Blog
Industry trends, latest developments, and announcements
Latest
What Do GLP-1s Do to Wearable Data? Heart Rate Rises, HRV Falls, and Some of the Changes Are Not What They Seem
On Wegovy, 26% of adults had a heart rate rise of 20 bpm or more at some visit. GLP-1s raise resting heart rate, lower HRV, improve sleep apnea, shrink lean mass and change the weight that calorie and VO2 max estimates depend on. Which of those changes are real, which are artifacts of how wearables calculate, and what a product should do when a user starts treatment.
How Many Days Does a Wearable Need to Learn Your Baseline? Two to Four Weeks, and Longer Is Not Always Better
Apple asks for 7 nights, Oura up to two weeks and Garmin about three weeks before personal baselines switch on. We simulated what different baseline lengths do: short ones raise false alarms, long ones take weeks to accept a real change. The trade-off, why HRV needs longer than resting heart rate, and the rules that make baselines dependable.
Average Steps per Day by Age, Sex and Country: Benchmarks for Health Apps and Programmes
Stanford's study of 717,527 phone users in 111 countries put the average at 4,961 steps a day. Its more useful finding was that the gap between a country's most and least active people predicted obesity better than its average. Steps by country, sex and age from the study's own data, and what it means for anyone setting step goals or benchmarks.
How Do You Know Wearable Data Is Wrong? 12 Checks to Run Before You Score Anything
Every score, AI coach and programme report inherits the errors in the data underneath it. Most of those errors are mundane and detectable: impossible values, wrong units, the same steps counted twice, records that were replaced, days the device was not worn, and two metrics that share a name but not a formula. Twelve checks, with rules of thumb and what to do when one fails.