SOMNUM is a computer program (software) intended for use as an aid for the diagnosis of sleep and respiratory related sleep disorders. SOMNUM is intended to be used for analysis (automatic scoring and manual re-scoring), display, redisplay(retrieve), summarize and reports generation 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.

For respiratory events - Sleep Disordered Breathing (Apneas)- obstructive, central, mixed apneas, and hypopneas must be manually scored by physician. The device does not output specific apnea or hypopnea events and therefore should not be used for management decisions.

Device Description

SOMNUM is a standalone software application that analyze previously recorded physiological data obtained during level 1 sleep studies, referred to as polysomnography (PSG) records. The SOMNUM software can analyze any EDF files. Automated algorithms are applied to the raw signals in order to identify the occurrence of certain events. The software automates recognition of:

· Sleep Stage Events : Wake, Stage N1, Stage N2, Stage N3, Stage REM
Respiratory Events : Sleep Disordered Breathing (device output does not distinguish between Apneas and Hypopneas. Obstructive, central, mixed apneas, and hypopneas must be manually scored by physician)
· Arousal Events
· Leg Movement Events : Periodic Leg Movements during Sleep (PLMs)

The SOMNUM software can be used as a stand-alone application for use on Windows 10 operating system platform. All processing, scoring, and analysis of signal data occurs on local desktop PC.

AI/ML Overview

The Honeynaps Co., Ltd. Somnum (v.1.1.2) device underwent a non-clinical performance test to establish substantial equivalence to predicate devices for the analysis of sleep and respiratory-related sleep disorders.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly stated as numerical thresholds for specific metrics before the results table. However, the "Discussion" sections following the results implicitly define acceptable performance based on comparisons to predicate devices and acceptable error ranges in clinical practice. The reported device performance is shown in the tables below.

Endpoint 1: Performance for Detecting Each Event Type (Sleep Stage, Arousal, SDB, PLMs)

Event Type	Metric	SOMNUM Performance (CI)	Predicate Device (K162627) Reference Data	Predicate Device (K112102) Reference Data	Implied Acceptance Criteria (Based on discussion)
Sleep Stage (Overall OPA and Kappa with reference to K162627)	OPA	87.5% (87.2, 87.8)	91% (91,92)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	Kappa	82.1% (81.6, 82.5)	N/A	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
Wake	PPA	89.9% (89.2, 90.6)	86% (82,88)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	NPA	97.4% (97.3, 97.6)	97% (95,98)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
N1	PPA	77.9% (77.0, 78.9)	41% (33,48)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	NPA	94.6% (94.4, 94.9)	94% (93,96)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
N2	PPA	91.1% (90.7, 91.5)	77% (73,81)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	NPA	92.4% (92.0, 92.7)	87% (85,90)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
N3	PPA	84.1% (82.6, 85.6)	81% (74,88)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	NPA	99.1% (99.0, 99.2)	93% (91,95)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
REM	PPA	84.7% (83.8, 85.4)	79% (72,84)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	NPA	98.9% (98.8, 99.0)	99% (98,99)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
Arousal	OPA	82.5% (82.2, 82.9)	87% (85,88)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	PPA	82% (81.4, 82.6)	66% (61,71)	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	NPA	82.8% (82.4, 83.2)	90% (88,91)	N/A	The lower NPA (8% lower than predicate) is considered within "clinically acceptable error range of around 15%".
SDB	OPA	92.3% (92.1, 92.6)	93.0% (from K112102 ref [1]) & 91% (90,92) (from K162627 ref [4])	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	PPA	94.2% (93.8, 94.5)	75.5% (from ref [4]) & 67% (58, 75) (from ref [1])	N/A	Exceeds predicate performance.
	NPA	91.3% (91.0, 91.6)	98.1% (from ref [4]) & 93% (92, 94) (from ref [1])	N/A	The lower NPA (1.7% lower than K162627, 6.8% lower than K112102) is considered acceptable when considering overall performance (PPA, OPA) and the 15% manual scorer agreement error range.
PLMS	OPA	94.1% (93.9, 94.4)	95.7% (from ref [4]) & 89% (87,90) (from ref [1])	N/A	Comparable to predicate and within clinically acceptable error (approx. 15%).
	PPA	92.9% (92.1, 93.6)	78.4% (from ref [4]) & 71% (60,80) (from ref [1])	N/A	Exceeds predicate performance.
	NPA	94.3% (94.1, 94.5)	97.6% (from ref [4]) & 90% (89,92) (from ref [1])	N/A	The lower NPA is considered within "clinically acceptable range".

