An automated algorithm to analyze nocturnal blood oxygen levels of children at risk for obstructive sleep apnea (OSA) may increase the diagnosis of this unhealthy condition, particularly in areas of the world that lack the resources to do overnight sleep studies, according to new research published online in the American Thoracic Society’s American Journal of Respiratory and Critical Care Medicine.
In “Nocturnal Oximetry-Based Evaluation of Habitually Snoring Children,” an international group of researchers led by David Gozal, MD, MBA, Herbert T. Abelson Professor of Pediatrics at the University of Chicago and immediate past- president of the American Thoracic Society, report on an automated neural network algorithm they developed to detect OSA based on data from an oximeter, a simple fingertip device to measure oxygen levels. They found that the algorithm’s ability to detect obstructive sleep apnea in children compared favorably to polysomnography, the diagnostic gold standard.
Pediatric sleep apnea affects at least three to five percent of all children. It has been shown to affect children’s behavior and their cognitive and physical development, including increasing their risk of hypertension and metabolic disease, which can lead to diabetes and cardiovascular disease later in life. Snoring regularly is a risk factor for OSA in children; however, only a small percentage of children who snore actually have OSA.
“Both in the U.S. and around the world, the vast majority of children with OSA are not diagnosed because of the scarcity of pediatric sleep laboratories and the costs associated with such tests,” Dr. Gozal said. “At the same time, many children with sleep apnea symptoms undergo surgical removal of tonsils and adenoids–the current standard of care treatment for pediatric OSA–even if they would not fulfill the criteria for OSA if they had been tested.”
The study authors wanted to address both issues—under diagnosis of OSA and unnecessary surgery–by developing a simple, accurate and inexpensive screening tool that could be used for all children who snore.
Previous studies using nocturnal oximetry as a screening tool for OSA found that the test had high specificity (it produced few false positives), but limited sensitivity (there were too many false negatives). The goal of the current study was to produce results with both high sensitivity and high specificity from 23 features of the oximetry recordings using an automated neural network algorithm. Neural networks are computing systems that can recognize patterns and reach conclusions much the way the human brain does.
Dr. Gozal and his colleagues compared data from both noctural oximetry studies and polysomnography performed on 4,191 children, ages 2 to 18, who were referred to 13 pediatric sleep laboratories around the world because they habitually snored or had other signs of OSA. The polysomnography study was considered definitive, and the researchers compared the apnea-hypopnea index (AHI), which measures the number of stopped or shallow breaths per hour, from those studies to the AHI obtained from the automated neural network algorithm.
The study found that the algorithm’s diagnostic ability increased with OSA severity. The algorithm’s diagnostic accuracy at:
-
AHI = 1 was 75.2 percent
-
AHI = 5 was 81.7 percent, and
-
AHI = 10 was 90.2 percent.
The authors noted that the increased reliability of their automated methodology corresponded to the “more widely used and clinically relevant cutoff criteria of OSA,” an AHI ≥ 5, which would allow clinicians using the algorithm to “confidently both confirm and discard cases that would or would not fulfill OSA criteria” in most cases.
The relatively small proportion of children with OSA not diagnosed by the algorithm, the authors argue, could be retested within weeks or a few months if their symptoms persisted. They added that even if some children need to be retested, the algorithm would likely be highly cost effective because the automated approach could be conducted at about one-tenth to one-twentieth the cost of polysomnography.
“Of course before widespread adoption and implementation, this test will need to be validated by conducting studies with children at home to make sure that the automated system continues to perform at the same high level of reliability,” Dr. Gozal said.
“At a time when preventive medicine and health care cost containments are at the forefront of policymaker agendas, this new approach could represent a game-changing opportunity,” he added. “It may enable correct treatment of a very frequent disease and prevent the serious health consequences that it causes later in adulthood.”
The Consejería de Educación de la Junta de Castilla y León, the European Regional Development Fund, the Ministerio de Economía y Competitividad and the Sociedad Española de Neumología y Cirugía Torácica supported some of the investigators involved in this study.
Be the first to comment