This service uses Support Vector Machines (SVMs), a robust machine learning method, to analyse nocturnal pulse oximetry data in children. SVMs were trained on diagnostic polysomnography (PSG) studies of 3,084 children aged 2-18 years between 2015-2021 at the Queensland Children’s Hospital in Brisbane, Australia. Computed statistical, signal processing, and oximetric features are used in the prediction process.

AI Sleep Staging of oximetry data is performed using an SVM Classifier (SVC). Thirty-second segments (epochs) of the recording are classified as Sleep or Wake, and these segments are filtered before analysis of oximetry data for sleep-disordered breathing. Sleep staging enables the computation of sleep statistics traditionally obtained from overnight polysomnography, such as sleep duration, latency, efficiency, and WASO. While this sleep staging step can be disabled, it is recommended for analysing oximetry data collected in uncontrolled environments (e.g., at home).

Analysis of recording to uses either a SVM Regressor (SVR) to produce a point estimate of the apnoea-hypopnea index (AHI) with accompanying uncertainty bounds, or an SVC to predict whether the apnoea-hypopnea index (AHI) is ≥5.

Peer-reviewed article containing out-of-sample performance data coming soon.

About this Service

This online service is designed to facilitate model evaluation and academic research in an accessible way. It is self-funded and so some functionality is limited (single-file processing and feature explanation iteration limits) to ensure we are able to serve the largest number of users with the limited cloud processing available. These limits may be circumvented using offline tooling.

Batch Processing/Offline Usage

Offline tooling is available to facilitate large-scale batch processing (e.g., for research or evaluation purposes), removal of limitations imposed for quality-of-service reasons, or where your IT network does not allow internet access. Contact us for details.