Researchers in Hong Kong have successfully used an iPhone camera and smartphone app to identify people with a type of irregular heartbeat called atrial fibrillation.
Users simply align their face with a red circle on the phone screen, and the app, called Cardiio Rhythm, calculates a regular or irregular heart rhythm using subtle beat-to-beat variations in facial skin color.
Among 85 patients at an average age of 72, the technology was near-perfect: It was 93 percent effective in recognizing AFib and 95 percent effective in recognizing patients without the condition.
“It’s pretty amazing that you can actually detect AFib just by analyzing signals coming off a person’s face,” said electrical and medical engineer Ming-Zher Poh, Ph.D., a study investigator and co-founder of Cardiio, a Cambridge, Massachusetts-based company developing the app and technology for detecting AFib.
The findings, presented at the American Heart Association’s Scientific Sessions in November, were confirmed with an electrocardiogram, which measures electrical impulses as they move through the heart. Twenty-five patients were ultimately diagnosed with AFib.
Early on, when Poh asked doctors and others about possible medical uses for his company’s app, “AFib tended to come up quite often,” he said.
AFib affects 3 million to 6 million Americans and increases the risk for strokes, heart failure and other heart-related complications.
But it can be difficult to diagnose, said the study’s lead researcher Bryan Yan, M.B.B.S., an associate professor at The Chinese University of Hong Kong.
“If you find it and confirm it, you can treat it to prevent stroke,” he said.
Poh noted that some people with AFib don’t have symptoms. “That’s where screening could be beneficial.”
Due to the wide use of smartphones and the low cost of apps, Yan said the technology could provide a cost-effective way to mass-screen people for AFib.
Plus, unlike other heart rate sensors, the app does not require skin contact to take a reading. This is particularly appealing in Asia, where people tend to be cautious about hygiene, Yan said.
It was Poh who developed the technology for measuring heartbeats using the face in 2010 as a graduate student at Massachusetts Institute of Technology. Each heartbeat changes the volume of blood in the body, he said. Hemoglobin in the blood absorbs light, so more hemoglobin means more absorbed light, and vice versa.
A screenshot of the Cardiio Rhythm app. (Courtesy of Ming-Zher Poh)
A smartphone camera can detect very slight changes in the amount of light reflected by the face, Poh said. Based on a 20-second look, the app rapidly translates variations of light into waveforms that correspond to the heartbeat.
Using a concept called “machine learning,” the phone’s internal computer can “learn” to detect normal or abnormal waveforms, in this case AFib.
“You show the computer different examples of waveforms, and teach the computer to recognize a specific pattern,” said Poh. “At Cardiio, we developed algorithms that are smart enough to recognize arrhythmia, particularly AFib.”
Yan said the app would only be used for initial screening, not to diagnose AFib, which would still require an ECG. “It could be put into a lot of places: at home in your mirror, or in clinic reception areas or pharmacies,” he said.
The Cardiio Rhythm app has not been cleared by the Food and Drug Administration and isn’t publicly available.
For now, the researchers said studies are needed to test the app in people with various skin tones in real-world settings, where lighting and other factors aren’t controlled. But eventually, the technology could potentially detect high blood pressure or very high or very low heart rates, Yan said.
Yan and Poh are currently exploring the “one-to-many” concept, using the app within a fixed, high-resolution camera.
“If no one moves,” Yan said, “it could pick up who has AFib in a crowd.”
- Rethink How You Check Your Heart Rhythm
- Why Atrial Fibrillation Symptoms Are Tough to Detect
- 4 Ways to Monitor Your Heart Rhythm
- Confirm Atrial Fibrillation With an EKG
- Diagnosing Atrial Fibrillation (AFib)
- Screening for Atrial Fibrillation Using a Smartphone: Is There an App for That?
Rethink How You Check Your Heart Rhythm
If you think you might have an irregular heartbeat like atrial fibrillation, a smartphone app may be able to confirm your suspicion — but you can check your heart rhythm on your own in simple ways, too.