Endpoint 2: Performance for Summary Variables (Absolute Max Difference/LOA)

Variable	Type of Limit	SOMNUM Abs. MAX	Target (Reference) Abs. MAX	SOMNUM LOA Range	Reference LOA Range (if available)	Acceptance Criteria (Based on discussion)
TST	U	20	120 (Ref [5])	U: 7.8, L: -14.21	U: 35, L: -70	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
SE	U	5	13 (Ref [7])	U: 1.69, L: -3.31	U: 10, L: -12	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
SOL	U	23	40 (Ref [7])	U: 2.93, L: -4.21	U: 15, L: -11	SOMNUM's LOA range is narrower than references or within target. Exceeds target. Also, has smaller absolute error compared to target.
ROL	U	120	170 (Ref [5])	U: 62.01, L: -60.69	U: 70, L: -90	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
Wake	U	22	60 (Ref [7])	U: 14.21, L: -7.80	U: 70, L: -45	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
N1	U	45	80 (Ref [5])	U: 25.30, L: -17.29	U: 30, L: -30	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
N2	U	65	120 (Ref [5])	U: 31.61, L: -29.10	U: 10, L: -75	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
N1_N2	U	55	70 (Ref [5])	U: 31.58, L: -19.17	U: 30, L: -75	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
N3	U	40	140 (Ref [5])	U: 18.83, L: -30.45	U: 65, L: -5	SOMNUM's LOA range is narrower than references or within target. Also, has smaller absolute error compared to target.
REM	U	40	80 (Ref [5])	U: 6.07, L: -31.95	U: 18, L: -55	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
Arousal Index	U	30	-	U: 23.91, L: -15.21	-	SOMNUM's LOA range is narrower than references or within target. Exceeds target.
PLMS Index	U	43	7 (Ref [6])	U: 12.24, L: -0.37	U: 13, L: -15	Shows almost same value as target. Differences considered within 15% clinical error range.
AHI Index	U	18	7 (Ref [5])	U: 8.79, L: -3.28	U: 4, L: -2	SOMNUM has smaller absolute error compared to target.

Conclusion: The study concludes that SOMNUM passed all pass/fail criteria for both Endpoint 1 and Endpoint 2, demonstrating substantial equivalence.

2. Sample Size and Data Provenance

Sample Size (Test Set): N=48 subjects
Data Provenance: The data was recorded in a sleep laboratory. The country of origin is not explicitly stated. The study design is described as "cross-sectional experimental design," which implies it was specifically conducted for this evaluation. It is not explicitly stated if it's retrospective or prospective, but the phrasing "representative N=48 subjects of data recorded in the sleep laboratory" suggests it was existing data selected for the study.

3. Number of Experts and Qualifications for Ground Truth

Number of Experts: Three technologists.
Qualifications of Experts: "Medical professionals certified on PSG recording and analysis". Specific years of experience are not provided.

4. Adjudication Method

Adjudication Method: 2/3 majority rule. This means at least two out of the three experts had to agree on the presence of an event within an epoch for it to be considered ground truth.

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

A MRMC comparative effectiveness study was not conducted to measure the improvement of human readers with AI assistance versus without AI assistance. The study focuses on the standalone performance of the AI.

6. Standalone Performance Study

Yes, a standalone study was conducted. The performance test evaluated "SOMNUM device performance using a cross-sectional experimental design." The comparison was between SOMNUM's scoring and the ground truth established by expert consensus.

7. Type of Ground Truth Used

Type of Ground Truth: Expert consensus (2/3 majority rule of three certified medical professionals).

8. Sample Size for the Training Set

The document does not provide specific details regarding the sample size used for the training set. It only describes the performance test (test set).

9. How Ground Truth for Training Set was Established

The document does not provide details on how the ground truth for the training set was established. It only describes the ground truth establishment for the test set.

