The market for fitness wearables is growing.

A new report by Juniper Research reveals that wearables, including health trackers and remote patient monitoring devices, are set to become ‘must haves’ in delivering healthcare, with $20 billion forecast to be spent annually on these devices by 2023, and the projection that five million individuals will be remotely monitored by healthcare providers by 2023.

Fitness trackers from FitBit to Garmin have been popular with health-conscious individuals for some time now, helping them monitor their activity and fitness levels, complementing exercise programmes with information about distance, calorie burn and heart rate.

Heart rate is a powerful metric being deployed by many manufacturers, most notably Apple’s use of ECG in the Apple Watch 4.

But what we’re seeing most recently is a powerful evolution from fitness wearable to health wearable.

The same principles and emerging technologies are now turning fitness wearables into powerful medical devices, being embraced by healthcare providers and patients alike, particularly when it comes to cardiac health and what that can tell us about individuals.

In a recent patient survey, two-thirds of respondents (64%) said they would utilise a wearable health monitoring device if it meant it could reduce the number of times they had to physically visit a doctor or hospital.

With appetite growing for health devices outside of clinical environments, the pressure is on for manufacturers to focus even more vigorously on the quality of data produced.

Unfortunately, some devices and technologies are falling short of the stringent quality levels needed to maintain the integrity of results.

The risks can be significant.

The Pitfalls of Fitness Tracking

Inaccurate or misleading heart rate measurements can have serious consequences for the average user, who is unlikely to have the necessary medical training to spot or interpret anomalies.

Misleading results could result in:

  • The delay of medical treatment for an unrecognised medical condition.
  • Causing the user to over or under exert themselves during a training or gym session leading to potential injury or a lack of development.
  • Leading the user to believe they have underlying health issues, thus leading to feelings of anxiety.

Additionally, inaccurate energy expenditure tracking can be detrimental to a user’s ability to lose or gain weight, whereas incorrect GPS and distance tracking could cause the user to under or over train themselves for a marathon leading to potential injury.

The risks are real, with potentially serious physical consequences.

Performance Analysis: B-Secur’s Expert View

We thought it would be useful to compare the results of some of the leading trackers on the market today, to really understand the range of discrepancy.

B-Secur data analyst Mark Lilburn has been working with the data research team to perform some interesting analysis and comparison.

Mark Lilburn, B-Secur data analyst

Mark explains:

“What we really wanted to understand is where popular health tracking tech falls down, and how our own algorithms compare.

"It’s not enough to believe in the rigour of our technology - our credibility is founded on being able to demonstrate it through comparative testing, which we do regularly. The results are often very interesting.”

Let’s review some of these results.

Wrist Wearables

We began by analysing the performance of a market leading wrist wearable device, against our own HeartKey product, with the goal of comparing signal conditioning and peak detect algorithm performance of the two systems via ECG-derived heart rate analysis.

How?

We passed medical grade ECGs of known heart rate into both devices to derive mean heart rate values.

ECGs of various amplitudes were used to replicate real life test cases and incremental, simulated noise was applied to the ECG signals prior to the ECG being passed into both systems.

A result was obtained for both HeartKey and the competitor.

Heart rate algorithm performance was analysed at these varying noise levels and compared to the known true heart rate value.

Outcomes

We were delighted to see that HeartKey strongly outperformed the competitor device.

The competitor device had an average mean absolute percentage error (MAPE) of 5.9% whereas HeartKey had an average MAPE of 0.8%.

HeartKey also had a significantly smaller HR range than the competitor.

Mark said:

“The accuracy of wrist health wearables is massively important due to their global popularity. They are often relied on by the user as a health tracker in regards to weight loss, as a performance measurement tool for athletes training for an event or for general cardiac health and wellbeing monitoring.

“The results of this study demonstrate the large variability of results found in a market leading device.

“These inaccuracies must be considered when trusting such devices for reliable medical standard information.”

Medical Device Benchmarking

We next performed a review of the performance of the HeartKey signal conditioning and peak detect algorithms when compared to an FDA 510(k) approved medical device and a market leading ECG chest strap.

The investigation assessed R-R interval data for low amplitude ECGs (<0.5mV) as this enabled heart rate variability (HRV) metrics to be determined for comparative analysis.

How?

The protocol involved was as follows:

  • 1 minute standing baseline
  • 1 minute light walk
  • 2 minute quick walk
  • 1 minute stair exercise
  • 1 minute standing recovery

Outcomes

HeartKey outperformed the commercial ECG chest monitor and matched the ECG medical device in each HRV related metric - particularly in SDNN (standard deviation of R-R intervals), mean R-R and RMSSD (root mean square of successive differences of the R-R intervals).

This indicates the leading commercial ECG monitoring devices are not up to a medical grade standard. While relatively accurate for general use and training purposes, they are not yet suitable for medical monitoring use cases.

Health in a HeartBeat: the Future

Our studies show that signal quality is a key component of accuracy.

It is common for fitness and health wearable devices to suffer from poor signal quality which will naturally have a detrimental effect on the accuracy of the device.

The majority of health wearables on the market use Photoplethysmography (PPG) alone to monitor heart rate.

PPG is an optical-based system which detects pulse rate rather than true heart rate, and as such, can be prone to noise artefact interference when incorporated as a sensing technology in a wrist wearable.

ECG offers significantly greater accuracy.

At B-Secur, we have completed rigorous electrode and material testing to enable the signal supplied to our algorithms is of the highest possible quality. This high quality raw ECG signal is then processed by HeartKey’s signal conditioning and peak detection algorithms for a clean, accurate result.

As health wearables look set to continue to play a major role in the future of fitness, the accuracy of the device is incredibly important and must be the founding pillar of any development.

Download: Measuring, Understanding And Mitigating Stress With ECG Biometrics

Learn more about:

  • Competing and complementary autonomic nervous systems which contribute to stress
  • A detailed understanding of their effects on the heart and the body and explores new ways to allow us to measure stress as a personalised variable.
  • How ECG biometrics can work to create a vital relative stress score, and where B-Secur's work is being used to develop new non-drug interventions on stress.
Subscribe and download

Thank you and enjoy our content!

Get download