Sometimes the irregular heartbeat of atrial fibrillation isn’t detected until the person has a life-threatening stroke or heart failure, because they notice no symptoms beforehand. In paroxysmal atrial fibrillation, symptoms come and go and may be easily overlooked.
Monitor your heart rhythm on your own through traditional or innovative new methods, and then discuss your findings with your doctor for a diagnosis. Your doctor may then order additional tests, either in the office or at home, to confirm a case of irregular heart rhythm.
Why Atrial Fibrillation Symptoms Are Tough to Detect
Normally, the heart contracts and relaxes in a steady rhythm. If you have atrial fibrillation, your heart’s two upper chambers quiver or contract irregularly. As a result, blood isn’t pumped properly into your heart’s lower chambers.
When this happens, you may experience atrial fibrillation symptoms, including:
- Rapid and irregular heartbeat
- Fluttering or pounding in your chest
Other symptoms, such as weakness and fatigue, may be less obvious. Complicating matters, some people have no symptoms at all, says Hugh Calkins, MD, an electrophysiologist and director of the Cardiac Arrhythmia Service at Johns Hopkins Medicine in Baltimore.
“You can have atrial fibrillation all the time and be completely unaware of it,” Dr. Calkins says. “For people who are completely asymptomatic, it may not be picked up until they have a stroke or heart failure.”
4 Ways to Monitor Your Heart Rhythm
The method you use to monitor your own heart rhythm will depend on how often you have symptoms and how comfortable you are using medical tools or devices.
Some methods, like the classic two-finger pulse test and the stethoscope, are traditional. But today more innovative methods are available, like smartphone apps that can accurately monitor your heart rhythm no matter where you are. These may help diagnose paroxysmal atrial fibrillation even if episodes are infrequent.
1. Pulse Check
To check your pulse, place the second and third fingers of your right hand on the edge of your left wrist. Slide your fingers to the center of your wrist until you find your pulse.
While taking your pulse, it’s important to remember that you’re checking your heart rhythm, not your heart rate.
Rather than counting the beats, check for a steady, regular rhythm, Calkins advises. Not all people find it easy to check their pulse, Calkins cautions, perhaps because of anxiousness.
Your doctor may use a stethoscope to monitor your heart rhythm, and this is something you can also do at home, Calkins says. “Patients can buy a $20 stethoscope and listen to their heart to see if it’s beating nice and regularly, or if it’s jumping around,” he says. But for some people, using a stethoscope may be difficult, triggering the same sort of anxiety that’s associated with a pulse check.
3. Holter Monitor
If you have sporadic paroxysmal afib episodes, your healthcare provider may give you a small electrocardiogram device known as a Holter monitor to wear. It records the electrical activity of your heart for as long as you wear it, which is typically a few days. Using wireless cellular technology, the device sends the recordings to your doctor’s office or a company that interprets the data.
If your afib episodes are very infrequent, you may need to use an event monitor. This device is similar to a Holter monitor, but it’s only activated once an episode begins.
4. Smartphone Heart Rhythm Apps
Smartphones provide another way for people to monitor their heart rhythm. “Now there are applications you can put on a smartphone that are personal EKG monitoring systems,” Calkins says. An example is the Kardia Mobile by AliveCor ($99), a tool with a smartphone app that allows you to monitor your blood pressure and heart rate, providing instant EKG analysis. Another app that enables heart rate monitoring is Cardiio (free). To measure your heart rate with Cardiio, simply place your finger over your smartphone camera flash for several seconds and wait for the results.
A study published in the journal HeartRhythm in March 2013, found that a smartphone app could accurately detect an irregular pulse in people with atrial fibrillation by analyzing signals recorded with their iPhone.
Calkins notes that heart rhythm apps could also prompt people to see their doctor. “Patients should be aware that although their heart rate varies, their heartbeat should be regular,” he says.
