Diagnosing OSA and Insomnia at Home Based Only on an Actigraphy Total Sleep Time and RIP Belts an Algorithm “Nox Body Sleep™”

Figures & data

Table 1 Patient Characteristics of Both OSA and CI Cohorts Separately and Together

	OSA Patients (N=67)	CI Patients (N=72)	Both Patient Groups (N=139)
Sex [female/male]	24 / 43	52 / 20	76 / 63
Age [years]	54.0 ± 14.2 (21.0–90.0)	45.3 ± 12.7 (19.0–80.0)	49.5 ± 14.1 (19.0–90.0)
Height [cm]	172.9 ± 9.7 (148.0–195.0)	167.8 ± 8.9 (150.0–196.0)	170.3 ± 9.6 (148.0–196.0)
Weight [kg]	89.8 ± 21.8 (46.0–155.0)	65.7 ± 14.8 (38.0–120.0)	77.3 ± 22.1 (38.0–155.0)
BMI [kg/m2]	29.9 ± 6.2 (18.4–49.5)	23.2 ± 4.8 (16.4–46.9)	26.4 ± 6.4 (16.4–49.5)
AHI [/hrs]	62.9 ± 31.9 (8.3–159.5)	6.2 ± 3.6 (0.0–16.2)	33.5 ± 36.1 (0.0–159.5)
Analysis duration [min]	452.1 ± 71.0 (324.5–654.1)	470.1 ± 68.1 (329.9–703.2)	461.4 ± 69.8 (324.5–703.2)

Notes: Characteristics are represented in the following form when appropriate: mean ± standard deviation (min-max).

Abbreviations: BMI, body mass index; AHI, apnea-hypopnea index.

Figure 1 Diagram that describes the data flow.

Table 2 Epoch-Level Sensitivity and Specificity of Scoring Sleep States Using Nox’s BodySleep Compared to Manually Scored Sleep States, Alongside 95% Confidence Intervals Bootstrapped on a Patient-Level

		Total Epochs	Positive Agreement	Negative Agreement	Overall Agreement
OSA Patients (N=67)	Wake	12,165	0.54 (0.48, 0.60)	0.95 (0.94, 0.96)	0.87 (0.85, 0.89)
	NREM	40,449	0.91 (0.89, 0.92)	0.54 (0.49, 0.59)	0.79 (0.76, 0.81)
	REM	7513	0.46 (0.37, 0.55)	0.96 (0.95, 0.97)	0.90 (0.88, 0.91)
	Total	60,127	0.78 (0.75, 0.80)	0.68 (0.64, 0.71)	0.82 (0.80, 0.84)
CI Patients (N=72)	Wake	15,029	0.57 (0.50, 0.63)	0.96 (0.95, 0.97)	0.88 (0.85, 0.90)
	NREM	40,139	0.93 (0.91, 0.94)	0.66 (0.61, 0.70)	0.82 (0.80, 0.84)
	REM	11,875	0.71 (0.65, 0.76)	0.97 (0.95, 0.97)	0.92 (0.91, 0.93)
	Total	67,043	0.81 (0.78, 0.83)	0.78 (0.75, 0.81)	0.85 (0.83, 0.86)
Both patient groups (N=139)	Wake	27,194	0.55 (0.51, 0.60)	0.96 (0.95, 0.97)	0.87 (0.86, 0.89)
	NREM	80,588	0.92 (0.90, 0.93)	0.61 (0.58, 0.64)	0.80 (0.79, 0.82)
	REM	19,388	0.61 (0.56, 0.66)	0.96 (0.96, 0.97)	0.91 (0.90, 0.92)
	Total	127,170	0.79 (0.77, 0.81)	0.74 (0.71, 0.76)	0.83 (0.82, 0.85)

Table 3 Sensitivity and Specificity of Estimating Sleep-Disordered Breathing (SDB) Severity Using Estimated Sleep States from Nox’s BodySleep Compared to Estimating SDB Severity Using Manually Scored PSG Sleep Stages

	Both Patient Groups (n=139)
	Total Patients	Positive Agreement^Erreur! Signet non défini.	Negative Agreement^Erreur! Signet non défini.	Overall Agreement^Erreur! Signet non défini.
Minimal SDB (AHI <5)	29	0.93 (0.82, 1.00)	0.91 (0.85, 0.96)	0.91 (0.86, 0.96)
Mild SDB (5≤ AHI ≤15)	43	0.77 (0.63, 0.89)	0.98 (0.95, 1.00)	0.91 (0.86, 0.96)
Moderate to severe SDB (AHI ≥15)	67	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)
Total	139	0.91 (0.86, 0.96)	0.97 (0.96, 0.99)	0.96 (0.92, 0.98)

Note: Each value is accompanied by bootstrapped 95% confidence intervals.