Summary

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

August 16, 2023

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Honeynaps Co., Ltd Tony Lee Official Correspondent 4F. Marine Tech B/D. 529. Nonhyeon-ro. Gangnam-gu Seoul. 06126 Korea, South

Re: K223922

Trade/Device Name: Somnum (v.1.1.2.) Regulation Number: 21 CFR 882.1400 Regulation Name: Electroencephalograph Regulatory Class: Class II Product Code: OLZ Dated: July 17, 2023 Received: July 17, 2023

Dear Tony Lee:

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. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. 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.

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

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

801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4. Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Patrick Antkowiak -S

for Jay Gupta Assistant Director DHT5A: Division of Neurosurgical, Neurointerventional and Neurodiagnostic Devices OHT5: Office of Neurological and Physical Medicine Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known) K223922

Device Name SOMNUM

Indications for Use (Describe)

X Prescription Use (Part 21 CFR 801 Subpart D)

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

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

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

Image /page/3/Picture/0 description: The image shows the logo for Honey Naps. The logo consists of a stylized letter "H" in two shades of blue, with the left side being a lighter blue and the right side being a darker blue. To the right of the "H" is the text "HONEY NAPS" in a dark blue sans-serif font. The word "HONEY" is above the word "NAPS".

Traditional 510(k) Premarket Submission

510(k) Summary

Device Name : SOMNUM (V.1.1.2. Final finished device)

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

Image /page/4/Picture/0 description: The image shows the logo for Honey Naps, a company that specializes in sleep products. The logo features a stylized "H" in blue, with the words "HONEY NAPS" in blue text to the right of the "H". Below the logo, the words "510(k) Summary" are written in a large, bold font.

In accordance with 21 CFR 807.92 the following summary of information is provided: Date : September 30, 2022

I. SUBMITTER

SUBMITTER :	Honeynaps
	529, Nonhyeon-ro, Gangnam-gu
	Seoul, Republic of Korea 06126
	Tel : +82-2-567-0134
CONTACT PERSON:	Honeynaps
	YoungJun Lee
	Chief Executive Officer
	tony.lee@honeynaps.com
PRIMARY CONTACT PERSON:	Honeynaps
	YoungJun Lee
	Chief Executive Officer
	tony.lee@honeynaps.com

II. DEVICE

Trade Name	SOMNUM
Common Name	Sleep Analysis System
Regulation Number	21 CFR 882.1400
Regulation Name	Electroencephalograph
Regulation Class	II
Classification Product Code	OLZ
Device Classification Name	Automatic Event Detection Software For Polysomnographwith Electroencephalograph
Review Panel	Neurology

Ⅲ. PREDICATE DEVICE
510(k) Number	K162627
Applicant	ENSODATA
Device Name	EnsoSleep
Regulation Number	21 CFR 882.1400
Regulation Name	Electroencephalograph
Regulation Class	II
Classification Product Code	OLZ
Device Classification Name	Automatic Event Detection Software For Polysomnographwith Electroencephalograph

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

Image /page/5/Picture/0 description: The image contains a logo with the text "HONEY NAPS". To the left of the text is a stylized letter "H" made up of two vertical bars connected by a horizontal bar. The left vertical bar is a lighter shade of blue than the right vertical bar. The logo appears to be for a company or product called "Honey Naps".

510(k) Number	K112102
Applicant	YOUNES SLEEP TECHNOLOGIES
Device Name	MICHELE SLEEP SCORING SYSTEM
Regulation Number	21 CFR 868.2375
Regulation Name	Breathing Frequency Monitor
Regulation Class	II
Classification Product Code	MNR
Device Classification Name	Ventilatory Effort Recorder

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

· Sleep Stage Events : Wake, Stage N1, Stage N2, Stage N3, Stage REM
Respiratory Events : Sleep Disordered Breathing (device output does not distinguish between Apneas and Hypopneas. Obstructive, central, mixed apneas, and hypopneas must be manually scored by physician)
· Arousal Events
· Leg Movement Events : Periodic Leg Movements during Sleep (PLMs)

The SOMNUM software can be used as a stand-alone application for use on Windows 10 operating system platform. All processing, scoring, and analysis of signal data occurs on local desktop PC.

V. INDICATIONS FOR USE

SOMNUM is a computer program (software) intended for use as an aid for the diagnosis of sleep and respiratory related sleep disorders. SOMNUM is intended to be used for analysis(automatic scoring and manual re-scoring), display, redisplay(retrieve), summarize, reports generation 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 adults patients.

