Sleep Apnea: Wearables, Home Tests, and Who Should Test

TL;DR: Your watch is good at raising a hand and bad at giving an all-clear. The Apple Watch and Samsung apnea features are cleared to flag signs of moderate-to-severe apnea and push you toward testing, and they do that job well, but a quiet watch misses a large share of true cases, so silence is not reassurance. If something flags you, or if you snore heavily, stop breathing at night, wake up unrefreshed, run blood pressure that will not come down, or have atrial fibrillation, get a medical sleep test. Home kits suit healthy people with obvious symptoms and tend to undercount, so a normal home result plus a convincing story means you need the lab, not relief. One claim to resist: treating apnea helps you sleep, feel, and function better and lowers blood pressure, but the big trials did not show it prevents heart attacks or strokes in people who were not sleepy. And since December 2024 there is a drug for it, tirzepatide, for people whose apnea rides on obesity.

How common is sleep apnea, and how many people miss it?

Your airway narrows or closes while you sleep. Airflow stops, your oxygen drops, and your brain hauls you up toward waking just enough to open your throat again. Then it repeats, sometimes hundreds of times before morning.

Close to a billion adults worldwide have at least the mild form, around 936 million people between 30 and 69, and about 425 million have it at the moderate-to-severe end.¹ In the United States, roughly 13 percent of middle-aged men and 6 percent of women carry the moderate-to-severe version.²

Now the part I find hard to get past. When researchers went looking, about 82 percent of men and 93 percent of women who had moderate-to-severe apnea had never been diagnosed, and the undiagnosed share still runs near 80 percent today.³ Nobody is being careless. Snoring reads as a nuisance, you cannot watch yourself breathe, and feeling wrecked at 3 PM gets filed under work stress or getting older. Carrying extra weight is the strongest driver you can change, and risk rises with age and runs higher in men, but you can have none of those and still have apnea. That is most of the reason it hides.

Can my Apple Watch or Oura ring detect sleep apnea?

No. Your watch cannot diagnose you, and it was never cleared to. What it can do is tell you to go get tested, and it turns out that is useful.

Take the Apple Watch. It reads tiny wrist movements that track with interrupted breathing, collects them over about a month, and pings you when the pattern looks like moderate-to-severe apnea. Apple's validation put its specificity near 98 percent, so when it fires, believe it. Sensitivity was about 66 percent overall and around 43 percent for moderate cases.⁴ Sit with that second number for a second. It means a silent watch misses something like a third of true apnea overall, and more than half of the moderate cases. Samsung's Galaxy Watch feature, the first cleared in the United States, works off the blood-oxygen sensor over two nights and comes out in the same place: it flags, it does not diagnose, and it will miss milder disease.

Oura and Whoop sit further out. They are wellness trackers, not cleared apnea tests, and the oxygen readings come from consumer sensors rather than medical oximeters. A choppy overnight oxygen trace is a reason to ask the question. It is not the answer.

So: a flag means test. And a quiet reading in someone who snores, gasps, and wakes up exhausted means nothing at all.

What is the AHI, and what do the numbers mean?

Get tested and you will come back with an AHI, the apnea-hypopnea index, which counts your breathing events per hour of sleep. An apnea is airflow essentially stopping for ten seconds or more. A hypopnea is a partial drop that costs you oxygen or jolts you toward waking. Under 5 is normal, 5 to 15 is mild, 15 to 30 is moderate, and over 30 is severe. You may also see an oxygen desaturation index, which counts how often your oxygen falls, and that is roughly what your watch is trying to approximate.

Hold the number loosely. One events-per-hour figure flattens a complicated night. It leaves out how far your oxygen fell or how long it stayed down, and that turns out to matter more: a measure called hypoxic burden tracks cardiovascular risk better than the raw count does.⁸ The AHI also moves depending on which scoring rule the lab used to define a hypopnea, so the same night can come back with two different numbers. And it knows nothing about how you feel. I have seen two people with an AHI of 20 who needed very different things.

Does treating sleep apnea protect your heart?

Probably not, and this is where I would ask you to be careful, because the internet says otherwise with a lot of confidence.

Start with what holds up. Untreated apnea travels with high blood pressure that resists medication, atrial fibrillation, stroke, heart disease, insulin resistance, daytime crashes, car accidents, and higher mortality in severe cases.⁵ Those links are consistent and they make biological sense. The leap is assuming that treating the apnea undoes the risk.

