Search Results

The Night Shift is indicated for prescription use for the treatment of adult patients with positional obstructive sleep apnea with a non-supine apnea-hypopnea index

Device Description

The Night Shift is worn around the neck to reduce the amount of time the user sleeps in the supine position as a treatment for positional obstructive sleep apnea. Night Shift combines hardware and firmware to detect when the user attempts to sleep in the supine position and can initiate vibro-tactile feedback with increasing intensity until the user shifts to a non-supine position. The initiation of positional feedback from the Night Shift is turned on is programmable to allow the user to fall asleep (if they must) on their back. Each night the Night Shift is worn, it monitors sleep position (% time supine), behavioral sleep efficiency, and snoring levels (% time snoring > 40 and 50 dB) as well as the frequency, duration and intensity of the feedback (when applied). These data can be optionally transferred via the USB port to the Night Shift Web Portal where the user can generate a report to assess how well the positional feedback is working. A "trial" protocol can include one night with no feedback to establish a baseline and two nights with feedback to assess compliance/efficacy. Utilization information is saved on the device that allows reports to be generated that compares daily use by month and monthly averages for one year. The portal also allows the device to be reformatted (to eliminate all previously recorded data) for a new user, adjust the feedback settings to a new user's personal preferences, and/or upgrade the firmware. For large healthcare organizations that limit internet access, desktop software is provided as an alternative to the portal.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study details for the Advanced Brain Monitoring, Inc. Night Shift device, based on the provided text:

Acceptance Criteria and Reported Device Performance

Endpoint	Acceptance Criteria	Reported Device Performance	Conclusion
Effectiveness of Night Shift therapy (Primary)	65% of PT compliant participants with baseline overall AHI > 10 and non-supine AHI 50% decrease in AHI.	Met (85.2% vs. 65% target)
Safety	80% of participants will complete the study with no adverse events resulting in voluntary dropping.	100% of compliant subjects successfully completed the study. No adverse events were reported.	Met (100% vs. 80% target)
Accuracy of Supine Position Measurement	Computation of percent time supine by Night Shift is within +/- 5% of the percent time supine by video recordings plus chest sensor in 73% of subjects.	Night Shift was within 5% of chest/video supine time in 92% of the studies.	Met (92% vs. 73% target)
Treatment Compliance	At least 80% of participants will be compliant (use Night Shift for a minimum of 5.5 hours/night or length of their time in bed, five nights/week).	100% of the participants wore the Night Shift for a minimum of 20 nights across the 28 nights of intended use.	Met (100% vs. 80% target)
Reduction in Supine Time	At least 70% of participants will average less than 15% time supine across the four weeks of home use.	97% of the participants averaged less than 15% of time in bed in the supine position when therapy was delivered.	Met (97% vs. 70% target)
Improved Epworth Sleepiness Score (ESS)	50% of PT compliant participants will show an improved ESS of ≥ 2.	50% of participants exhibited an improvement of 2 or more, and 50% showed no change. None of the ESS scores worsened by 2 or more.	Met (50% vs. 50% target, with no worsening)
Improved Functional Outcomes of Sleep Questionnaire (FOSQ) total	FOSQ total will improve by ≥ 2 points in at least 50% of subjects.	57% exhibited an improvement of 2 or more, 23% showed no change, and 20% showed a worsening of 2 or more.	Met (57% vs. 50% target)
Mean Sensitivity (sleep) and Specificity (wake) for Night Shift	The mean sensitivity (sleep) and specificity (wake) for Night Shift will be 0.85 and 0.50, respectively.	The endpoint was met based on the sensitivity and specificity of 90% and 58% across 65 studies.	Met (90% sensitivity vs. 0.85, 58% specificity vs. 0.50)
Night Shift Total Sleep Time (TST) within predicate range	73% of subjects will be within the range of the predicate when subtracting PSG Total Sleep Time (TST) from Night Shift TST (i.e., range 151 and -129 minutes).	99% of the studies had TST derived from Night Shift within the maximum error (based on two standard deviations of the TST error for the predicate device) vs. PSG TST.	Met (99% vs. 73% target)
Night Shift Sleep Efficiency (SE) within predicate range	73% of subjects will be within the range of the predicate when subtracting PSG Sleep Efficiency (SE) from Night Shift SE (i.e., range 19.1 and -17.2%).	92% of studies had SE values derived from Night Shift within the maximum error (based on two standard deviations of the SE error for the predicate device) vs. PSG SE. 80% of subjects had sleep onset values 50 dB to identify AHI ≥ 10 (sensitivity > 0.80, specificity > 0.65)**	The percent time snoring > 50 dB can be used to identify patients with an AHI ≥ 10 with a sensitivity > 0.80 and a specificity > 0.65.
Identification of treatment success/failure based on AHI, ESS, PHQ9, ISI, GAD7, FOSQ	Those successfully or unsuccessfully treated with Night Shift can be identified via a combination of changes in the AHI, daytime drowsiness (ESS), depression (PHQ9), Insomnia (ISI), anxiety (GAD7) and quality of life (FOSQ).	Evaluating trends across these measures, 50% of subjects showed a substantial improvement as a result of Night Shift therapy and an additional 10% showed improvement, and 33% showed no change. None showed a worsening and two cases (7%) showed substantial overall worsening of subjective measures.	Met (with caveat) - "numbers of failures were too few to characterize"

Study Details for Clinical Tests:

Sample size used for the test set and the data provenance:
- Test Set Sample Size for Primary Effectiveness Endpoint: 27 patients with pre-treatment positional obstructive sleep apnea with a non-supine AHI 20).
- Data Provenance: Not explicitly stated, but the study was a clinical study conducted to evaluate safety and efficacy, implying prospective data collection. The location (country of origin) is not mentioned.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This information is not provided in the given text. Ground truth for sleep studies typically involves highly trained sleep technologists and physicians interpreting polysomnography (PSG) data. However, the document does not specify the number or qualifications for this particular study.
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- This information is not provided in the given text.
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The study evaluated the device's performance in treating sleep apnea and recording sleep parameters, not how human readers improve with or without AI assistance in interpreting diagnostic data from the device. The Night Shift is a therapeutic and monitoring device, not an AI diagnostic interpretation tool.
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Yes, the study primarily assessed the standalone performance of the Night Shift device. While it is a prescription device, its effectiveness was measured by its ability to reduce supine sleep and associated AHI, as well as its accuracy in measuring sleep parameters (position, TST, SE) independently. Human interaction is primarily for setup, compliance, and physician review of the generated reports, but the core therapeutic and monitoring function is standalone.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth for sleep parameters (AHI, supine time, TST, SE) appears to be Polysomnography (PSG), a gold standard for sleep disorder diagnosis. For the "Accuracy of Supine Position Measurement" endpoint, the ground truth was "video recordings plus chest sensor." For subjective measures (ESS, FOSQ), the ground truth was the participant's self-reported scores.
The sample size for the training set:
- This information is not provided in the given text. The document describes a clinical validation study, not the development or training phase of an algorithm.
How the ground truth for the training set was established:
- This information is not provided as the training set details are not mentioned.

Ask a Question

Ask a specific question about this device

Page 1 of 1