Table 4 Sensitivity and specificity of estimating sleep-disordered breathing (SDB) severity estimated without sleep staging compared to estimating SDB severity using manually scored PSG sleep stages

	Both patient groups (n=139)
	Total Patients	Positive Agreement^Erreur ! Signet non défini.	Negative Agreement^Erreur ! Signet non défini.	Overall Agreement^Erreur ! Signet non défini.
Minimal SDB (AHI <5)	29	0.69 (0.52, 0.85)	0.93 (0.88, 0.97)	0.88 (0.82, 0.93)
Mild SDB (5≤ AHI ≤15)	43	0.79 (0.66, 0.91)	0.91 (0.84, 0.96)	0.87 (0.81, 0.92)
Moderate to severe SDB (AHI ≥15)	67	1.00 (1.00, 1.00)	0.99 (0.95, 1.00)	0.99 (0.98, 1.00)
Total	139	0.87 (0.81, 0.92)	0.95 (0.92, 0.97)	0.93 (0.89, 0.96)

Table 5 Confusion Matrix for Estimating SDB Severity Using Sleep States Estimated from Nox’s BodySleep Compared to Estimating SDB Severity Using Manually Scored Sleep Stages

		Nox’s BodySleep
		AHI <5	5≤ AHI ≤15	AHI ≥15
Manual PSG with sleep staging	AHI <5	27	2	0
	5≤ AHI ≤15	10	33	0
	AHI ≥15	0	0	67

Table 6 Confusion Matrix for Estimating SDB Severity Without Sleep Staging Compared to Estimating SDB Severity Using Manually Scored PSG Sleep Stages

		Manual PSG Scorings Without Sleep Staging
		AHI <5	5≤ AHI ≤15	AHI ≥15
Manual PSG with sleep staging	AHI <5	20	9	0
	5≤ AHI ≤15	8	34	1
	AHI ≥15	0	0	67

Note: Each value is accompanied by bootstrapped 95% confidence intervals.

Table 7 Summary Statistics Mean ± Standard Deviation (Min-Max) for Each Scoring Overall Recordings

	AHI [/hrs]	Total Sleep Time [m]
Manually scored	31.03 ± 33.47 (0.20–164.10)	388.07 ± 65.93 (231.00–535.00)
Nox BodySleep	33.55 ± 35.92 (0.00–159.50)	361.18 ± 75.11 (112.50–528.00)
Manually scored without sleep staging	29.72 ± 30.86 (0.50–156.60)	454.52 ± 67.56 (324.50–689.70)

Note: One-way repeated measures analysis of variance was performed using the Friedman test.

Figure 2 Continued.

Figure 2 Scatter plots and Bland-Altman plots for the indices. The indices from the Nox BodySleepTM 1.0 and Manual scoring with no sleep scoring were compared against the manual scoring of polysomnography (PSG). (a–d): Apnea-Hypopnea Index (AHI), and (e–h): Total Sleep Time (TST). Sleep Efficiency (SE) and Wake after Sleep Onset (WASO) scatter plots (i and j) and Bland-Altman plots (k and l) from manually scored recordings vs recordings scored with the Nox BodySleep 1.0 algorithm, in both groups of patients with Obstructive Sleep Apnea (OSA) and with chronic insomnia.

Table 8 The Median Pairwise Difference Between the Absolute Error of Manual PSG Scoring Vs Nox BodySleep and the Absolute Error of Manual PSG Vs Manual Without Sleep Staging

	All (N=139)	OSA (N=67)	CI (N=72)
AHI [1/hrs]	−0.80 (−1.40, −0.60)	−2.20 (−3.40, −1.50)	−0.40 (−0.60, −0.20)
TST [min]	−46.10 (−50.70, −39.50)	−39.20 (−51.00, −29.20)	−48.45 (−55.25, −42.10)

Table 9 Intraclass Correlation Between Parameters Inferred from Nox’s BodySleep Scorings versus the Parameters Calculated from Manual PSG Scorings for Each Cohort Alongside Bootstrapped 95% Confidence Intervals

	Nox BodySleep vs Manual PSG Sleep Staging			Manual PSG Scorings Without Sleep Staging vs Manual PSG Scorings with Sleep Staging
	OSA Patients (N=67)	CI Patients (N=72)	Both Patient Groups (N=139)	OSA Patients (N=67)	CI Patients (N=72)	Both Patient Groups (N=139)
AHI	0.96 (0.92, 0.98)	0.90 (0.80, 0.97)	0.98 (0.97, 0.99)	0.92 (0.86, 0.95)	0.73 (0.56, 0.87)	0.96 (0.94, 0.98)
TST	0.80 (0.71, 0.87)	0.64 (0.43, 0.80)	0.72 (0.61, 0.81)	0.46 (0.37, 0.54)	0.21 (0.04, 0.38)	0.32 (0.20, 0.43)
SE	0.53 (0.38, 0.68)	0.56 (0.29, 0.73)	0.55 (0.39, 0.67)	–	–	–
WASO	0.62 (0.47, 0.76)	0.63 (0.38, 0.79)	0.63 (0.46, 0.75)	–	–	–

Notes: The intraclass correlation between manual scorings without sleep staging and with PSG sleep staging is included in the table for comparison.