For respiratory events - Sleep Disordered Breathing (Apneas and Hypopneas)- obstructive, central, mixed apneas, and hypopneas must be manually scored by physician. The device does not output specific apnea or hypopnea events and therefore should not be used for management decisions.

Description	Subject Device	Predicate Device
	SOMNUM	ENSOSLEEP(K162627)
Indications for Use	SOMNUM is a computer program(software) intended for use as anaid for the diagnosis of sleep andrespiratory related sleep disorders.SOMNUM is intended to be usedfor analysis(automatic scoring andmanual re-scoring), display,redisplay(retrieve), summarize,reports generation of digital datacollected by monitoring devicestypically used to evaluate sleep andrespiratory related sleep disorders.	EnsoSleep is intended for use for thediagnostic evaluation by a physician toassess sleep quality and as an aid for thediagnosis of sleep and respiratory relatedsleep disorders in adults only. EnsoSleepis a software-only medical device to beused under the supervision of a clinicianto analyze physiological signals andautomatically score sleep study results,including the staging of sleep, detection ofarousals, leg movements, and sleepdisordered breathing events includingobstructive apneas. All automatically

Table 1. Comparison of Indications for Use

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

	The device is to be used under thesupervision of a physician Use isrestricted to files obtained fromadults patients.For respiratory events - SleepDisordered Breathing (Apneas andHypopneas)- obstructive, central, mixedapneas, and hypopneas must bemanually scored by physician. Thedevice does not output specific apneaor hypopnea events and thereforeshould not be used for managementdecisions	scored events are subject to verificationby a qualified clinician. Central apneas,mixed apneas, and hypopneas must bemanually marked within records.
Intended Use	Analyze physiological data previouslyrecorded during sleep and presenta report.	Analyze physiological data previouslyrecorded during sleep and present areport.
Environment of Use	Healthcare Facility	Healthcare Facility

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

Image /page/8/Picture/0 description: The image shows the logo for Honey Naps. The logo consists of a stylized letter "H" on the left and the words "HONEY NAPS" on the right. The "H" is made up of two vertical bars connected by a horizontal bar, with circles at the top and bottom of each vertical bar. The word "HONEY" is above the word "NAPS". The colors of the logo are shades of blue.

VI. COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE PREDICATE DEVICE

There are no significant differences in the technological characteristics of this device compared to the predicate device which adversely affect safety or effectiveness. The below table is summarized and compared with the technological characteristics between the SOMNUM and the predicate device :

Table 2. Comparison of Technological Characteristics

Description	Subject DeviceSOMNUM	Predicate DeviceENSOSLEEP(K162627)
Clinical Criteria :
Clinical condition or purpose:Diagnosis of sleep andrespiratory disorders	YES	YES
Population: Human subjectsundergoing sleep studies	YES	YES
Five-stage Sleep Stage Scoring(Wake, REM, Three non-REMstages)	YES	YES
Arousal Scoring	YES	YES
Respiratory Events Scoring	YES	YES
Leg Movements Scoring	YES	YES
Performance assessed bypercent agreement(and Cohen'skappa) between automatic andhuman scoring	YES	YES
Basic operation: processing ofpolysomnography datarecorded from patients insleep laboratories andpolysomnography reportgeneration	YES	YES
Data inputs for Sleep Stage and Arousal Scoring:
Centralelectroencephalogram(EEG)	YES	YES
Left and right eyeelectroocculogram(EOG)	YES	YES
Chin electromyogram(EMG)	YES	YES
Electrocardiogram (ECG)	YES	YES
Data inputs for Respiratory Events Scoring :
Chest and abdomenmovements measured byrespiratory bands	YES	YES
Oxygen saturation	YES	YES

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

Image /page/9/Picture/0 description: The image shows the logo for Honey Naps. The logo consists of a stylized letter H on the left and the words "HONEY NAPS" on the right. The letter H is made up of two vertical bars connected by a horizontal bar in the middle. The words "HONEY NAPS" are written in a sans-serif font.

