TABLE.
Characteristic | Training | Testing |
---|---|---|
Patients, n | 3,806 | 1,613 |
Seizure frequency, per mo: median (min—max)a | 2.56 (0.04–503.63) | 3.67 (0.09–882.63) |
Diary duration, days: median (min—max) | 364 (85–2,362) | 329 (85–1,366) |
Total number of seizures: median (min—max) | 31 (3–23,838) | 43 (3–19,873) |
Gender, %, M/F/ unknown | 47.3/50.6/2.1 | 49.0/48.2/2.8 |
Age, yr, median (min—max)b | 17.3 (0.6–84.5) | 16.4 (0.9–87.6) |
VNS usage, n (%) | 643 (16.9%) | 312 (19.3%) |
Brain surgery, n (%) | 112 (2.9%) | 39 (2.4%) |
Epilepsy type, %, focal/nonfocal/unknownc | 16.8/9.7/73.5 | 15.6/10.0/74.5 |
Numbers summarizing across patients are always given as median, and a range between the minimum (min) and maximum (max) value.
Twelve patients in the training set and 0 in the testing set had seizure frequencies < 1/yr, with the minimum rate being 1 seizure every other year.
Age on the last date of the exported dataset (training or testing).
Epilepsy type was defined based on user profiles in the Seizure Tracker database. Focal epilepsy = users who checked any of the list A items AND did not check any of the list B items. Nonfocal epilepsy = users who did not check any of the list A items AND did check any of the list B items. List A: brain tumors, brain trauma, brain hematoma, stroke, brain surgery, brain malformations, tuberous sclerosis. List B: Alzheimer disease, metabolic disorder, genetic abnormalities, electrolyte abnormalities, alcohol or drug abuse, Dravet syndrome, Angelman syndrome, neurofibromatosis, Down syndrome, Aicardi syndrome, Sturge–Weber syndrome, Rett syndrome, hypothalamic hamartoma.
F = female; M = male; VNS = vagal nerve stimulation.