The role of novel clinical digital tools in the screening or diagnosis of Obstructive Sleep Apnea ¿ A systematic review (Preprint)

• Type: Other Publications
• Date: 2023

Authors

Duarte, M (Author) Other; Pedro Pereira Rodrigues (Author) FMUP; Ferreira-Santos, D (Author) Other

Other information

Authenticus ID: P-00Y-6WK

DOI: 10.2196/preprints.47735

Abstract (EN): <sec> <title>BACKGROUND</title> <p>Clinical digital tools are an up-and-coming new technology that can be used in the screening or diagnosis of obstructive sleep apnea (OSA) patients, notwithstanding the crucial role of polysomnography (PSG) ¿ the gold standard.</p> </sec> <sec> <title>OBJECTIVE</title> <p>The aim of our study was to identify, gather, and analyze existing digital tools and smartphone-based health platforms that are being used for this disease¿s screening or diagnosis in the adult population.</p> </sec> <sec> <title>METHODS</title> <p>We performed a comprehensive literature search in MEDLINE, Scopus, and Web of Science databases for studies evaluating the validity of digital tools in OSA screening or diagnosis until November 2022. The risk of bias was assessed using JBI Critical Appraisal Tool for Diagnostic Test Accuracy Studies. Sensitivity, specificity, and area under the receiver-operating curve (AUC) were used as discrimination measures.</p> </sec> <sec> <title>RESULTS</title> <p>We retrieved 1714 articles, 41 of which were included. We found 7 smartphone-based tools, 10 wearables, 11 bed/mattress sensors, 5 nasal airflow devices, and 8 other sensors that did not fit the previous categories. Only 8 (20%) studies performed external validation of their developed tool. Of those, the highest reported values for AUC, sensitivity, and specificity were 0.99, 96%, and 92%, respectively, for a clinical cutoff of apnea-hypopnea index (AHI) ¿ 30 and correspond to a non-contact audio recorder that records sleep sounds, which are then analyzed by a deep learning technique that automatically detects sleep apnea events, calculates the AHI, and identifies OSA. Looking at the studies that only internally validated their models, the work that reported the highest accuracy measures showed AUC, sensitivity, and specificity values of 1.00, 100%, and 96%, respectively, for a clinical cutoff AHI ¿ 30. It uses the Sonomat ¿ a foam mattress that, aside from recording breath sounds, has pressure sensors that generate voltage when deformed, thus detecting respiratory movements, and using it to classify OSA events.</p> </sec> <sec> <title>CONCLUSIONS</title> <p>These clinical tools presented promising results, showing high discrimination measures (best results reaching AUC > 0.99). However, there is still a need for quality studies, comparing the developed tools with the gold standard and validating them in external populations and other environments before they can be used in a clinical setting.</p> </sec> <sec> <title>CLINICALTRIAL</title> <p>This systematic review was registered in PROSPERO under reference CRD42023387748.</p> </sec>

Language: English

Type (Professor's evaluation): Scientific