spo2) within a predefined range.
To determine whether autonomous oxygen titration increases the proportion of time spent in a targeted normoxemia range compared with usual care in acutely ill adults.
This multicenter, unblinded, parallel-group, randomized clinical trial was conducted at 4 US hospitals from May 6, 2024, to November 17, 2025, among adults hospitalized for acute respiratory illness, trauma, burn, or acute care surgery who were receiving supplemental oxygen.
Patients were randomly assigned to receive oxygen titration via either autonomous oxygen titration or usual care (manual oxygen titration by clinicians) during the first 72 hours after randomization.
The primary outcome was the proportion of time spent within the targeted normoxemia range (Spo2 90%-96%). The key secondary outcome was the proportion of time spent in hypoxemia (Spo2 <88%).
Among 300 patients randomized and included in the trial population (median [IQR] age, 66 (55-75) years; 162 [54%] female), 152 were assigned to autonomous oxygen titration and 148 to usual care. Participants represented a range of skin pigmentation categories defined by the Monk Skin Tone Scale, including 67 (22%) categorized as light, 168 (56%) as medium, and 65 (22%) as dark. The mean (SE) proportion of time spent in normoxemia was greater in the autonomous oxygen titration group than in the usual care group (85% [1%] vs 63% [2%]; adjusted risk difference [RD], 21 percentage points [pp]; 95% CI, 18-25 pp; P < .001). The mean (SE) proportion of time spent in hypoxemia was lower in the autonomous oxygen titration group than in the usual care group (2.0% [0.2%] vs 3.6% [0.4%]; adjusted RD, -1.3 pp; 95% CI, -2.0 to -0.5 pp; P = .002). The mean (SE) proportion of time spent in hyperoxemia (Spo2 >96%) was 9.2% (1.0%) in the autonomous oxygen titration group and 29.1% (1.7%) in the usual care group. The mean (SE) proportion of time spent in borderline hypoxemia (Spo2 88%-89%) was 3.4% (0.3%) in the autonomous oxygen titration group and 4.0% (0.4%) in the usual care group. Results were consistent across prespecified subgroups.
In this randomized clinical trial among adults hospitalized with an acute illness or injury and receiving supplemental oxygen, autonomous oxygen titration substantially increased the proportion of time spent in normoxemia and decreased time spent in hypoxemia compared with usual care.
ClinicalTrials.gov Identifier: NCT06374225.

PMID:
42546017
Bibliographic data and abstract were imported from PubMed on 04 Aug 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.