K Number
K112102
Date Cleared
2011-12-20

(151 days)

Product Code
Regulation Number
868.2375
Reference & Predicate Devices
Predicate For
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The MICHELE Sleep Scoring System is a computer program (software) intended for use as an aid for the diagnosis of sleep and respiratory related sleep disorders.
The MICHELE Sleep Scoring System is intended to be used for analysis (automatic scoring and manual rescoring), display, redisplay (retrieve), summarize, reports generation and networking of digital data collected by monitoring devices typically used to evaluate sleep and respiratory related sleep disorders.
The device is to be used under the supervision of a physician. Use is restricted to files obtained from adult patients.

Device Description

The MICHELE Sleep Scoring System (MICHELE) is a software system that scans physiological data obtained during level 1 sleep studies, referred to as polysomnography (PSG) records, and applies a variety of analytical approaches to identify the occurrence of certain events that relate to the presence and type of sleep state, breathing abnormalities and limb movements. The system scores Sleep Stages, Arousals, Respiratory Events and Leg Movements. At the end of the analysis the system generates a PSG Report that includes tables and graphs typical of those generated following manual scoring of PSG records by certified technologists. The results of the automated scoring may be displayed using a PSG Scoring Viewer application, which allows manual editing of the results and generation of a revised PSG Report.
The device does not analyze data that are different from those analyzed by human scorers. It also neither interprets the results nor suggests a diagnosis.

AI/ML Overview

Here's a detailed breakdown of the MICHELE Sleep Scoring System's acceptance criteria and the study that proves its performance, based on the provided text:


MICHELE Sleep Scoring System Performance Study Analysis

The MICHELE Sleep Scoring System is a software intended to aid in the diagnosis of sleep and respiratory-related sleep disorders by automatically scoring polysomnography (PSG) records.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for the MICHELE system were established by comparing its performance against a consensus of human technologists and, in some cases, against predicate devices. The performance was evaluated using epoch-by-epoch agreement and agreement for clinically relevant data.

Table 1: Acceptance Criteria and Reported Device Performance (Epoch-by-Epoch Agreement)

Scoring FunctionMetricAcceptance Criteria (Implied: Better than Predicate Alice 5)MICHELE Performance (vs. 2/3 Consensus)Predicate Alice 5 Performance (vs. 2/3 Consensus)
All Sleep StagesOverall % Agreement> 30.5%82.6%30.5%
Kappa> 5.9%76.5%5.9%
AwakeAPPA> 5.4%89.9%5.4%
ANPA> 85.1%96.4%85.1%
N1APPA> 2.3%50.4%2.3%
ANPA> 94.6%94.7%94.6%
N2APPA> 42.1%82.9%42.1%
ANPA> 51.2%89.6%51.2%
N3APPA> 34.7%82.9%34.7%
ANPA> 73.9%97.5%73.9%
REMAPPA> 7.5%89.8%7.5%
ANPA> 93.1%98.5%93.1%
ArousalsOverall % Agreement> 57.9%89.9%57.9%
Kappa> 10.0%54.2%10.0%
APPA (Yes)> 28.1%60.0%28.1%
ANPA (None)> 70.3%94.1%70.3%
Periodic Leg Movements (PLMs)Overall % Agreement> 88.3%95.7%88.3%
Kappa> 38.2%68.7%38.2%
APPA (Yes)> 44.7%78.4%44.7%
ANPA (None)> 93.4%97.6%93.4%
Respiratory Events (Criteria A)Overall % Agreement> 78.0%94.0%78.0%
Kappa> 24.7%74.2%24.7%
Respiratory Events (Criteria B)Overall % Agreement> 75.9%93.0%75.9%
Kappa> 23.1%70.4%23.1%

Table 2: Acceptance Criteria and Reported Device Performance (Clinically Relevant Data - ICC)

VariableAcceptance Criteria (Implied: Not significantly different from human variability & > Predicate Alice 5)MICHELE ICC vs. Ave. Techs.Predicate Alice 5 ICC vs. Ave. Techs.
Total sleep time (min)> -0.2260.983-0.226
Sleep efficiency (%)> -0.2430.985-0.243
Sleep-onset latency (min)> -0.1180.950-0.118
REM-onset latency (min)N/A (Alice 5 didn't report)0.923N/A
Stage wake (min)> -0.2290.986-0.229
Stage 1 (min)> -0.2190.876-0.219
Stage 2 (min)> -0.2880.922-0.288
Stage 1+2 (min)> -0.1920.923-0.192
Stage delta (min)> -0.1320.869-0.132
Stage REM (min)> -0.2820.951-0.282
Arousal Index (hr⁻¹)> -0.2510.566-0.251
PLM Index (hr⁻¹)> 0.5890.9580.589
AHI A (hr⁻¹)> 0.3690.9820.369
AHI B (hr⁻¹)> 0.3840.9710.384
Average ICC-0.918-

Note: The acceptance criteria are implicitly defined by demonstrating superior or comparable performance to the predicate devices and strong agreement with human expert consensus.

