Original Investigation
Autonomous Oxygen Titration for Maintaining Normoxemia in Acutely Ill Adults: The SAVE-O2 AI Randomized Clinical Trial
David J. Douin, John D. Rice, Mengli Xiao, et al
JAMA Intern Med Published Online: August 3, 2026
doi: 10.1001/jamainternmed.2026.4023
Key Points
Question Can autonomous oxygen titration increase the proportion of time acutely ill adults receiving supplemental oxygen spend in a targeted normoxemia range (peripheral oxygen saturation 90%-96%) and decrease time spent in hypoxemia (peripheral oxygen saturation <88%)?
Findings In this randomized clinical trial among 300 acutely ill adults in 4 US hospitals, autonomous oxygen titration increased the proportion of time spent in normoxemia and decreased the proportion of time spent in hypoxemia compared to usual care.
Meaning Autonomous oxygen titration safely increased the time that acutely ill adults spent in a targeted normoxemia range compared with oxygen delivery in current clinical care.
Abstract
Importance 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.
Objective 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.
Design, Setting, and Participants 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.
Intervention 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.
Main Outcomes and Measures 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%).
Results 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.
Conclusions and Relevance 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.
Trial Registration ClinicalTrials.gov Identifier: NCT06374225
