The application does present some data: 41% sensitivity, 92% specificity, but that's not the basis of approval, nor has it been published in a peer reviewed journal (or even with proper details like a table 1 or detailed description of control BP measurement methods, or even what "FDA approved" home device and protocol was used for reference)

Even assuming the device performs exactly as described (difficult to say given the paucity of presented data) the performance characteristics are the opposite of what you want in a screening test.

The hypertension feature was approved based on the pathway as being similar to the already approved Viz.ai software to detect hypertrophic cardiomyopathy by ECG analysis

That's not really the same thing at all