2. Sample Size Used for the Test Set and Data Provenance

  • Sample Size for Test Set: 30 full night studies.
  • Data Provenance: Retrospective, from the sleep laboratory of a tertiary care facility (Foothills Hospital, Calgary, Canada).
  • Patient Characteristics: Included 19 patients with sleep apnea (15 moderate to severe), 9 with PLMs, 2 with severe sleep fragmentation, and 7 with normal sleep. Total Sleep Time ranged from 2.6 to 7.8 hours, sleep efficiency from 37% to 99%, and arousal index from 9 to 97 hr⁻¹. A total of 24,967 thirty-second epochs were scored.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

  • Number of Experts: Three technologists.
  • Qualifications of Experts: Each technologist was Board certified and had at least 15 years of hands-on experience in scoring polysomnograms.

4. Adjudication Method for the Test Set

  • Adjudication Method: 2+1 (consensus of two out of three scorers). This means that for a ground truth label to be established, at least two of the three technologists had to agree on the scoring of an epoch or event.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

  • Was an MRMC study done? A direct MRMC comparative effectiveness study "with AI vs. without AI assistance" to measure human reader improvement was not explicitly reported in the provided text. The study focused on evaluating the standalone performance of the MICHELE system against human consensus and comparing it to predicate devices.
  • However, the study implicitly compares the effectiveness of the automated system to human scoring (without assistance), and then highlights that MICHELE's performance matches or exceeds that of human inter-reader variability and predicate devices. For instance, the average ICC for MICHELE vs. average of three technologists (0.918) was only marginally below S1 (0.954) and not significantly different from S2 or S3 (all individual technologists were compared against the average of all three, including themselves). This suggests MICHELE performs at a level comparable to individual human experts.

6. Standalone (Algorithm-Only) Performance

  • Was a standalone study done? Yes, the entire performance evaluation described is for the standalone (algorithm-only) performance of the MICHELE Sleep Scoring System. The system processes PSG records and applies analytical approaches to identify and score events, then generates a report. While the results may be displayed using a PSG Scoring Viewer application, which allows manual editing of the results, the performance metrics reported in Tables 6-1, 6-2, and 6-3 are for the automated scoring before any potential manual rescoring.

7. Type of Ground Truth Used

  • Type of Ground Truth: Expert consensus. Specifically, a 2/3 consensus of three Board-certified technologists was used for epoch-by-epoch agreement and for calculating summary variables in the clinical report. The scoring was done according to the standard guidelines of the American Academy of Sleep Medicine (AASM) described in The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications, American Academy of Sleep Medicine, Westchester, IL, 2007.

8. Sample Size for the Training Set

  • The document does not explicitly state the sample size for a separate training set. The descriptions of the study focus on the evaluation of the device performance using the 30 full night studies. It's possible that these 30 studies or a subset were used for internal development/tuning, or that the system was developed using other proprietary data not detailed in this 510(k) summary.

9. How the Ground Truth for the Training Set Was Established

  • As the training set size and its specific use are not detailed, the method for establishing ground truth for a training set (if distinct from the test set) is also not provided in this document. It is implied that the development and validation adhere to AASM guidelines, similar to how the test set ground truth was established by certified technologists.

{0}------------------------------------------------

YST

Younger Sleep Technologies

Younes Sleep Technologies

K112102

DEC 2 0 2011

6.0 510(k) Summary

6.1 Background Information

510(k) Owner:Younes Sleep Technologies
Address:435 Ellice AvenueWinnipeg, Manitoba R3B 1Y6Canada
Tel.:+1-204-943-6295
Fax.:+1-204-943-6295
Contact:Magdy Younes, President

October 16, 2011 Date of Summary:

Device Trade Name:MICHELE Sleep Scoring System
Device Common Name:Sleep Analysis System
Classification Name:Ventilatory Effort Recorder
Class:II
Product Code:MNR
Regulation Number:21 CFR 868.2375

Indications for Use:

l

The MICHELE Sleep Scoring System is a computer program (software) intended for use as an aid for the diagnosis of sleep and respiratory related sleep disorders.

  • The MICHELE Sleep Scoring System is intended to be used for analysis (automatic scoring and manual rescoring), display, redisplay (retrieve), summarize, reports generation and networking of digital data collected by monitoring devices typically used to evaluate sleep and respiratory related sleep disorders.
    The device is to be used under the supervision of a physician. Use is restricted to files obtained from adult patients.

Predicate Devices to which Substantial Equivalence is Claimed:

Trade Name:Alice 5 System
Respironics Inc.
510(k) Number:K040595
Classification Name:Electroencephalography/Polysomnography System
Class:II
Product Code:GWQ

6-1

{1}------------------------------------------------

Sleen Technolor

Regulation Number:21 CFR 882.1400 Electroencephalograph
2. Trade Name:Morpheus™ 1, Automated Sleep Study Scoring andData Management SystemWideMed Ltd.
510(k) Number:K022506
Classification Name:Ventilatory Effort Recorder
Class:II
Product Code:MNR
Regulation Number:21 CFR 868.2375 Breathing Frequency Monitor
3. Trade Name:Somnolyzer® 24x7The Siesta Group North America
510(k) Number:K083620
Classification Name:Ventilatory Effort Recorder
Class:II
Product Code:MNR
Regulation Number:21 CFR 868.2375 Breathing Frequency Monitor

6.2 Device Description

6.2.1 How the Device Functions

The MICHELE Sleep Scoring System (MICHELE) is a software system that scans physiological data obtained during level 1 sleep studies, referred to as polysomnography (PSG) records, and applies a variety of analytical approaches to identify the occurrence of certain events that relate to the presence and type of sleep state, breathing abnormalities and limb movements. The system scores Sleep Stages, Arousals, Respiratory Events and Leg Movements. At the end of the analysis the system generates a PSG Report that includes tables and graphs typical of those generated following manual scoring of PSG records by certified technologists. The results of the automated scoring may be displayed using a PSG Scoring Viewer application, which allows manual editing of the results and generation of a revised PSG Report.

