Initial outcomes using a novel bedwetting alarm (Gogoband®) that utilizes real time artificial intelligence to wake
1Department of Urology, Yale University School of Medicine, New Haven, CT, USA; GoGoband Inc. Richmond, VA, USA.
Abstract:
We evaluated a new bedwetting alarm, GOGOband®® which utilizes real time heart rate variability (HRV) analysis and applied artificial intelligence (AI) to create an alarm that can wake the user prior to wetting. Our aim was to evaluate the efficacy of GOGOband® for users in the first 18-months of use.
Methods:
A quality assurance study was conducted on data retrieved from our servers, of initial users of the GOGOband® which includes a heart rate monitor, moisture sensor, bedside PC-tablet, and a parent app. There are three sequential modes beginning with Training, Predictive mode and Weaning mode. Outcomes were reviewed and data analysis was done with SPSS and xlstat.
Results:
All 54 subjects who used the system from Jan 1, 2020, to June 2021 for more than 30 nights were included in this analysis. The mean age of the subjects is 10.1 ± 3.7 yrs. Subjects wet the bed a median of 7 (IQR6-7) nights per week prior to treatment. Severity and number of accidents per night had no impact on the ability to achieve dryness with GOGOband®. A crosstab analysis was performed which indicated that high compliant users (>80%) can remain dry 93% of the time compared to the whole group 87.7%. Overall ability to achieve 14 dry nights in a row was 66.7% (36/54) with some achieving a median of 16 14-day periods of dryness (IQR 0-35.75).
Conclusions:
We found 93% dry night rate in high compliance users in Weaning, this translates to 1.2 wet nights per 30 days. This compares to all users who wet 26.5 nights prior to treatment and 11.3 wet nights per 30 days during Training. The ability to achieve 14 days straight of dry nights was 85%. Our findings indicate that GOGOband® provides a significant benefit to all its users reducing nocturnal enuresis rates.