Confirm Atrial Fibrillation With an EKG
Although you may detect an abnormal heart rhythm by checking your pulse or listening to your heart, the only way to confirm an atrial fibrillation diagnosis is to get an electrocardiogram (EKG or ECG) from your healthcare provider. This is considered the gold standard — the most reliable way to diagnose the condition and to tell what type of atrial fibrillation you have, according to Calkins.
During this test, electrodes are placed on your chest to pick up the electrical impulses that cause your heart to beat. These impulses are sent to a screen or an EKG strip. Your doctor will examine the pattern of these impulses and determine if you have an atrial fibrillation diagnosis.
In order for an EKG to pick up afib, you must be having an episode during the test. This may work well for people who’ve had persistent afib for many years, but if you have paroxysmal atrial fibrillation, an EKG may not detect any irregularity.
“It can be like catching a fox in the henhouse,” Calkins explains. “It can also take years to go from intermittent to persistent afib.”
Arrhythmias or heart rhythm problems are experienced by more than 2 million people a year in the UK. Most people with an abnormal heart rhythm can lead a normal life if it is properly diagnosed.
The main types of arrhythmia are:
- atrial fibrillation (AF) – this is the most common type, where the heart beats irregularly and faster than normal
- supraventricular tachycardia – episodes of abnormally fast heart rate at rest
- bradycardia – the heart beats more slowly than normal
- heart block – the heart beats more slowly than normal and can cause people to collapse
- ventricular fibrillation – a rare, rapid and disorganised rhythm of heartbeats that rapidly leads to loss of consciousness and sudden death if not treated immediately
Arrhythmias can affect all age groups, but atrial fibrillation is more common in older people. Drinking alcohol in excess or being overweight increases your likelihood of developing atrial fibrillation.
You may also be at risk of developing an arrhythmia if your heart tissue is damaged because of an illness – for example, if you have had a heart attack or have heart failure.
Atrial fibrillation is a common cause of stroke. Having atrial fibrillation means your risk of stroke is 5 times higher than for someone whose heart rhythm is normal.
Certain types of arrhythmia occur in people with severe heart conditions, and can cause sudden cardiac death. This kills 100,000 people in the UK every year. Some of these deaths could be avoided if the arrhythmias were diagnosed earlier.
Common triggers for an arrhythmia are viral illnesses, alcohol, tobacco, changes in posture, exercise, drinks containing caffeine, certain over-the-counter and prescribed medicines, and illegal recreational drugs.
Diagnosing Atrial Fibrillation (AFib)
Several tests can be done to check for a fast or irregular heartbeat. Your doctor may order these tests if you are having signs or symptoms of a heart problem.
- Electrocardiogram (ECG)
An ECG is a snapshot of your heartâs electrical activity. Stickers (electrodes) are attached to your chest, arms, and legs. These electrodes measure the rate and rhythm of your heart.
- Holter monitor
A Holter monitor is a portable ECG. It can be worn for several days. Stickers (electrodes) are placed on your chest and are then connected to a small recording machine that is usually worn around the waist. It records the electrical activity of your heart for your doctor to review later.
- Mobile cardiac monitoring
A mobile cardiac monitor is worn for up to 30 days. It records your heartâs beat when it is in normal and abnormal rhythm. The results are automatically sent to your doctor. Your doctor uses this information to evaluate your symptoms to determine what is causing the abnormal rhythm.
- Event monitor
An event monitor is a portable ECG that is used for patients who have an irregular heart rhythm every once in a while. You will carry the monitor with you at all times and attach it to your chest when you feel symptoms. This lets your doctor check your heart rhythm at the time of your symptoms.
An echocardiogram uses sound waves to produce images of your heart. This test allows your doctor to see how your heart muscle is moving and pumping blood.
