Treatment of Nocturnal Enuresis Using Miniaturised Smart Mechatronics With Artificial Intelligence

Area of Science:

• Biomedical Engineering
• Artificial Intelligence in Medicine
• Wearable Technology

Background:

• Nocturnal Enuresis (NE) affects many individuals, leading to discomfort and social challenges.
• Current treatments for NE, such as post-void alarms, can be inefficient and lack personalization.
• There is a need for a proactive, comfortable, and customizable solution to manage bladder control.

Purpose of the Study:

• To develop and validate a wearable medical device, MyPAD, for monitoring bladder fullness.
• To utilize miniaturized mechatronics and Artificial Intelligence (AI) for early detection of the need to void.
• To provide a comfortable and customizable solution for treating Nocturnal Enuresis (NE) at the pre-void stage.

Main Methods:

• Development of a wearable device with bespoke ultrasound (US) probes and custom electronics.
• Implementation of AI algorithms, including Bidirectional Long Short-Term Memory Recurrent Neural Networks (Bi-LSTM-RNN) and Reinforcement Learning (RL), for signal processing and alarm generation.
• Validation using a tissue-mimicking phantom and human volunteers to assess device performance.

Main Results:

• The MyPAD device demonstrated high accuracy in monitoring bladder expansion.
• Achieved a Sensitivity (Se) of 99% and Specificity (Sp) of 99.5%, with an overall accuracy of 99.3%.
• Empirical evidence supports the device's viability for monitoring voiding needs and enabling continuous learning for bladder control.

Conclusions:

• The MyPAD device offers a promising, accurate, and efficient approach to managing NE.
• Its customizable and comfortable design, combined with AI, provides a superior alternative to existing treatments.
• The device has the potential to significantly improve the quality of life for individuals with incontinence, promoting consistent dry nights.