Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

BSP neural network architecture diagram.

The BSP proprietary OSA detection algorithm was built using neural networks and trained with a dataset of 5,783 patients and 8,417 records of overnight sleep studies. (A) Respiratory event detection model containing 160, 80, and 20 neurons; (B) Total sleep time estimation model containing 160, 80, and 5 neurons.

More »

Fig 1 Expand

Fig 2.

CONSORT flow diagram.

More »

Fig 2 Expand

Table 1.

Summary of subject characteristics and PSG results.

More »

Table 1 Expand

Fig 3.

Scatterplots.

(A) Scatterplot comparing bAHI to PSG-AHI; (B) Scatterplot comparing bTST to PSG-TST. bAHI = Belun apnea-hypopnea index; PSG-AHI = polysomnography apnea-hypopnea index; bTST = Belun total sleep time; PSG-TST = polysomnography total sleep time.

More »

Fig 3 Expand

Fig 4.

Bland-Altman plots.

(A) Bland-Altman plot for bAHI vs. PSG-AHI; (B) Bland-Altman plot for bTST vs. PSG-TST. bAHI = Belun apnea-hypopnea index; PSG-AHI = polysomnography apnea-hypopnea index; bTST = Belun total sleep time; PSG-TST = polysomnography total sleep time.

More »

Fig 4 Expand

Fig 5.

ROC curves for bAHI vs. PSG-AHI at PSG-AHI Cutoffs of 5, 15, and 30 events/h (N = 78).

ROC = receiver operator characteristic; bAHI = Belun apnea-hypopnea index; PSG-AHI = polysomnography apnea-hypopnea index.

More »

Fig 5 Expand

Table 2.

Performance (mean with 95% CI) of bAHI at PSG-AHI cutoffs of 5, 15, and 30 (all subjects, N = 78).

More »

Table 2 Expand

Table 3.

Contingency table of OSA severity measured by PSG and BSP (all subjects, N = 78).

More »

Table 3 Expand

Table 4.

Performance (mean with 95% CI) of bAHI at PSG-AHI cutoff of 15 for subjects taking heart-rate affecting medicines and subjects with comorbidities.

More »

Table 4 Expand

Fig 6.

The combined diagnostic algorithm using STOP-Bang cutoff of 5 and bAHI cutoff of 15 events/h curtailed the need for further sleep testing by 61%.

bAHI = Belun apnea-hypopnea index. a This false negative case had a PSG-AHI of 17.6 events/h; b These two false positive cases had mild OSA with PSG-AHI ≥ 5 events/h.

More »

Fig 6 Expand

Table 5.

Performance (mean with 95% CI) of STOP-Bang score of 5 at PSG-AHI cutoffs of 5, 15, and 30 (N = 78).

More »

Table 5 Expand

Table 6.

Performance (mean with 95% CI) of the combined approach using STOP-Bang cutoff of 5 and bAHI cutoff of 15 (N = 48).

More »

Table 6 Expand