Automation

Automated Oxygen System Keeps Hospital Patients in Target Range 85% of Time

University of Colorado trial shows autonomous titration outperforms manual adjustments while reducing clinician workload.

Omega Editorial· August 4, 2026· 3 min read

An automated oxygen delivery system maintained hospitalized patients in their target oxygen saturation range 85 percent of the time compared with 63 percent under standard clinician-managed care, according to results from a multicenter clinical trial led by the University of Colorado Anschutz.

The SAVE-O2 AI trial, published in JAMA Internal Medicine, enrolled 300 adults receiving supplemental oxygen at four U.S. hospitals. Patients were randomly assigned to either conventional oxygen therapy managed by nurses and respiratory therapists or autonomous titration using the O2matic PRO100 device, which continuously monitors oxygen levels via pulse oximetry and adjusts flow rates in real time.

How the automated system performed

Patients treated with the automated system spent significantly less time experiencing both hypoxemia (dangerously low oxygen) and hyperoxemia (excessively high oxygen). The device required fewer manual adjustments by clinical staff and produced no increase in serious adverse events compared with standard care.

"Oxygen is one of the most widely used therapies in medicine yet even in 2026, it is still managed largely through repeated manual adjustments made by clinicians," said Adit Ginde, senior associate dean for clinical research and professor of emergency medicine at the CU Anschutz School of Medicine and principal investigator of the study.

The trial included adults hospitalized with acute respiratory illness, traumatic injury, burns, and surgical recovery. In current practice, oxygen levels are typically adjusted during periodic nursing checks, allowing saturation to drift outside target ranges between assessments. The automated system uses a fingertip pulse oximeter to measure oxygen continuously and adjust delivery without waiting for clinician input.

Why it matters

Maintaining precise oxygen levels is critical but difficult in hospital settings. Too little oxygen can damage organs; too much may also cause harm. An automated system that reduces the manual burden on nurses and respiratory therapists while improving clinical outcomes addresses both patient safety and healthcare workforce constraints. The technology shows particular promise for military medicine, where medics must manage multiple urgent tasks simultaneously in resource-limited environments.

Military and emergency applications

The research reflects broader efforts through the CU Anschutz Combat Medicine Research Center to improve oxygen therapy across care settings. Vik Bebarta, chair of emergency medicine and founding director of the center, noted the technology's potential in combat casualty care: "When you are caring for a wounded service member hours from a hospital, oxygen runs short and so does the medic's attention. A device that adjusts oxygen on its own takes one urgent task off their hands."

The research team plans to evaluate the technology in emergency transport and prehospital settings, where rapid decision-making and limited staffing make manual oxygen management particularly challenging.

The study was conducted in collaboration with UCHealth University of Colorado Hospital, Vanderbilt University Medical Center, Oregon Health & Science University, and Wake Forest University School of Medicine. Details were first reported by News-Medical and presented simultaneously at the Military Health System Research Symposium.

#automated oxygen delivery#hospital automation#clinical ai#respiratory care#military medicine#healthcare ai

This is an original analysis by the Omega editorial team. Source reporting: Automation Watch.

Want systems like this working for your business?

Book a Call

More in Automation

Automation· 3 min read

Comau pivots to battery, energy automation after Stellantis split

The industrial robotics firm sees newly independent status as a springboard into sectors where automation spending will top 25% of capex.

Via Automation Watch · Jul 28, 2026
Automation· 3 min read

Google Study: Workers Use AI to Assist, Not Replace Themselves

Analysis of 15 million Gemini interactions reveals AI handles low-expertise tasks while humans retain control of complex work.

Via Automation Watch · Jul 28, 2026
Automation· 4 min read

Leena AI rebuilt its platform twice to reach 70% ticket deflection

Three first-time founders pivoted from HR chatbot to enterprise agentic AI, tripling revenue while keeping headcount flat.

Via Automation Watch · Jul 28, 2026