Apple Watch data deemed unreliable by researchers due to sudden algorithm changes

Apple Watch data deemed unreliable by researchers due to sudden algorithm changes

Researchers say that they believe some of the health data collected by Apple Watches is unreliable, at least when used in a research setting. The reason is simple — the data Apple Watches collect often changes thanks to algorithm updates.

According to a new report by The Verge, PJ Onnela, associate professor of biostatistics at the Harvard T.H. Chan School of Public Health and developer of the open-source data platform Beiwe, is concerned that the data Apple Watches collect changes as Apple Watch algorithm updates are rolled out. Because Apple Watch doesn’t surface the raw data to researchers, this inconsistency means that they can’t trust the information they’re being provided.

VPN Deals: Lifetime license for $16, monthly plans at $1 & more

The issue is best shown by a test carried out a few months apart, both relating to the same data collected during the same timeframe. But because watchOS updates had made changes to the way Apple Watch interprets the raw data from its sensors, the results also changed.

So, they checked in on heart rate data his collaborator Hassan Dawood, a research fellow at Brigham and Women’s Hospital, exported from his Apple Watch. Dawood exported his daily heart rate variability data twice: once on September 5th, 2020 and a second time on April 15th, 2021. For the experiment, they looked at data collected over the same stretch of time — from early December 2018 to September 2020.

While there was some expectation that the two exports would see some data differences, the results were still striking. If the same data isn’t actually the same data depending on when it’s extracted, how can it be trusted?

Put simply — it can’t, whether you’re using the latest and greatest Apple Watch Series 6, or not.

You can read the full report over on The Verge along with more input from other researchers.

Source link


Please enter your comment!
Please enter your name here