Cloud Algorithm-Driven Oximetry-Based Diagnosis of Obstructive Sleep Apnea in Symptomatic Habitually-Snoring Children

Abstract

The ability of a cloud-driven Bluetooth oximetry-based algorithm to diagnose obstructive sleep apnea (OSA) was examined in habitually snoring children concurrently undergoing overnight polysomnography. Children clinically referred for overnight in-laboratory polysomnographic evaluation for suspected OSAS were simultaneously hooked with a Bluetooth oximeter linked to a smartphone. PSG findings were scored and the apnea hypopnea index (AHI_PSG) was tabulated while oximetry data yielded an estimated AHI_OXI using a validated algorithm. The accuracy of the oximeter in identifying correctly patients with OSAS in general, or with mild (AHI1–5 events·h⁻¹), moderate (5–10 events·h⁻¹) or severe OSAS (>10 events·h⁻¹) was examined in 432 subjects (6.5±3.2 years) with 343 having AHI_PSG>1 event·h⁻¹. The accuracies of AHI_OXI were consistently >79% for all levels of OSAS severity, and specificity was particularly favorable for AHI≥10 events·h⁻¹ (92.7%). Using the criterion of AHI_PSG >1 event·h⁻¹, only 4.7% of false negative cases emerged, from which only 0.6% of cases showed moderate or severe OSAS. Overnight oximetry processed via Bluetooth technology by a cloud-based machine learning-derived algorithm can reliably diagnose OSAS in children with clinical symptoms suggestive of the disease. This approach provides virtually limitless scalability and should alleviate the substantial difficulties in accessing pediatric sleep laboratories while markedly reducing the costs of OSAS diagnosis.