Smartphone Health Apps Miss Some Daily Activity of Users

If you use your smartphone to monitor your physical activity, you're probably more active than it suggests. A new UBC study finds that the iPhone's built-in pedometer missed about 1,340 steps during a user's typical day when compared to a purpose-built accelerometer worn on the waist.

The accuracy of smartphones and health apps is becoming more important as medical experts and technology companies rush to tap into the smartphone's enormous potential as a tool for gathering health data. Almost everyone has a smartphone, and they're usually handy, making it easy for an average person to participate in a study, and for scientists to gather data.

"In order to make accurate conclusions, we as researchers need to know that the data is actually representative of real behaviour," said Mark Duncan, the study's lead author. "That has major impacts in terms of patient care, and in terms of developing new and better research in the field."

The UBC study involved 33 participants and was divided into two parts: a laboratory test and a test in regular living conditions. In the lab test, participants carried two iPhones - a personal iPhone and a shared one provided by the lab - so researchers could see if different phone models produced different results. Participants walked on a treadmill for 60 seconds at various speeds and their steps were counted manually. Personal iPhones underestimated steps by 9.4 per cent at the slowest speed of 2.5 km/h. The shared iPhone fared slightly better at 7.6 per cent. At faster walking speeds, the phones were off by less than five per cent, which is generally considered acceptable for a pedometer.

For the other part of the study, participants fixed accelerometers to their waists for a full day, and recorded step readings from the iPhone at the beginning and end of the day. Over three days, the iPhone underestimated the accelerometer data by an average of 21.5 per cent, or 1,340 steps per day.

The technology is not entirely to blame, though. Several participants reported leaving phones behind during short trips to the bathroom or the water cooler. And daily living often involves slower walking speeds, which the lab test showed can affect accuracy.

"The accelerometer in the iPhone actually does a pretty good job when tested under lab conditions," said senior author Guy Faulkner. "You just have to have it on you at all times."

The results suggest researchers should use caution when relying on smartphone data, but Duncan said the average person shouldn't be discouraged from using health apps for motivation.

"For people who are already tracking their steps, they can rest assured that if their phone says they're getting the recommended 10,000 steps in a day, they are probably getting at least that many, and they are working toward better health," said Duncan. "From a public health point of view, it's better that it underestimates than overestimates."

Markus J. Duncan, Kelly Wunderlich, Yingying Zhao, Guy Faulkner.
Walk this way: validity evidence of iphone health application step count in laboratory and free-living conditions.
Journal of Sports Sciences. doi: 10.1080/02640414.2017.1409855.

Most Popular Now

Unlocking the 10 Year Health Plan

The government's plan for the NHS is a huge document. Jane Stephenson, chief executive of SPARK TSL, argues the key to unlocking its digital ambitions is to consider what it...

Alcidion Grows Top Talent in the UK, wit…

Alcidion has today announced the addition of three new appointments to their UK-based team, with one internal promotion and two external recruits. Dr Paul Deffley has been announced as the...

AI can Find Cancer Pathologists Miss

Men assessed as healthy after a pathologist analyses their tissue sample may still have an early form of prostate cancer. Using AI, researchers at Uppsala University have been able to...

New Training Year Starts at Siemens Heal…

In September, 197 school graduates will start their vocational training or dual studies in Germany at Siemens Healthineers. 117 apprentices and 80 dual students will begin their careers at Siemens...

AI, Full Automation could Expand Artific…

Automated insulin delivery (AID) systems such as the UVA Health-developed artificial pancreas could help more type 1 diabetes patients if the devices become fully automated, according to a new review...

How AI could Speed the Development of RN…

Using artificial intelligence (AI), MIT researchers have come up with a new way to design nanoparticles that can more efficiently deliver RNA vaccines and other types of RNA therapies. After training...

MIT Researchers Use Generative AI to Des…

With help from artificial intelligence, MIT researchers have designed novel antibiotics that can combat two hard-to-treat infections: drug-resistant Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus (MRSA). Using generative AI algorithms, the research...

AI Hybrid Strategy Improves Mammogram In…

A hybrid reading strategy for screening mammography, developed by Dutch researchers and deployed retrospectively to more than 40,000 exams, reduced radiologist workload by 38% without changing recall or cancer detection...

Penn Developed AI Tools and Datasets Hel…

Doctors treating kidney disease have long depended on trial-and-error to find the best therapies for individual patients. Now, new artificial intelligence (AI) tools developed by researchers in the Perelman School...

Are You Eligible for a Clinical Trial? C…

A new study in the academic journal Machine Learning: Health discovers that ChatGPT can accelerate patient screening for clinical trials, showing promise in reducing delays and improving trial success rates. Researchers...

Global Study Reveals How Patients View M…

How physicians feel about artificial intelligence (AI) in medicine has been studied many times. But what do patients think? A team led by researchers at the Technical University of Munich...

New AI Tool Addresses Accuracy and Fairn…

A team of researchers at the Icahn School of Medicine at Mount Sinai has developed a new method to identify and reduce biases in datasets used to train machine-learning algorithms...