Scientists have found a cheap and easy way of 1 a condition from recordings of people sleeping. Severe snoring is the sound of a sleeper fighting for 2 . Lots of people snore, but the loud and 3 snoring caused by a condition known as 4 sleep apnea, OSA, can leave a sufferer 5 and fuddled during the day.
OSA is costly and 6 to diagnose, and it"s difficult to distinguish genuine OSA from 7 snoring. But a team in Brazil has a simpler solution: they have found a way of analyzing snore recordings that is able not only to 8 OSA but can distinguish between mild and 9 cases.
Diagnosing OSA from snore sounds is not a new idea. The question is how the clinical condition is revealed by the 10 . In 2008, a team in Turkey showed that the statistical 11 of snores has the 12 to discriminate ordinary sleepers from OSA 13 .
Scientists looked for 14 patterns in OSA and the snore 15 can be used as a pretty reliable 16 for the AHI (the apnea-hypopnea index). And "snore 17 " is measured by a Hurst exponent, which reveals 18 patterns in a series of events. An 19 computer analysis of the snore series could "learn" to use the Hurst exponent to distinguish 19 from severe cases of OSA, making the correct diagnosis for 16 of 17 patients.