Respiratory airflow	YES	YES
Thermister	YES	YES
Audio	NO	YES
Body position	NO	YES
Airway CO2	NO	YES
Data inputs for Leg Movement Scoring :
EMG recorded from right andleft legs	YES	YES
Additional Technical Criteria :
Polysomnography recordsscored per 30 second epoch	YES	YES
Cardiac artifacts removed fromEEG, EMG and EOG channels	YES	YES
Others :
Standard of scoring manual	The AASM Manual for the Scoring ofSleep and Associated Events, 2016	The AASM Manual for the Scoring ofSleep and Associated Events, 2007
Re-scoring	YES	YES
File Format	.EDF, .XML, .JSON format	.EDF, .
Network	Access to Internet is not required.	Access to Internet is required
Operating System	Windows 10	Windows XP, Windows 7, Windows 10

VII. PERFORMANCE DATA

Software Verification & Validation

Support for the substantial equivalence of the SOMNUM Software was provided as a result of risk management and software testing. Software verification and validation testing were conducted and documentation was provided as recommended by FDA's Guideline for Industry and FDA Staff, "Guidance for the Content of Premarket Submission for Software Contained in Medical Device."(Document issued on : May 11, 2005)

· Verification of each independent software subsystem against defined requirements
· Verification of interfaces between software subsystems against defined interface requirements
· Validation of fully integrated system including all subsystems against overall system requirements

The results of the verification and validation activities that have been performed demonstrate that the software meets requirements to support substantial equivalence.

Performance Test (Non-clinical test)

Performance testing was completed by evaluating SOMNUM device performance using a cross-sectional experimental design on a representative N=48 subjects of data recorded in the sleep laboratory. Substantial Equivalence was established through a testing protocol that used full night studies data to evaluate the performance of SOMNUM. The goal of the test reported here is to establish that SOMNUM performance is equivalent to the performance of the predicate device. We confirm that SOMNUM does not present any new concerns about safety or effectiveness compared to the predicate device, MICHELE Sleep Scoring System(K112102). The performance was measured by epoch by epoch agreement between SOMNUM's

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

Image /page/10/Picture/0 description: The image contains the logo for Honey Naps. The logo consists of a stylized "H" made of rounded rectangles and circles, with the left side in a lighter blue and the right side in a darker blue. To the right of the "H" are the words "HONEY" stacked on top of "NAPS", both in the same darker blue color as the right side of the "H".

ing and the scoring of three technologists using 2/3 majority rule, that is, at least two out of three export scoring(medical professionals certified on PSG recording and analysis) agree on the presenceof an event within an epoch. SOMNUM device performance was evaluated using the defined test design, statistical methodology, and controls across the following two endpoints:

Endpoint 1. As SOMNUM is intended to analyze physiological signals and automatically score sleep study results, including sleep staging and detection of respiratory events, PLMs events, device performance for detecting each event type must be validated.

Endpoint 2. As SOMNUM is intended to present summary variables that appear in the clinical report used by physician to assess sleep disorders.

Test Result Summary

Data for End point 1

Sleep Stage

		SOMNUM					Reference[2]
		W	N1	N2	N3	R	W	N1	N2	N3	R
	W	89.96	6.93	0.86	0.14	4.13	82.2	35.9	4.0	0.5	5.8
		(89.22-	(6.35-	(0.73-	(0.00-	(3.69-
		90.67)	7.51)	0.98)	0.32)	4.61)
	N1	6.15	77.93	5.46	0.28	5.88	9.6	26.1	4.7	0.4	8.7
		(5.63-	(76.95-	(5.16-	(0.09-	(5.38-
		6.73)	78.86)	5.78)	0.52)	6.43)
Scorers	N2	2.06	13.21	91.13	15.52	5.37	3.8	33.2	85.0	16.0	12.3
		(1.75-	(12.42-	(90.71-	(14.02-	(4.84-
		2.41)	13.96)	91.47)	16.95)	5.84)
	N3	0.01	0.07	1.84	84.04	0.00	0.2	0.2	5.4	82.3	0.0
	R	1.81	1.86	0.72	0.05	84.62	4.2	4.7	0.8	0.8	73.2
		(1.49-	(1.53-	(0.60-	(0.00-	(83.81-
		2.14)	2.19)	0.84)	0.14)	85.48)

Table 3. Performance Comparison of sleep stage.