The device does not analyze data that are different from those analyzed by human scorers. It also neither interprets the results nor suggests a diagnosis.

6.2.2 Scientific Concepts that form the Basis for the Device

MICHELE is a standalone software system. It processes PSG records that consist of several channels of data recorded from patients during sleep, including electroencephalogram (EEG), Chin electromyogram (EMG), electroocculogram (EOG), electrocardiogram (ECG), leg EMG, chest and abdomen excursions measured

This document contains confidential information, which is the property of Younes Sleep Technologies (YST). This document may not, in whole or in part, be duplicated, disclosed, or used for design or manufacturing purposes without the prior written permission of YST,

{2}------------------------------------------------

Image /page/2/Picture/1 description: The image shows the letters YST in a stylized font. A line underlines the letters YS, and then continues in a wavy pattern to the right of the letter T. The letters are in black and the background is white.

Younes Sleep Technologies

by respiratory bands, nasal cannula flow, thermister flow and oxygen saturation. It does not record data and therefore does not have direct contact with patients.

MICHELE has been designed to score Sleep Stages, Arousals, Respiratory Events and Leg Movements as a human certified technologist would, according to the standard guidelines of the American Academy of Sleep Medicine (AASM) described in The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications, American Academy of Sleep Medicine, Westchester, IL, 2007.

6.2.3 Significant Physical and Performance Characteristics

The system uses standard desktop computers with Windows XP (Service Pack 3) or Windows 7 operating systems. The programming environment is Visual Studio. Further details regarding software are presented in Section 17 of this 510(k) Notification.

The software performance was measured by: A) Determining epoch-by-epoch agreement between MICHELE's scoring and the scoring of three technologists with respect to the four scoring functions (Sleep staging, Arousals, Periodic Leg Movements (PLMs) and Respiratory Events) (Objective 1). B) Determining the agreement between MICHELE's results of Clinically Relevant Data, such as Total Sleep Time in Different Stages, Apnea and Hypopnea Index (AHI ... etc) and the results of the three technologists (Objective 2). MICHELE's performance, so determined, was compared with the results of analysis of the same validation files by one of the predicate devices, Alice 5 (K040595), using the same scoring guidelines (AASM 2007). It was also compared with the published performance of the two other predicate devices, Somnolyzer (K083620) and Morpheus (K022506).

6.2.3.1 Files: Software performance was assessed using 30 full night studies recorded in the sleep laboratory of a tertiary care facility (Foothills Hospital, Calgary, Canada). The files were selected at random and included 19 patients with sleep apnea. Fifteen of these patients had moderate to severe sleep apnea (AHI 73±38 hr' ') and underwent split studies with one part (pre-CPAP) where sleep was severely fragmented and a second part (on CPAP) with fairly normal sleep and breathing. The group also included 9 patients with PLMs (8 to183 hr '; average 38±55 hr'), two patients with severe sleep fragmentation for no apparent cause (non-organic insomnia) and seven patients with normal sleep. Overall, the quality of sleep varied considerably among the 30 patients with Total Sleep Time ranging from 2.6 to 7.8 hours (4.2±1.1 hours), sleep efficiency ranging from 37 to 99% (61±18%) and arousal index ranging from 9 to 97 hr ' (17±4 hr'). A total of 24967 thirty-second epochs were scored.

6.2.3.2 Technologists: Each of the three scorers is Board certified and has had at least 15 years of hands-on experience in scoring polysomnograms.

This document contains confidential information, which is the property of Younes Sleep Technologies (YST). This document may not, in whole or in part, be duplicated, disclosed, or used for design or manufacturing purposes without the prior written permission of YST.

{3}------------------------------------------------

Image /page/3/Picture/1 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a bold, sans-serif font. Below the letters is a line that resembles a sleep wave. Below the line is the text "Younes Sleep Technologies" in a smaller, sans-serif font.

6.2.3.3 Analytical Methods and Results:

6.2.3.3.1 Objective 1 testing (epoch-by-epoch agreement). Table 6-1, left panels, shows results of epoch-by-epoch agreement between MICHELE and a consensus (≥2 of the scorers agree) of the three scorers. The right panels show the results for the predicate device to which it was possible to directly compare results, Alice 5, (referred to as Alice herein) using the same files and scoring guidelines. Positive Percent Agreement (PPA), Negative Percent Agreement (NPA), Overall % agreement and Cohen's kappa (kappa) were calculated according to Altman DG et al (1). The weighted average of test and reference scorers was obtained for PPA (i.e. APPA) and NPA (i.e. ANPA).

APPA, ANPA, Overall % agreement and kappa obtained with MICHELE exceeded the corresponding values obtained with Alice for all comparisons.