- Transthoracic echocardiogram (TTE)
A TTE is a standard non-invasive (no incisions or cuts) echocardiogram that gives your doctor a picture of your beating heart. An imaging device, called a transducer, gives off and reads sound waves. The imaging device records the sound waves bouncing off the walls and valves (echoes) in your heart. A computer then creates a video of your heart. This video can show the size of your heart, how well your heart is working, if the heart valves are working, and if there are blood clots in your heart.
- Transesophageal echocardiogram (TEE)
A TEE is often done when the doctor needs to get a good picture of the back of your heart. To get a clear picture, a probe is placed down the esophagus (the tube that connects your mouth to your stomach). The esophagus passes right behind the heart. Once the probe is in place, it works the same way as a TTE described above.
- Cardiac computerized tomography (CT) or magnetic resonance imaging (MRI)
Cardiac CT uses an X-ray machine and a computer to take clear, detailed pictures of the heart. During a cardiac CT, an X-ray machine will take pictures of your heart and chest. A computer will put the pictures together to make a three-dimensional (3D) picture of your heart and chest.
A cardiac MRI uses radio waves, magnets, and a computer to create pictures of your heart. Cardiac MRI creates detailed pictures of your heart as it is beating. The MRI will create snapshots as well as videos. Doctors use cardiac MRI to see the beating heart, the parts of the heart, and how the heart is working.
Screening for Atrial Fibrillation Using a Smartphone: Is There an App for That?
|Study, Device/Algorithm, Population||n||Sensitivity||Specificity|
|Chan et al,13 Cardiio Rhythm PPG, outpatient||1013||92.9%||97.7%|
|Chan et al,13 AliveCor ECG, outpatient||1013||71.4%||99.4%|
|Lau et al,10 AliveCor ECG, outpatient and inpatient||204||98%||97%|
|Lowres et al,15 AliveCor ECG, community pharmacy||1000||98.5%||91.4%|
|Desteghe et al,16 AliveCor ECG, inpatient geriatric||113||78.9%||97.9%|
|Desteghe et al,16 MyDiagnostick ECG, inpatient geriatric||113||89.5%||95.7%|
There is always a trade‐off between sensitivity and specificity in setting algorithm diagnostic criteria. For physician or health practitioner use in screening for AF, very high sensitivity is required to pick up every person with unknown AF. This will of necessity reduce specificity. For an ECG‐based device with an immediate high‐quality ECG image, instant verification is possible, whereas for a PPG device, verification requires a sequential ECG. For health professional use of ECG‐based devices for screening, higher sensitivity will be required than documented in the current study13 for the AliveCor algorithm. This would necessitate reversion to the original algorithm with very high sensitivity but lower specificity. Essentially a health professional screening version of the AliveCor app is required for this device if it is to be used for AF screening.
For screening in the community or for personal use, a drop in sensitivity may be a necessary trade‐off to achieve very high specificity. This is particularly important if large numbers of people are screened or when multiple recordings are requested in each person, as might be the case with a PPG app. In this situation even small reductions in specificity could lead to very large numbers of false‐positive results, which would require verification with a separate ECG.
Ultimately for the diagnosis of AF, an ECG will be required. This is the reason for the class 1 recommendation in guidelines18: “Electrocardiographic documentation is recommended to establish the diagnosis of AF.” Therefore, AF screening workflow using any automated pulse‐detection method, be it smartphone PPG or BP oscillometry, needs to factor in a mechanism for ECG verification. Verification will take time, involve logistic difficulties, and of course cost more. If hand‐held ECGs are used to screen for AF, the cost of expert verification of the ECG signal must also be factored in, although having an ECG trace available immediately is an advantage. The Chan et al study13 examined the net reclassification index (NRI), of the Cardiio Rhythm PPG algorithm over the AliveCor ECG algorithm, which would be appropriate only if the PPG were used as a second test following a hand‐held ECG test, which is highly unlikely and not the sequence of testing used in the study itself.