Arousal

Table 4. Performance Comparison of sleep stage.

SOMNUM				Reference[3]
EventTotalEpoch	PPA	NPA	OPA	EventTotalEpoch	PPA	NPA	OPA
13108	82.02(81.42-82.64)	82.78(82.41-83.17)	82.5(82.2-82.9)	6468	76.82	82.48	-

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

Image /page/11/Picture/0 description: The image contains the logo for Honey Naps. The logo consists of a stylized letter "H" made of two vertical bars connected by a horizontal bar in the middle. The left vertical bar is light blue, while the right vertical bar is dark blue. To the right of the "H" are the words "HONEY" and "NAPS" stacked on top of each other, both in dark blue.

SDB & PLMS

	SOMNUM				Reference[4]			Reference[1]
	EventTotalEpoch	PPA	NPA	OPA	EventTotalEpoch	PPA	NPA	OPA	EventTotalEpoch	PPA	NPA	OPA
SDB	15984	94.18(93.79-94.52)	91.29(90.98-91.61)	92.3(92.1-92.6)	2439	75.5	98.1	93.0	4705	67(58, 75)	93(92, 94)	91(90, 92)
PLMS	5215	92.89(92.18-93.55)	94.30(94.08-94.51)	94.1(93.9-94.4)	1741	78.4	97.6	95.7	5796	71(60, 80)	90(89, 92)	89(87, 90)

Table 5. Performance Comparison of sleep stage.

Please note that Event total Epoch means the total number of epochs with events. The total epoch is 43971 epochs (event epoch + non-event epoch).

Discussion:

For Sleep Stage and Arousal, SOMNUM exceeded all performance targets, while for SDB and PLMS, SOMNUM exceeded the performance targets for PPA. Comparing NPA of SOMNUM with that of predicate device, the NPA of SOMNUM' is 3.3% lower. however, it is unknown whether a statistically significant comparison can be made due to lack of Cl. Therefore, the NPA of K162627 was compared as the reference device, and in this case, SOMNUM showed good performance by 4.3%. In conclusion, the NPA performance for PLMS is considered to be within clinically acceptable range. The NPA for SDB showed a performance that was 1.7% lower than K162627 and about 6.8% lower than K112102. However, considering both PPA and OPA of SOMNUM, the overall performance of SOMNUM is better than that of K162627. In addition, considering the situation where there is no standard reference, it cannot be said that this difference shows the low performance of SOMNUM. Furthernore, the manual scorer agreement[8], which is generally acceptable in clinical practice, is considered to have an error range of around 15%, these performance differences are considered to be within the clinically acceptable error range.

In conclusion, SOMNUM passed all pass/fail criteria for Endpoint 1.

Data for End point 2:

Table 6. Performance Comparison of Relevant Scoring Variables Between SOMNUM and Performance Target for Endpoint

Variable	Type OfLimit	SOMNUM	abs. MAX	Target	abs. MAX	Unit
TST	U	10	20	60	120	[min]
	L	-20		-120

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

	NAPS						Variable	LOA	SOMNUM	References	Ref. No.	Unit
SE	U	2.5	5	10	13	%	TST(Total Sleep Time)	U	7.8	35	[5]	[min]
	L	-5		-13				L	-14.21	-70
SOL	U	8	23	40	40	[min]	SE(Sleep Efficiency)	U	1.69	10		%
	L	-23		-5				L	-3.31	-12	[7]
ROL	U	120	120	170	170	[min]	SOL(Sleep On Latency)	U	2.93	15	[7]	[min]
	L	-70		-130				L	-4.21	-11
Wake	U	22	22	60	60	[min]	ROL(REM On Latency)	U	62.01	70	[5]	[min]
	L	-10		-45				L	-60.69	-90
N1	U	30	45	80	80	[min]	Wake	U	14.21	70	[7]	[min]
	L	-45		-60				L	-7.80	-45
N2	U	65	65	70	120	[min]	N1	U	25.30	30	[5]	[min]
	L	-50		-120				L	-17.29	-30
N1_N2	U	55	55	70	70	[min]	N2	U	31.61	10	[5]	[min]
	L	-35		-60				L	-29.10	-75
N3	U	30	40	140	140	[min]	N1_N2	U	31.58	30	[5]	[min]
	L	-40		-10				L	-19.17	-75
REM	U	20	40	50	80	[min]	N3	U	18.83	65	[5]	[min]
	L	-40		-80				L	-30.45	-5
Arousal Index	U	30	30	-		events/hour	REM	U	6.07	18	[5]	[min]
	L	-20		-	-			L	-31.95	-55
PLMS Index	U	43		7		events/hour	Arousal Index	U	23.91	-	-	events/hour
	L	-2	43	-43	43			L	-15.21	-
AHI Index	U	18		7		events/hour	PLMS Index(Periodic LimbMovements of SleepIndex)	U	12.24	13		events/hour
	L	-7	18	-20	20			L	-0.37	-15	[6]
AHI Index(Apnea-Hypopnea Index)	U	8.79	4	[5]	events/hour
	L	-3.28	-2