6.2.3.3.1.1 Comparison with Other Predicate Devices:

There is only one study dealing with the performance of Morpheus (2). These authors reported on the agreement between Morpheus and two individual (i.e. not a consensus) technologists, M1 and M2, as well as the agreement between M1 and M2. The paper includes data on all four functions. Data available for sleep staging include agreement for 5-stage scoring along with PPA for each stage and the overall %agreement and kappa. They also provided %agreement and kappa, but not PPA, for 4-stage scoring (A'wake, N1+N2, N3, Rem) and 3-stage scoring (awake, non-Rem and Rem). For scoring of arousals, PLM and respiratory events, they provided overall %agreement and kappa for scoring one event, two events or no events (3 x 3 matrix). There was no information on agreement for different categories of respiratory events.

Two studies are available for the Somnolyzer. In one (4), the authors reported on % agreement for sleep stages only, in comparisons between the Somnolyzer and a 2/3 consensus of technologists. Their subjects were mostly normal but the study included 25 patients with sleep apnea (severity unspecified). The % agreement and kappa values for sleep staging by MICHELE (82.6%, Table 6-1) exceeded the values reported in that study both for the apnea patients (75.6%) and the normal subjects (80.4%).

The other study on Somnolyzer (3) reported on %agreement and kappa in comparisons between the Somnolyzer and one scorer. Comparisons were limited to sleep staging, and the subjects were all normal.

In order to compare our results with those cited above (2,3) it was necessary to analyze and report our data in the same fashion (i.e. one-on-one comparisons between the Auto-score and two technologists and between the two technologists). This is presented below for our first two scorers (SI and S2) along with the agreement indices that correspond to what they reported (Table 6-2).

This document contains confidential information, which is the property of Younes Sleep Technologies (YST). This document may not, in whole or in part, be duplicated, disclosed, or used for design or manufacturing purposes without the prior written permission of YST.

{4}------------------------------------------------

Image /page/4/Picture/0 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a bold, sans-serif font. A line extends from under the letters and forms a wave-like pattern. Below the logo is the text "Younes Sleep Technologies" in a smaller, sans-serif font.

TABLE 6-1

AGREEMENT BETWEEN AUTO-SCORING AND CONSENSUS (2/3) OF THREE TECHNOLOGISTS

MICHELEALICE
SCORING FUNCTIONTotalby Techs.APPAANPAOverall %Agreementkappa(%)Totalby Techs.APPAANPAOverall %Agreementkappa(%)
SLEEP STAGING2496782.676.52496730.55.9
Awake656389.996.465635.485.1
N1241150.494.724112.394.6
N2984682.989.6984642.151.2
N3286282.997.5286234.773.9
Rem328589.898.532857.593.1
No Consensus283283
AROUSALS1764889.954.21764857.910.0
Yes227860.094.1227828.170.3
None1537015370
No Consensus104104
PLMs1846195.768.71846188.338.2
Yes174178.497.6174144.793.4
None1672016720
No Consensus4747
RESPRIRATORY EVENTS
Criteria A1774694.074.21774678.024.7
Hypopnea151376.396.615139.395.3
Obstructive Apnea32957.199.232914.892.0
Mixed Apnea21479.499.721434.899.1
Central Apnea17464.999.617416.799.1
None1551696.989.11551690.148.0
No Consensus132132
Criteria B1782493.070.41782475.923.1
Hypopnea182260.397.618225.194.1
Obstructive Apnea35955.999.335915.591.7
Mixed Apnea21483.699.621434.299.1
Central Apnea17763.899.617716.698.9
None1525298.175.51525289.047.7
No Consensus133133

Numbers in Sleep Staging rows are number of 30-second epochs. Numbers in Event rows are numbers of events and not epochs except in the "None" category where the number of epochs with no events. APPA, Averaged Positive Percent Agreement; ANPA, Averaged Negative Percent Agreement; N1, N2, and N3, Non-Rem stages 1, 2 and 3; PLMs, Periodic Limb Movements; No Consensus, all three technologists gave different scores.

6-5

{5}------------------------------------------------

Image /page/5/Picture/0 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a stylized font, with a line underneath the letters that extends into a waveform pattern. Below the logo, the words "Younes Sleep Technologies" are printed in a smaller, sans-serif font.

Table 6-2 shows that the agreement between MICHELE and individual technologists equals or exceeds the corresponding values in the Morpheus study (2). It is to be noted that the criteria for scoring respiratory events used in the Morpheus study (the Chicago criteria (5)) were different from the criteria used in our study (AASM criteria (6)), and that the latter criteria are more complex than the former. It is also notable that the agreement between MICHELE and each of the two technologists (S1 and S2) is substantially comparable to the agreement between the two technologists. The other published study dealing with the Somnolyzer (3) reported a % agreement of 72.3% with a kappa of 59.1% for agreement between the Somnolyzer and one scorer in staging sleep. The agreement between MICHELE and either technologist (S1 or S2) exceeds their reported value.