Researchers tested that leap three times. Three randomized trials put people with moderate-to-severe apnea and either established heart disease or a recent cardiac event on CPAP, the mask that splints the airway open with air pressure. None of the three cut heart attacks, strokes, or cardiovascular death.⁶¹¹¹²

There are fair objections. People wore the mask about three hours a night, under the four hours usually thought necessary, and a mask on the nightstand cannot help anybody. The trials also mostly left out the very sleepy, who are the ones most likely to benefit. So this is not proof that CPAP does nothing for the heart. It is proof that the confident version of the claim has never been demonstrated, and the observational studies that suggest otherwise are mostly comparing people who stick with therapy against people who do not, which is a comparison between two kinds of patient as much as two treatments.

Here is what treatment reliably delivers, and it is plenty: less daytime sleepiness, less snoring, better quality of life, and lower blood pressure. Atrial fibrillation follows a similar pattern, with untreated apnea tracking more recurrences after ablation and treatment associated with better rhythm control, though that evidence is observational too.¹³ Treat your apnea to sleep better, feel better, and help your blood pressure and your rhythm. Do not treat it believing you have bought insurance against a heart attack.

Home sleep test or the sleep lab: which do you need?

Two routes, and the match matters more than most people expect. A home sleep apnea test is a small kit you wear in your own bed, recording airflow, breathing effort, oxygen, and heart rate. A full in-lab study, polysomnography, adds sensors for brain waves, eye movement, and muscle activity, so it knows when you are asleep, can stage that sleep, and can catch central apnea and other causes of shallow breathing that a home kit cannot see.

The sleep-medicine guideline draws the line clearly.⁷ Home testing is for an otherwise healthy adult with a high pretest probability of moderate-to-severe apnea and none of the complicating conditions. It is the wrong tool if you have heart failure, serious lung or neuromuscular disease, chronic opioid use, or suspected central apnea, and all of those belong in a lab.

One limitation is worth carrying with you. A home kit cannot tell sleep from lying awake, so it averages your events across the entire recording rather than across the hours you slept, and it undercounts, with false-negative rates reported up to about 17 percent. Which gives you the rule I use: a normal home test in somebody with a convincing story does not rule apnea out. It sends you to the lab.

Who should get tested?

Testing follows symptoms and risk, so start with the symptoms. Loud habitual snoring. Someone telling you that you stop breathing. Waking up gasping or choking. Sleep that never restores you. Sleepiness heavy enough to make driving or working unsafe. Morning headaches and getting up repeatedly to urinate often ride along. Two findings move you up the list fast: blood pressure that will not come down on several medications, and atrial fibrillation. A questionnaire called STOP-BANG is a decent triage tool that catches most true cases and over-flags plenty of others, so it points toward testing rather than settling anything.

The people we miss are the ones who do not look the part. Women often present with fatigue, insomnia, or low mood instead of the dramatic witnessed pause, and get undercounted for it. Lean people get apnea through the shape of the jaw, palate, and airway, so a normal weight clears nothing. Plenty of people with confirmed apnea are not particularly sleepy. If you have been telling yourself you are not heavy and not tired so this cannot be you, that reasoning does not hold.

The other direction matters too. The US Preventive Services Task Force does not recommend screening adults who have no symptoms at all, judging the evidence insufficient to weigh benefit against harm.⁹ That is about screening the symptom-free, and it says nothing against working up somebody who has symptoms.

What are the treatment options if you do have it?

More options than the mask everybody pictures. CPAP holds the airway open with gentle pressure and remains the most effective treatment and the usual first move, and its weakness is tolerance, since a treatment only works while you are wearing it. A custom oral appliance that pulls the lower jaw forward works well for milder disease and for people who cannot manage CPAP. Positional strategies help when your apnea shows up mostly on your back. An implanted nerve stimulator is available for selected people who fail CPAP. And weight loss can change the disease itself when weight is what is driving it.

The newest option is a genuine change. In 2024, a large trial gave tirzepatide, a GLP-1-based weight-loss medication, to adults who had moderate-to-severe apnea alongside obesity. It cut events by roughly 25 to 29 an hour, against a few per hour on placebo, with close to a fifth of body weight lost. The FDA approved it as Zepbound for that group in December 2024.¹⁰

Keep it in proportion. It was studied only in people with obesity, it does nothing about the jaw and airway anatomy that causes apnea in lean people, and plenty of people who improved did not reach a normal AHI. It is a genuine addition to the toolkit. It is not a cure.