The best device for the purpose of AF detection for screening or diagnosis will need to be individualized to the situation and the healthcare system. It will be important to optimize sensitivity for AF detection while preserving specificity, to reduce the workload and expense caused by false‐positive readings, and better noise detection and cancellation algorithms to reduce false positives. Adequate instruction in use of devices or apps is crucial to optimal performance. There cannot be a “one size fits all” solution for AF screening, and it is useful to have an addition to the diagnostic armamentarium, provided all are aware of the pitfalls as well as the advantages of the technique. Importantly, when deciding on devices for performing mass screening for AF, caveat emptor.
B.F. received research grants to conduct investigator‐initiated studies from BMS/Pfizer, Bayer Pharma, and Boehringer‐Ingelheim and was a consultant for Bayer Pharma, BMS/Pfizer, Boehringer‐Ingelheim, Servier, Astra‐Zeneca, and Gilead, and speaker for Bayer Pharma, BMS/Pfizer, AstraZeneca. AliveCor provided ECG cases for screening studies, including some before the devices had been approved in any jurisdiction, but no funding.
*Correspondence to: Ben Freedman, MBBS, PhD, FRACP, FCSANZ, FACC, FESC, FAHA, Heart Research Institute, Level 3E D17, Charles Perkins Centre, University of Sydney, Sydney, New South Wales 2006, Australia. E‐mail: ben.edu.au
- 1 Friberg L, Rosenqvist M, Lindgren A, Terent A, Norrving B, Asplund K. High prevalence of atrial fibrillation among patients with ischemic stroke. Stroke. 2014; 45:2599–2605.Google Scholar
- 2 Freedman SB, Lowres N. Asymptomatic atrial fibrillation. The case for screening to prevent stroke. JAMA. 2015; 314:1911–1912.CrossrefMedlineGoogle Scholar
- 3 Lowres N, Neubeck L, Redfern J, Freedman SB. Screening to identify unknown atrial fibrillation. A systematic review. Thromb Haemost. 2013; 110:213–222.CrossrefMedlineGoogle Scholar
- 4 Svennberg E, Engdahl J, Al‐Khalili F, Friberg L, Frykman V, Rosenqvist M. Mass screening for untreated atrial fibrillation: the STROKESTOP Study. Circulation. 2015; 131:2176–2184.Google Scholar
- 5 Healey JS, Connolly SJ, Gold MR, Israel CW, Van Gelder IC, Capucci A, Lau CP, Fain E, Yang S, Bailleul C, Morillo CA, Carlson M, Themeles E, Kaufman ES, Hohnloser SH. Subclinical atrial fibrillation and the risk of stroke. N Engl J Med. 2012; 366:120–129.CrossrefMedlineGoogle Scholar
- 6 Camm AJ, Lip GY, De Caterina R, Savelieva I, Atar D, Hohnloser SH, Hindricks G, Kirchhof P; Guidelines ESCCfP . 2012 focused update of the ESC guidelines for the management of atrial fibrillation: an update of the 2010 ESC guidelines for the management of atrial fibrillation. Developed with the special contribution of the European Heart Rhythm Association. Eur Heart J. 2012; 33:2719–2747.CrossrefMedlineGoogle Scholar
- 7 Fitzmaurice DA, Hobbs FDR, Jowett S, Mant J, Murray ET, Holder R, Raftery JP, Bryan S, Davies M, Lip GYH, Allan TF. Screening versus routine practice in detection of atrial fibrillation in patients aged 65 or over: cluster randomised controlled trial. BMJ. 2007; 335:383.CrossrefMedlineGoogle Scholar