TABLE 6-2

ScoringFunctionTest reportedMICHELE Sleep Scoring SystemMorpheus (2)
Auto vs.S1Auto vs. S2S1 vs S2Auto vs.M1Auto vs. M2M1 vs M2
SLEEP (5-stage)%agreement (kappa)80.9(74.4)76.7(68.4)79.6(72.3)77.7(67.0)73.3(61.0)82.1(73.0)
AwakePPA94.482.675.068.769.680.9
N1PPA41.441.953.613.119.921.3
N2PPA80.976.182.973.568.977.1
N3PPA89.789.290.558.035.347.7
RemPPA87.385.894.260.757.179.0
SLEEP (4-stage)%agreement (kappa)88.0(81.8)83.3(74.6)84.9(76.6)82.6(71.0)79.9(65.0)88.7(80)
SLEEP (3-stage)%agreement (kappa)91.4(83.5)91.1(81.8)90.8(82.8)88.0(75.0)88.0(74.0)93.5(87.0)
AROUSALS (3X3)%agreement (kappa)84.1(38.8)87.9(49.3)85.7(46.4)76.2(28.0)76.1(30.0)83.7(57.0)
PLMs (3X3)%agreement (kappa)95.0(66.2)94.6(67.0)93.8(60.2)93.1(68.0)92.2(66.0)95.6(77.0)
RESPRIRATORYChicago (3X3)%agreement (kappa)89.7(66.0)89.7(66.0)94.9(82.0)
Criteria A (3X3)%agreement (kappa)94.8(78.3)94.6(75.2)94.9(76.4)
Criteria B (3X3)%agreement (kappa)94.3(76.5)93.9(71.7)93.8(74.3)

COMPARISON OF MICHELE SLEEP SCORING SYSTEM AND MORPHEUS

6-6

{6}------------------------------------------------

Image /page/6/Picture/1 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a stylized font, with a line underneath that resembles a sleep wave. Below the logo, the words "Younes Sleep Technologies" are written in a smaller, simpler font. The logo is simple and professional, and it effectively communicates the company's focus on sleep technology.

6.2.3.3.2 Objective 2 testing:

In this section we discuss agreement between automatic and manual scoring for summary variables that appear in the clinical report used by physicians to assess sleep disorders. Table 6-3 shows the results for 14 variables. These were selected because they are the most commonly used variables in the clinical assessment.

The first data Column of Table 6-3 is the average score of the three technologists for each of the 14 variables of interest. The averaging was done on a file-by-file basis. The values and corresponding standard deviations (SD) given in column 1 are the average and SD of the 30 averages. The second column contains the average and SD of the values obtained from automatic analysis with MICHELE Sleep Scoring System. The third column lists the average and SD of the thirty differences between MICHELE and the corresponding average of the three technologists (Bland and Altman analysis).

The fourth and fifth columns are the corresponding results for the predicate device (Alice). Shaded cells in columns 3 and 5 indicate significant difference (p≤ 0.05) between the Auto-score (MICHELE or Alice) and the average of the three technologists. The last five columns contain the intra-class correlation coefficients for comparisons between each of the five scorers and the average score of the three technologists.

The results show good agreement in general between MICHELE scores and the average of three technologists. With the exception of the arousal index where concordance (ICC) between the Auto-score and the average was only modest (ICC = 0.566), concordance was excellent and mostly within the range observed in comparisons between individual technologists and the average of the three technologists. Average ICC for MICHELE vs. average of three technologists was 0.918 (bottom row, Table 6-3), only marginally below S1 (p=0.03 by ANOVA for repeated measures) and not significantly different from $2 or $3.

The results for analysis with the predicate device (Alice) are also shown in Table 6-3. It is clear that MICHELE's performance is superior in all respects. Alice found no Rem sleep in 27 of the 30 files, even though Rem was present in 28 of the files as identified by each of the three technologists and by MICHELE.

6.2.3.3.2.1 Comparison with Other Predicate Devices:

Table 6-4 shows results for MICHELE (left 6 columns) and the only results available in the literature for another predicate device (Morpheus) (2). The first three columns in each set are the average results for the two human scorers (S1 and S2 in the case of MICHELE, and M1 and M2 for Morpheus) and the corresponding automatic score. The next three columns are intra-class correlation coefficients (ICC) for the relation between the Auto-score and the two technologists as well as the relation between the two technologists.

{7}------------------------------------------------

Image /page/7/Picture/0 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a stylized font, with a line underneath the letters that extends into a wavy line. Below the logo, the words "Younes Sleep Technologies" are written in a smaller, simpler font.

AverageMicheleAliceIntra-class Correlation Coefficients
VariableS1-S3SDMichele - ave.SDSDAlice - ave.SDSDMichelevs. Ave.Alicevs.Ave.S1 vs.Ave.S2 vs.Ave.S3 vs.Ave.
Total sleep time (min)312743127201344066-128960.983-0.2260.9540.9780.992
Sleep efficiency (%)74.617.074.716.60.12.997.011.0-23.021.00.985-0.2430.9570.980.994
Sleep-onset latency (min)242724290912-24270.950-0.1180.9910.9970.995
REM-onset latency(min)1267112673028NANA0.923NA0.9880.9660.992
Stage wake (min)1087610874-1121243-97880.986-0.2290.9580.980.994
Stage 1 (min)47304228-51439-44290.876-0.2190.9120.8640.91
Stage 2 (min)1655415950-520233104-691310.922-0.2880.9830.9640.972
Stage 1+ 2 (min)2125720262-1021236107241320.923-0.1920.9510.9350.95
Stage delta (min)47386046-1317193101-1471000.869-0.1320.9400.8470.948
Stage REM (min)53265126-28314-50280.951-0.2820.9880.9770.984
Arousal Index (hr 1)33232511-9155418-21310.566-0.2510.9370.9560.932
PLM Index (hr 1)12291331194342-29300.9580.5890.9780.8550.867
AHI A (hr 1)304132402734224340.9820.3690.9920.9740.988
AHI B (hr 1)31422736-483021-2350.9710.3840.990.9670.986