Discussion: TST, SE, ROL, Wake, N1, N2, N1_N2, and REM satisfy the provided Upper and Lower LOA.

However, SOL has a target of -5 to 40, while SOMNUM has a range of -23 to 8, and N3 has a target of -10 to 140, while SOMNUM has a range of -40 to 30. The PLMS index has a target of -40 to 10, but SOMNUM has a range of -2 to 43, and the AHI index has a target of -20 to 7, but SOMNUM has a range of -7 to 18.

When considering the actual range of absolute errors, SOL has a target of 40 minutes, while SOMNUM has 23 minutes, and N3 has a target of 140, while SOMNUM has 40 minutes. The AHI index has a target of 22, but SOMNUM has 18, resulting in smaller absolute errors.

PLMS index has a target of 43, while SOMNUM has 43, it shows the almost same value. However, considering the 15% error among scorers presented in Reference [8], it cannot be said that it affects the performance.

In addition, we compared the LOA of Relevant Sleep Scoring Variables of SOMNUM and those of References. The table 12 showed the LOA of SOMNUM and References.

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

Image /page/13/Picture/0 description: The image shows the logo for Honey Naps. The logo consists of a stylized letter "H" on the left, with the word "HONEY" above the word "NAPS" on the right. The letter "H" is made up of two vertical bars connected by a horizontal bar, with circles at the top and bottom of each vertical bar. The left vertical bar is light blue, and the right vertical bar is dark blue. The words "HONEY NAPS" are also dark blue.

Table 7. Performance Comparison of LOA between SOMNUM and References for Endpoint 2

When comparing the LOA ranges of SOMNUM and References, the CI ranges of SOMNUM is narrower than those of the references except for AHI. In conclusion, SOMNUM passed all pass/fail criteria for Endpoint 2.

Output Comparison Data

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

Image /page/14/Picture/0 description: The image contains the logo for Honey Naps. The logo consists of a stylized letter "H" on the left, with the words "HONEY" and "NAPS" stacked on top of each other to the right of the "H". The "H" is made up of two vertical bars connected by a horizontal bar in the middle, with circles at the top and bottom of each vertical bar. The logo is colored in shades of blue.

SCORINGFUNCTION	SOMNUM					ENSOSLEEP(K162627)
	TotalEpochs	PPA(%)	NPA(%)	OPA(%)	kappa(%)	TotalEpochs	PPA(%)	NPA(%)	OPA(%)	kappa(%)
SLEEPSTAGING	43971			87.5(87.2,87.8)	82.1(81.6,82.5)	59719	78(77,80)	95(94,95)	91(91,92)
Awake	6719	89.9(89.2,90.6)	97.4(97.3,97.6)			17459	86(82,88)	97(95,98)	94(92,95)
N1	6522	77.9(77.0,78.9)	94.6(94.4,94.9)			3293	41(33,48)	94(93, 96)	91(90,93)
N2	20448	91.1(90.7,91.5)	92.4(92.0,92.7)			26839	77(73,81)	87(85,90)	83(80,85)
N3	1012	84.1(82.6,85.6)	99.1(99.0,99.2)			5587	81(74,88)	93(91,95)	92(90,94)
REM	7364	84.7(83.8,85.4)	98.9(98.8,99.0)			6541	79(72,84)	99(98,99)	96(96,97)
No Consensus	756					1432
AROUSAL	43971			82.5(82.2,82.9)	60.8(60.1,61.5)	59719			87(85,88)	-
Yes	13108	82(81.4,82.6)	82.8(82.4,83.2)			7686	66(61,71)	90(88,91)
None	30863
No Consensus	0					0
PLMS	43971			94.1(93.9,94.4)	75.7(74.7,76.5)	59719			89(87,90)	-
Yes	8509	92.9(92.1,93.6)	94.3(94.1, 94.5)			5796	71(60,80)	90(89,92)
None	35462
No Consensus	0					0
RESPIRATORYEVENTS	43971			92.3(92.1,92.6)	83.8(83.2,84.3)	59719			91(90,92)	-
YES	15984	94.2(93.8,94.5)	91.3(91.0,91.6)			4705	67(58,75)	93(92,94)
None	27987
No Consensus	0					0

