RESUMEN
Aim: The current gold standard for measuring sleep disorders is polysomnography (PSG), which is manually scored by a sleep technologist. Scoring a PSG is time-consuming and tedious, with substantial inter-rater variability. A deep-learning-based sleep analysis software module can perform autoscoring of PSG. The primary objective of the study is to validate the accuracy and reliability of the autoscoring software. The secondary objective is to measure workflow improvements in terms of time and cost via a time motion study. Methodology: The performance of an automatic PSG scoring software was benchmarked against the performance of two independent sleep technologists on PSG data collected from patients with suspected sleep disorders. The technologists at the hospital clinic and a third-party scoring company scored the PSG records independently. The scores were then compared between the technologists and the automatic scoring system. An observational study was also performed where the time taken for sleep technologists at the hospital clinic to manually score PSGs was tracked, along with the time taken by the automatic scoring software to assess for potential time savings. Results: Pearson's correlation between the manually scored apnea-hypopnea index (AHI) and the automatically scored AHI was 0.962, demonstrating a near-perfect agreement. The autoscoring system demonstrated similar results in sleep staging. The agreement between automatic staging and manual scoring was higher in terms of accuracy and Cohen's kappa than the agreement between experts. The autoscoring system took an average of 42.7 s to score each record compared with 4,243 s for manual scoring. Following a manual review of the auto scores, an average time savings of 38.6 min per PSG was observed, amounting to 0.25 full-time equivalent (FTE) savings per year. Conclusion: The findings indicate a potential for a reduction in the burden of manual scoring of PSGs by sleep technologists and may be of operational significance for sleep laboratories in the healthcare setting.
RESUMEN
OBJECTIVES: Up to 77% of patients with obstructive sleep apnoea (OSA) have positional OSA (POSA) but traditional positional therapy (PT) methods have failed as they were poorly tolerated. New convenient vibratory PT devices have been invented but while recent studies suggest high treatment efficacy and adherence, there are no published data comparing these devices directly with continuous positive airway pressure (CPAP). Our objective is to evaluate if a convenient vibratory PT device is non-inferior to CPAP in POSA treatment. METHODS: In this crossover randomised controlled trial, we enrolled patients with POSA with significant daytime sleepiness (Epworth Sleepiness Scale (ESS)≥10). POSA diagnosis was based on: (1) total Apnoea/Hypopnoea Index (AHI)>10/hour and non-supine AHI<10/hour (2) supine AHI≥2 × non-supine AHI. Patients used their initial allocated devices (PT or CPAP) for 8 weeks before crossing to the alternative intervention after a 1 week washout. The primary aim is to measure changes in ESS between the two treatments. Secondary outcomes include sleep study parameters and patient treatment preference (ClinicalTrials.gov: NCT03125512). RESULTS: 40 patients completed the trial between April 2017 and December 2018. Difference in ESS after 8 weeks of device use (PT minus CPAP) was 2.0 (95% CI 0.68 to 3.32), exceeding our predetermined non-inferiority margin of 1.5. AHI on CPAP was lower than with PT (4.0±3.2 vs 13.0±13.8 events/hour, respectively, p=0.001), although both were lower than at baseline. Time spent supine was significantly lower with PT than CPAP (p<0.001). 60% of patients preferred CPAP, 20% preferred PT, while 20% preferred neither device. CONCLUSIONS: The non-inferiority ESS endpoint for PT compared with CPAP was not met and the results were inconclusive. Future trials with larger sample sizes or in less symptomatic patients are warranted to provide further insight into the role of these new vibratory PT devices.