Table 6-3: Agreement between Manual and Automatic Scoring for Relevant Scoring Variables

{8}------------------------------------------------

Image /page/8/Picture/0 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a bold, sans-serif font. A line extends from under the letters and turns into a waveform. Below the logo, the words "Younes Sleep Technologies" are written in a smaller, sans-serif font.

Table 6-4

Comparison between Michele and Morpheus for Scoring Clinically Relevant Variables
Michele Sleep-Scoring SystemMorpheus
VariableS1S2AutoS1 vs. S2S1 vs. AutoS2 vs. AutoM1M2AutoM1 vs. M2M1 vs. AutoM2 vs. Auto
Total sleep time (min)3303003120.8760.9340.9683483453570.9800.9200.940
SD737672636165
Sleep efficiency (%)7972750.8830.9410.9688382850.9600.8700.910
SD161817121112
Sleep-onset latency (min)2225240.980.940.952626221.0000.8600.860
SD272729242421
REM-onset latency (min)1311211260.920.900.921301271750.9900.4600.460
SD727173797481
Stage wake (min)911201080.8860.9420.9698589760.9600.8700.910
SD728074494650
Stage 1 (min)5244420.6920.7310.8041949380.2200.3700.530
SD402928152027
Stage 2 (min)1671681590.9250.9260.8222312222140.8000.8400.720
SD575750544648
Stage 1+2 (min)2192122020.8300.9030.8112502702520.8600.8700.730
SD626162555359
Stage delta (min)5536600.6710.9670.5483821500.5700.5300.180
SD433646262326
Stage REM (min)5551510.9480.9530.9156053550.9200.7200.760
SD282526302634
Arousal Index (events/h)3233250.8750.5940.4613036220.8100.7200.580
SD182411191716
PLM Index (events/h)1112130.8490.9590.7381316190.9300.6100.650
SD313231192125
Resp. Disturbance Index2123240.9900.9500.950
SD232523
AHI A (events/h⁻¹)3028320.9470.9850.930
SD404140
AHI B (events/h⁻¹)3431290.9320.9670.926
SD434337
Average0.8720.9030.8380.8450.7380.70

Significantly different from Auto. Significantly different from Tech.2. Significantly different from both Tech. 2 and Auto.

As may be expected from comparisons involving a large number of pairs, and as shown in Table 6-4 by highlighted cells, there were many significant differences between the three scorers even though the average differences were small. The results

{9}------------------------------------------------

Image /page/9/Picture/1 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a stylized font, with a line underneath the letters that resembles a sleep wave. Below the letters, the words "Younes Sleep Technologies" are written in a smaller, sans-serif font. The logo is simple and modern, and it effectively communicates the company's focus on sleep technology.

of Morpheus were significantly different from both M1 and M2 in eight variables (solid shade and diagonal stripes). MICHELE Auto-scoring was different from both S 1 and S2 in five. As in the case of the MICHELE, the authors of the Morpheus study (2) commented on the occasional inaccuracy of the Morpheus system in estimating Rem-onset latency. They indicated that Morpheus missed the first Rem period in 10 patients (32%) whereas MICHELE missed the first Rem period in only one patient. The differences they reported between manual and automatic scoring in the other variables were in the same range as what we observed with MICHELE. Both systems underestimated the arousal index. With Morpheus the difference was 11 hr" (0.5[30+36]-22) while MICHELE underestimated the index by 8 hr 1 {0.5[32+33]-25). The correlation coefficients for comparisons between manual and MICHELE's scoring (S1 vs. Auto and S2 vs. Auto)) exceeded the corresponding coefficients in the Morpheus study (M1 vs. Auto and M2 vs. Auto)) in all categories except the Arousal Index, where it was only marginally lower. The averages of all correlation coefficients for the comparisons between Tech.1&Tech.2, Tech.1 vs. Auto and Tech.2 vs. Auto are given at the bottom of Table 6-4. There were no significant differences (by ANOVA for repeated measures) between the three averages in the case of MICHELE.

6.3 Comparison of Indications for Use Statements

The following table compares Indications for Use Statements between the MICHELE Sleep Scoring System, and the three predicate devices, i.e. Alice 5,
Somnolyzer® 24x7 and Morpheus™ 1, Automated Sleep Study Scoring and Data Management System (referred to as Morpheus TM in the table).

Similar to the other two predicate devices, the principal predicate device used for direct comparison, Alice 5, automatically scores polysomnography data based on user-specified criteria, and reports findings about sleep stages, arousals, periodic limb movements, and respiratory events in a conventional PSG report. The user may edit the automatic scoring but the report can be printed with or without editing.