Discussion : Except for the NPA of Arousal, SOMNUM is superior to the predicate device in all PPA and NPA. However, the NPA of arousal is about 8% lower, but this is within the limit that can be seen between general scorers. The manual scorer agreement[8], which is generally acceptable in clinical practice, is considered to have an error range of around 15%, these performance differences are considered to be within the clinically acceptable error range.

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

Image /page/15/Picture/0 description: The image contains the logo for Honey Naps. The logo consists of a stylized "H" made of two vertical bars connected by a horizontal bar in the middle. The "H" is colored in shades of blue. To the right of the "H" is the text "HONEY NAPS" in a sans-serif font, with "HONEY" in a lighter blue and "NAPS" in a darker blue.

Clinical Test Summarv

No clinical studies were considered necessary and performed.

Summary

In summary, performance test results demonstrated that SOMNUM achieved sleep disordered breathing, arousal, PLMs events detection agreement that is substantially equivalent to the predicate device Ensosleep (K162627) and MICHELE Sleep Scoring(K112102) performance for all comparisons in all endpoints analyzed respectively. The SOMNUM performance validation testing demonstrates the safety and effectiveness of SOMNUM whenused for the defined indications for use. The performance data demonstrates that the SOMNUM device performs comparably to the predicate device that is currently marketed for the same intended use.

References

[1] FDA, 510(k) Summary(MICHELE Sleep Scoring System, K112102)

[2] DJ Levendowski, et. al. "The Accuracy, Night-to-Night Variability, and Stability of Frontopolar Sleep Electroencephalography Biomarkers" Journal of Clinical Sleep Medicine, Vol. 13, No. 6, pp.791 - 803, 2017

[3] F De Carli, et. al, "A Method for the Automatic Detection of Arousals During Sleep, Vol. 22, No. 5, pp. 561~572, 1999

[4] FDA, K162627 510K summary report

[5] Atul Malhotra, et. al., "Performance of an Automated Polysomnography Scoring System Versus Computer-Assisted Manual Scoring" SLEEP, Vol. 36, No. 4, pp. 573-582, 2013

(6) S. D. Pittman, et. al., "Assessment of Automated Scoring of Polysomnographic Recordings in a Population with Suspected Sleep-disordered Breathing", SLEEP, Vol. 27, No. 7, 2004 pp.1394-1403

[7] C. Stepnowsky, et. al, "Scoring accuracy of automated sleep staging from a bipolar recording compared to manual scoring by multiple raters, Sleep Medicine 14 (2013) 1199-1207

[8] T. Penzel, "Sleep scoring moving from visual scoring", SLEEP, 2022, Vol. 45, No. 10. pp. 1 – 3.

{16}------------------------------------------------

Image /page/16/Picture/0 description: The image shows the logo for Honey Naps, which is a blue stylized H with two circles on the left, and the words "HONEY NAPS" in blue on the right. Below the logo, the words "VIII. CONCLUSIONS" are written in black. The text is in a simple, sans-serif font.

Based on a comparison of the intended use and technological characteristics, performance test, the SOMNUM software is substantially equivalent to the identified predicate device. Minor differences in technological and performance characteristics did not raise new or different questions of safety and effectiveness. Additionally, the non-clinical testing supports that the system performs in accordance with its intended use and is as safe, as effective, and performs as well as the predicate device.

Regulation Number and Section

§ 882.1400 Electroencephalograph.

(a)
Identification. An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.(b)
Classification. Class II (performance standards).