JMIR Publications

ABSTRACT

Background:

Hypospadias remains as the most prevalent congenital abnormality in boys worldwide. However, limited infrastructure and number of pediatric urologists capable of diagnosing and managing the condition needed hinder the management of hypospadias in Indonesia. The use of artificial intelligence and image recognition is thought to be beneficial in improving the management of hypospadias cases in Indonesia.

Objective:

To develop and validate a digital pattern recognition system based on artificial neural network to determine various parameters in hypospadias.

Methods:

A hypospadias and normal penis image with matched age database was used to train the artificial neural network. Three image aspects of the penis (ventral, dorsal, and lateral aspect which include the glans, shaft, and scrotum) were taken from each subjects. The data was labeled with hypospadias parameter: hypospadias status, meatal location, meatal shape, quality of the urethral plate, glans diameter, and glans shape. The data were uploaded to train the image recognition model. Intra and interrater analysis were performed using the tests images shown to the algorithm.

Results:

This study is at the protocol development stage. A preliminary study regarding its development and feasibility will be started at December 2022. The results of this study are expected to be available by the end of 2023.

Conclusions:

The development of digital pattern recognition using artificial neural network is designed to improve the diagnosis and management of hypospadias patients, especially those residing in regions with limited infrastructure and health personnel.