MICHELEALICE 5SOMNOLYZER®24x7Morpheus™
Indicationsfor UseThe MICHELE SleepScoring System is acomputer program(software) intendedfor use as an aid forthe diagnosis of sleepand respiratory relatedsleep disorders.The MICHELE SleepScoring System isThe Alice 5 System isa PolysomnographySystem that isintended to record,display and printphysiologicalinformation toclinicians/physicians.These parameters arepresented graphicallySomnolyzer 24X7 isa computer program(software) intendedfor use as an aid forthe diagnosis of sleepand respiratorydisorders.Somnolyzer 24X7 isintended to be usedfor analysisThe Morpheus™ Automated Sleep Study Scoring and Data Management System is a computer program (software) intended for use as an aid for the diagnosis of sleep and

Table 6-5: Comparison of Indications for Use Statements

6-10

{10}------------------------------------------------

Image /page/10/Picture/1 description: The image shows a logo with the letters "YST" in a bold, serif font. A horizontal line underlines the letters, extending into a wavy line that resembles a heartbeat or sound wave. The logo is simple and monochromatic, with a focus on the typography and the dynamic line element.

Younes Sleep Technologies

MICHELEALICE 5SOMNOLYZER®24x7Morpheus™
intended to be usedfor analysis(automatic scoringand manualrescoring), display,redisplay (retrieve),summarize, reportsgeneration andnetworking of digitaldata collected bymonitoring devicestypically used toevaluate sleep andrespiratory relatedsleep disorders.The device is to beused under thesupervision of aphysician.on a computer screenfor diagnostic review,similar in applicationto the use of atraditional paperbased polygraphrecorder. The devicewill be used inhospitals, institutions,sleep centers orclinics, or otherenvironments whereadults or infantpatients require thedocumentation ofvarious sleep or otherphysiologicaldisorders. Thisdevice does notprovide alarms and, isnot intended for useas an automatedapnea monitor. (From510k Number(automatic scoringand manualrescoring), display,redisplay (retrieve),summarize, reportsgeneration andnetworking of datareceived frommonitoring devicestypically used toevaluate sleep andrespiratory relatedsleep disorders.This device is to beused under thesupervision of aphysician. (From510k NumberK083620)respiratorydisorders. TheMorpheus™ 1Automated SleepStudy Scoring andData ManagementSystem is intendedto be used foranalysis (automaticscoring and manualrescoring), display,redisplay (retrieve),summarize, reportsgeneration andnetworking of datareceived frommonitoring devicestypically used toevaluate sleep andrespiratory relatedsleep disorders.This device is to beused under thesupervision of a

6.4 Comparison of Technological Characteristics

The following table compares characteristics between MICHELE and the
three predicate devices, i.e. the Alice 5, Somnolyzer® 24x7 and Morpheus™. The comparison demonstrates that MICHELE is substantially equivalent to the predicate devices considering the essential characteristics identified in the table.

.

MICHELEALICE 5Somnolyzer®24x7MORPHEUSTM
Clinical Criteria:
Clinical condition or purpose:Diagnosis of sleep andrespiratory disordersXXX [7]X [8]
Population: Human subjectsXXX [9]X [2]
MICHELEALICE 5Somnolyzer®24x7MORPHEUSTM
undergoing sleep studies
Five-stage Sleep Stage Scoring(wake, Rem, three non-Remstages)XXX [3]X [2]
Arousal ScoringXX [11]X [9]X [2]
Respiratory Events ScoringXX [11]X [9]X [2]
Leg Movements ScoringXX [11]X [9]X [2]
Performance assessed bypercent agreement (andCohen's kappa) betweenautomatic and human scoringXX [11]X [6]X [2]
Basic operation: processing ofpolysomnography datarecorded from patients in sleeplaboratories andpolysomnography reportgenerationXX [11]X [9]X [10]
Data inputs for Sleep Stage and Arousal Scoring:
Central electroencephalogram(EEG)XX [11]X [9]X [2]
Left and right eyeelectroocculogram (EOG)XX [11]X [9]X [2]
Chin electromyogram (EMG)XX [11]X [9]X [2]
Electrocardiogram (ECG)XX [11]X [4]X [2]
Data inputs for Respiratory Events Scoring:
Chest and abdomenmovements measured byrespiratory bandsXX [11]X [4]X [2]
Oxygen saturationXX [11]X [4]X [2]
Respiratory airflowXX [11]X [4]X [2]
ThermisterXX [11]X [2]
AudioXX [11]X [2]
Body positionXX [11]X [2]
Airway CO2X
Airway pressureXX [11]
Data inputs for Leg Movements Scoring:
EMG recorded from right andleft legsXX [11]X [4]X [2]
Additional Technical Criteria:
Polysomnography recordsscored per 30 second epochXX [11]X [4]X [2]
Cardiac artifacts removed fromEEG, EMG and EOG channelsXX [2]

6-11

{11}------------------------------------------------

Image /page/11/Picture/0 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a stylized font, with a line underneath the letters. The line extends to the right of the letters and forms a wave-like pattern, possibly representing sleep patterns. Below the logo, the words "Younes Sleep Technologies" are written in a smaller, simpler font.

