“…From the studies performed between 2016 and 2020 (n=257,829), a stratified weighted sample of 10,000 studies was drawn that overweighted studies with AS (sampling probability weights of 1 for no AS, 5 for non-severe AS, 50 for severe AS). After removing 3,378 studies with no pixel data, de-identifying video frames, and using an automated view classifier to determine the PLAX view, our final derivation set (training and validation) consisted of 6,021 studies with 22,912 videos (1,269,764 frames) (mean age 70.2 ± 15.7 years, n=2950 (49.0%) women), with mild, moderate, and severe AS in 12.4% (n=747), 8.4% (n=503), and 22.3% (n=1,344) of studies, respectively. A held-out, randomly selected, sample of 1,063 studies from the same period was used for (internal) testing, whereas 2,040 randomly selected scans with a total of 6,530 videos performed between January 1 st 2021 and December 15 th 2021 (mean age 65.7 ± 16.4 years, n=997 (48.9%) women) were used for external testing.…”