AI HELPS FIND UNTAPPED HEALTH PREDICTORS IN SLEEP STUDIES
Analyzing routine sleep study data with artificial intelligence reveals a wealth of biomarkers predictive of a much broader range of health risks than doctors usually identify, researchers have found.
Polysomnograms, or in-lab sleep studies, are typically performed to look for obstructive sleep apnea, a common disorder in which throat muscles relax and repeatedly block the airway during sleep.
The studies collect data on breathing, brain and muscle activity and other factors, but doctors generally focus on the apnea-hypopnea index, or the average number of breathing pauses and shallow breathing events per hour.
For the new study, investigators tasked AI with uncovering hidden physiologic patterns in more than 10,000 full-night sleep studies and linking the patterns with long-term clinical outcomes in patients’ medical records. AI, using a wealth of data typically ignored during such studies, identified five clinically meaningful patient subtypes, each with sharply different long-term health risks, they reported in Nature.
For example, patients whose sleep data patterns put them in the highest-risk group for serious health issues had twice the odds of death over the next five years compared to those in the lowest-risk group, a distinction not captured by the apnea-hypopnea index.
In this most at-risk group, odds were 65% higher for heart failure, 84% higher for heart attack, 93% higher for cognitive impairment, and more than 200% higher for atrial fibrillation and for epilepsy, compared to odds in the lowest-risk group.
AI predicted outcomes well for men and women, while the apnea-hypopnea index has historically performed better in men, the researchers noted.
Their model was equally accurate when they tested it in a separate nationwide cohort of more than 6,000 patients, they said.
“For decades we have distilled an overnight sleep study into a handful of summary measures,” study leader Dr. Reena Mehra of the University of Washington said in a statement.
“AI gives us the opportunity to move beyond those summaries and learn from the full richness of sleep physiology.”
AI IMPROVES OXYGEN DELIVERY IN HOSPITAL PATIENTS
Using artificial intelligence to automate oxygen delivery increases the time patients spend getting the proper amount, a new study shows. Patients in the automated group spent 85% of their time in the target oxygen range compared with 63% in the standard care group, researchers reported at the Military Health System Research Symposium and in JAMA Internal Medicine.
“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,” study leader Dr. Adit Ginde of the CU Anschutz School of Medicine in Aurora, Colorado, said in a statement.
The researchers enrolled 300 adults receiving supplemental oxygen at four U.S. hospitals. They received either standard clinician-managed oxygen therapy or autonomous oxygen titration via PRO100, developed by Denmark-based O2matic, which continuously monitors oxygen levels via a small sensor placed on the fingertip and adjusts oxygen flow in real time.
Patients in the AI-assisted group spent less time with low oxygen levels and less time with high oxygen levels, and they required fewer manual oxygen adjustments by clinical staff, with no increase in serious adverse events, the researchers reported.
Their work informs ongoing military-supported efforts to improve oxygen delivery in high-stress environments, they said.
“When you are caring for a wounded service member hours from a hospital, oxygen runs short and so does the medic’s attention,” study coauthor Dr. Vik Bebarta, director of the CU Anschutz Combat Medicine Research Center and a U.S. Air Force Reserve colonel, said in a statement.
“A device that adjusts oxygen on its own takes one urgent task off their hands so they can focus on everything else the patient needs,” he said.
NON-OPIOID DRUG BEATS VICODIN FOR ABDOMINAL SURGERY PAIN
An experimental non-opioid pain medicine was more effective than the commonly prescribed opioid Vicodin at relieving pain from abdominal surgery, according to results of a mid-stage trial. The drug, LTG-001 from Latigo Biotherapeutics, was also significantly more effective than a placebo, the primary goal of the study published in The New England Journal of Medicine.
LTG-001 is a selective Nav 1.8 inhibitor, part of a new class of non-opioid analgesics designed to block pain signals throughout the body.
The researchers enrolled 343 patients with moderate or severe pain after abdominal surgery and randomly assigned them to receive high or low doses of LTG-001, a placebo, or Vicodin.
High-dose LTG-001 achieved significant pain improvement over 48 hours compared to the placebo, with the strongest effect ever reported in a study of non-opioid painkillers versus placebo for abdominal surgery, the researchers said.
High-dose LTG-001 had about 50% greater analgesic effect than Vicodin, they found.
Slightly more than half of the high-dose group remained opioid-free throughout the 48-hour treatment period, compared to 22% in the placebo group.
Adverse events were mostly mild to moderate, according to the report.
“These published results of LTG-001 add to the growing body of evidence supporting the investigation of novel, non-opioid mechanisms for pain management at a time when there remains significant focus on addressing the public health impact of opioid use,” study coauthor Dr. Harold Minkowitz of the University of Texas MD Anderson Cancer Center in Houston said in a statement.