Guidance from the Clinic

"The wearable era has been good for sleep apnea in one way: it gets people asking. When a patient shows me an apnea flag from their watch, I take it seriously, because those flags rarely fire without reason. What I also tell them is the other half of the truth, that a quiet watch proves nothing, so if you snore, stop breathing at night, wake up unrefreshed, or your blood pressure will not come down, we test you regardless of what the device says. I pick the test to fit the person: a home kit for a healthy patient with obvious symptoms, a sleep lab when there is heart or lung disease or when a home test comes back normal but the story does not add up. And I am careful about the promise I make. Treating apnea will very likely help you feel better, sleep better, and get your blood pressure down, and that is worth doing. What I will not tell you is that it will prevent a heart attack, because the big trials did not show that. Honest expectations are part of good care here."

Related at Fishtown Medicine

• Your Apple Watch Says You Might Have AFib. Now What? - the companion "your watch flagged something" question, and the apnea-AFib link
• Tirzepatide (Zepbound, Mounjaro) - the drug now approved for obesity-related sleep apnea
• Sleep Apnea in Fit Men - apnea, testosterone, and why lean athletes are missed
• Sleep: The Foundation of Recovery - sleep architecture, HRV, and what wearables track well
• Sleep Disorders Treatment in Philadelphia - how we evaluate and treat sleep problems in the practice
• When the Adhesive Is the Problem - skin reactions to monitor patches, sensors, and watch bands, and how to wear them longer

Scientific References

1. Benjafield AV, Ayas NT, Eastwood PR, et al. "Estimation of the Global Prevalence and Burden of Obstructive Sleep Apnoea: A Literature-Based Analysis." Lancet Respiratory Medicine. 2019;7(8):687-698.
2. Peppard PE, Young T, Barnet JH, et al. "Increased Prevalence of Sleep-Disordered Breathing in Adults." American Journal of Epidemiology. 2013;177(9):1006-1014.
3. Young T, Evans L, Finn L, Palta M. "Estimation of the Clinically Diagnosed Proportion of Sleep Apnea Syndrome in Middle-Aged Men and Women." Sleep. 1997;20(9):705-706.
4. Apple Inc. "Estimating Sleep Apnea Risk from Breathing Disturbances: Sleep Apnea Notification Feature Performance." Validation white paper, 2024. (FDA 510(k) K240929.)
5. Yaggi HK, Concato J, Kernan WN, et al. "Obstructive Sleep Apnea as a Risk Factor for Stroke and Death." New England Journal of Medicine. 2005;353(19):2034-2041.
6. McEvoy RD, Antic NA, Heeley E, et al. "CPAP for Prevention of Cardiovascular Events in Obstructive Sleep Apnea (SAVE)." New England Journal of Medicine. 2016;375(10):919-931.
7. Kapur VK, Auckley DH, Chowdhuri S, et al. "Clinical Practice Guideline for Diagnostic Testing for Adult Obstructive Sleep Apnea: An American Academy of Sleep Medicine Clinical Practice Guideline." Journal of Clinical Sleep Medicine. 2017;13(3):479-504.
8. Azarbarzin A, Sands SA, Stone KL, et al. "The Hypoxic Burden of Sleep Apnoea Predicts Cardiovascular Disease-Related Mortality." European Heart Journal. 2019;40(14):1149-1157.
9. US Preventive Services Task Force. "Screening for Obstructive Sleep Apnea in Adults: US Preventive Services Task Force Recommendation Statement." JAMA. 2022;328(19):1945-1950.
10. Malhotra A, Grunstein RR, Fietze I, et al. "Tirzepatide for the Treatment of Obstructive Sleep Apnea and Obesity (SURMOUNT-OSA)." New England Journal of Medicine. 2024;391(13):1193-1205.
11. Sanchez-de-la-Torre M, Sanchez-de-la-Torre A, Bertran S, et al. "Effect of Obstructive Sleep Apnoea and Its Treatment with Continuous Positive Airway Pressure on the Prevalence of Cardiovascular Events in Patients with Acute Coronary Syndrome (ISAACC study)." Lancet Respiratory Medicine. 2020;8(4):359-367.
12. Peker Y, Glantz H, Eulenburg C, et al. "Effect of Positive Airway Pressure on Cardiovascular Outcomes in Coronary Artery Disease Patients with Nonsleepy Obstructive Sleep Apnea (RICCADSA)." American Journal of Respiratory and Critical Care Medicine. 2016;194(5):613-620.
13. Shukla A, Aizer A, Holmes D, et al. "Effect of Obstructive Sleep Apnea Treatment on Atrial Fibrillation Recurrence: A Meta-Analysis." JACC: Clinical Electrophysiology. 2015;1(1-2):41-51.