Traditional 510(k), MICHELE Sleep Scoring System Rev. 01 17-Oct-11

6-12

This document confidential information, which is the property of Younes Sieep Technologies (YST). This
document may not, in whole or in part, be duplicated, or used for d

{12}------------------------------------------------

YST

6.5 Description and Conclusions of Testing

MICHELE has been tested as described in Section 17 of this 510(k) Notification. Testing is an integral part of YST's software development process as described in the company's product development process.

The successful non-clinical testing demonstrates the safety and effectiveness of MICHELE when used for the defined indications for use and demonstrates that the device for which the 510(k) is submitted performs as well as the legally marketed predicate devices.

REFERENCES:

[1] Altman DG, Machin D, Bryant TN, Gardner MJ. Statistics With Confidence. British Medical Journal 2000.

[2] Pittman SD et al. (2004), "Assessment of Automated Scoring of Polysomnographic Recordings in a Population with Suspected Sleep-disordered Breathing," SLEEP 27:1394-1403.

[3] Svetnik V et al. (2007), "Evaluation of Automated and Semi-Automated Scoring of Polysomnographic Recordings from a Clinical Trial Using Zolpidem in the Treatment of Insomnia." SLEEP 30: 1562-1574.

[4] Anderer P et al. (2005), "An E-Health Solution for Automatic Sleep Classification according to Rechtschaffen and Kales: Validation Study of the Somnolyzer 24 x 7 Utilizing the Siesta Database," Neuropsychobiology 51:115-133

[5] Sleep-related breathing disorders in adults: recommendations for syndrome definition and measurement techniques in clinical research. The report of an American Academy of Sleep Medicine Task Force. Sleep 22: 667-689, 1999.

[6] The AASM Manual for the Scoring of Sleep and Associated Disorders. American Academy of Sleep Medicine, Westchester, Illinois. 2007

[7] 510(k) Summary, K083620, for The Siesta Group Somnolyzer 24x7

[8] 510(k) Summary, K022506, for the WideMed Ltd. MorpheusTM 1, Automated Sleep Study Scoring and Automated Data Management System

[9] Siesta Group website, http://www.thesiestagroup.com/index.php?id=167

[10] WideMed Ltd. website, http://www.widemed.com/

[11] Alice 5 User Manual

{13}------------------------------------------------

Image /page/13/Picture/1 description: The image is a circular logo for the U.S. Department of Health & Human Services. The logo features a stylized eagle with three wing strokes and a flowing tail. The text "DEPARTMENT OF HEALTH & HUMAN SERVICES • USA" is arranged around the top half of the circle.

Food and Drug Administration 10903 New Hampshire Avenue Document Control Room -WO66-G609 Silver Spring, MD 20993-0002

Mr. Magdy Younes President Younes Sleep Technologies 435 Ellice Avenue Winnipeg, Manitoba CANADA R3B 1Y6

DEC 2 0 2011

Re: K112102

Trade/Device Name: MICHELE Sleep Scoring System Regulation Number: 21 CFR 868.2375 Regulation Name: Breathing Frequency Monitor Regulatory Class: II Product Code: MNR Dated: October 17, 2011 Received: December 16, 2011

Dear Mr. Younes:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

{14}------------------------------------------------

Page 2 - Mr. Younes

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please go to http://www.fda.gov/AboutFDA/CentersOffices/CDRH/CDRHOffices /ucm115809.htm for the Center for Devices and Radiological Health's (CDRH's) Office of Compliance. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address http://www.fda.gov/MedicalDevices/Resourcesfor You/Industry/default.htm.

Sincerely yours.

h foc

Anthony D. Watson, B.S., M.S., M.B.A. Director Division of Anesthesiology, General Hospital, Infection Control and Dental Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

{15}------------------------------------------------

Image /page/15/Picture/0 description: The image shows the logo for Younes Sleep Technologies. The logo consists of the letters "YST" in a stylized font, with a line underneath the letters that extends into a wavy line. Below the logo is the text "Younes Sleep Technologies" in a smaller, sans-serif font.

Indications for Use

510(k) Number (if known):

Device Name: MICHELE Sleep Scoring System

Indications for Use:

The MICHELE Sleep Scoring System is a computer program (software) intended for use as an aid for the diagnosis of sleep and respiratory related sleep disorders.

The MICHELE Sleep Scoring System is intended to be used for analysis (automatic scoring and manual rescoring), display, redisplay (retrieve), summarizing, reports generation and networking of digital data collected by monitoring devices typically used to evaluate sleep and respiratory related sleep disorders.

The device is to be used under the supervision of a physician. Use is restricted to files obtained from adult patients.

Prescription Use X (Part 21 CFR 801 Subpart D)

AND/OR

Over-The-Counter Use (21 CFR 801 Subpart C)

(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)

L. Schult Concurrence of CDRH, Office of Device Evaluation (ODE)

(Division Sign-Off) Division of Anesthesiology, General Hospital Infection Control, Dental Devices

510(k) Number: K112102

Page 1 of

5-2

§ 868.2375 Breathing frequency monitor.

(a)
Identification. A breathing (ventilatory) frequency monitor is a device intended to measure or monitor a patient's respiratory rate. The device may provide an audible or visible alarm when the respiratory rate, averaged over time, is outside operator settable alarm limits. This device does not include the apnea monitor classified in § 868.2377.(b)
Classification. Class II (performance standards).