- 8 McManus DD, Lee J, Maitas O, Esa N, Pidikiti R, Carlucci A, Harrington J, Mick E, Chon KH. A novel application for the detection of an irregular pulse using an iPhone 4S in patients with atrial fibrillation. Heart Rhythm. 2013; 10:315–319.CrossrefMedlineGoogle Scholar
- 9 Wiesel J, Arbesfeld B, Schechter D. Comparison of the Microlife blood pressure monitor with the Omron blood pressure monitor for detecting atrial fibrillation. Am J Cardiol. 2014; 114:1046–1048.CrossrefMedlineGoogle Scholar
- 10 Lau JK, Lowres N, Neubeck L, Brieger DB, Sy RW, Galloway CD, Albert DE, Freedman SB. iPhone ECG application for community screening to detect silent atrial fibrillation: a novel technology to prevent stroke. Int J Cardiol. 2013; 165:193–194.CrossrefMedlineGoogle Scholar
- 11 Tieleman RG, Plantinga Y, Rinkes D, Bartels GL, Posma JL, Cator R, Hofman C, Houben RP. Validation and clinical use of a novel diagnostic device for screening of atrial fibrillation. Europace. 2014; 16:1291–1295.CrossrefMedlineGoogle Scholar
- 12 Lowres N, Neubeck L, Freedman SB. Can screening for atrial fibrillation be implemented at scale?Europace. 2016; doi:10.1093/europace/euw030. Available at: http://europace.oxfordjournals.org/content/early/2016/03/02/europace.euw030. Accessed July 8, 2016.CrossrefMedlineGoogle Scholar
- 13 Chan PH, Wong CK, Poh YC, Pun L, Leung WWC, Wong YF, Wong MMY, Poh MZ, Chu DWS, Siu CW. Diagnostic performance of a smartphone‐based photoplethysmographic application for atrial fibrillation screening in a primary care setting. J Am Heart Assoc. 2016; 5:e003428 doi: 10.1161/JAHA.116.003428.Google Scholar
- 14 McManus DD, Chong JW, Soni A, Saczynski JS, Esa N, Napolitano C, Darling CE, Boyer E, Rosen RK, Floyd KC, Chon KH. PULSESMART: pulse‐based arrhythmia discrimination using a novel smartphone application. J Cardiovasc Electrophysiol. 2016; 27:51–57.CrossrefMedlineGoogle Scholar
- 15 Lowres N, Neubeck L, Salkeld G, Krass I, McLachlan AJ, Redfern J, Bennett AA, Briffa T, Bauman A, Martinez C, Wallenhorst C, Lau JK, Brieger DB, Sy RW, Freedman SB. Feasibility and cost‐effectiveness of stroke prevention through community screening for atrial fibrillation using iPhone ECG in pharmacies. The SEARCH‐AF study. Thromb Haemost. 2014; 111:1167–1176.CrossrefMedlineGoogle Scholar
- 16 Desteghe L, Raymaekers Z, Lutin M, Vijgen J, Dilling‐Boer D, Koopman P, Schurmans J, Vanduynhoven P, Dendale P, Heidbuchel H. Performance of handheld electrocardiogram devices to detect atrial fibrillation in a cardiology and geriatric ward setting. Europace. 2016; doi:10.1093/europace/euw025. Available at: http://europace.oxfordjournals.org/content/early/2016/02/17/europace.euw025. Accessed July 8, 2016.CrossrefMedlineGoogle Scholar
- 17 Albert DE. Letter on Desteghe et al. “Performance of handheld electrocardiogram devices to detect atrial fibrillation in a cardiology and a geriatric ward setting”. Europace. In press.Google Scholar
- 18 January CT, Wann LS, Alpert JS, Calkins H, Cigarroa JE, Cleveland JC, Conti JB, Ellinor PT, Ezekowitz MD, Field ME, Murray KT, Sacco RL, Stevenson WG, Tchou PJ, Tracy CM, Yancy CW; Members AATF . 2014 AHA/ACC/HRS guideline for the management of patients with atrial fibrillation: a report of the American College of Cardiology/American Heart Association Task Force on practice guidelines and the Heart Rhythm Society. Circulation. 2014; 130:e199–e267.Google Scholar