SOMNUM (SOMNUM)

K253390 · Honeynaps Co., Ltd. · OLZ · Jun 27, 2026 · Neurology

Device Facts

• Record ID: K253390
• Device Name: SOMNUM (SOMNUM)
• Applicant: Honeynaps Co., Ltd.
• Product Code: OLZ · Neurology
• Decision Date: Jun 27, 2026
• Decision: SESE
• Submission Type: Traditional
• Regulation: 21 CFR 882.1400
• Device Class: Class 2
• Attributes: AI/ML, Software as a Medical Device, Real-World Evidence

Real-World Evidence

Submission	Device	Sponsor	RWD Sources	RWE Use Summary	Key Tags
K253390 · Jun 27, 2026	SOMNUM (SOMNUM)	Honeynaps Co., Ltd.	National Sleep Research Resource (NSRR) STAGES dataset; Routine clinical PSG recordings from U.S. sleep centers (Bogan Sleep Consulting, Geisinger Health, MedSleep, St. Luke's Hospital); Routine clinical PSG recordings from Korean sleep laboratories (Soonchunhyang University Hospital, Ajou University Hospital, Chungnam National University Hospital)	Retrospective clinical performance studies were conducted to validate the AI/ML algorithms for sleep stage classification, arousal detection, respiratory event detection, and leg movement detection by comparing device output against a consensus reference standard derived from routine clinical PSG data.	Retrospective study; PSG; Sleep disorders; AI/ML validation; Clinical performance

Clinical Evidence

Study Design	Population	Comparator	Key Endpoints
U.S. STAGES Study; Retrospective cross-sectional validation study; Follow-up/Duration: Full-night PSG	100 adult subjects (50 male, 50 female); Sample Size: 100; Number of Sites: 4	Not applicable for this study	Sleep stage classification, arousal detection, respiratory event detection, and PLM detection accuracy
Korean 48 case study; Retrospective cross-sectional clinical performance study; Follow-up/Duration: Full-night PSG	48 adult subjects (32 male, 16 female); Sample Size: 48; Number of Sites: 3	Not applicable for this study	Epoch-level agreement, subject-level agreement for sleep variables, and patient-level diagnostic performance for sleep apnea

AI Performance

Output	Algorithm	Acceptance	Observed	Dev DS	Dev Readers	Test DS	Test Readers
Sleep Stage Classification	AI/ML algorithms	—	W: 93.6%, N1: 81.4%, N2: 93.7%, N3: 87.9%, R: 89.8%	—	—	U.S. STAGES Study: 100 full-night PSG recordings from four U.S. sleep centers.	3 (RPSGT-certified PSG technologists) + 1 (board-certified sleep physician)
Arousal Detection	AI/ML algorithms	—	PPA: 83.8%, NPA: 99.4%, OPA: 98.74%	—	—	U.S. STAGES Study: 100 full-night PSG recordings from four U.S. sleep centers.	3 (RPSGT-certified PSG technologists) + 1 (board-certified sleep physician)
Respiratory Event Detection	AI/ML algorithms	—	Hypopnea PPA: 81.71%, Obstructive Apnea PPA: 86.26%, Central Apnea PPA: 82.19%, Mixed Apnea PPA: 75.67%	—	—	U.S. STAGES Study: 100 full-night PSG recordings from four U.S. sleep centers.	3 (RPSGT-certified PSG technologists) + 1 (board-certified sleep physician)
Periodic Leg Movement Detection	AI/ML algorithms	—	PPA: 87.18%, NPA: 98.61%, OPA: 97.63%	—	—	U.S. STAGES Study: 100 full-night PSG recordings from four U.S. sleep centers.	3 (RPSGT-certified PSG technologists) + 1 (board-certified sleep physician)

Indications for Use

SOMNUM is an AI-enabled software program intended for use as an aid in the diagnosis of sleep and respiratory-related sleep disorders. SOMNUM is intended to be used for analysis — including automatic scoring using AI/ML algorithms for sleep stage classification, arousal detection, respiratory event detection, and leg movement event detection, as well as manual scoring/re-scoring, display, redisplay (retrieve), summarization, and report 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 data obtained from adult patients.

Device Story

SOMNUM is an AI-enabled standalone software application for analyzing recorded physiological data from adult level 1 sleep studies (PSG). It processes EDF-formatted inputs (EEG, EOG, EMG, ECG, respiratory effort, airflow, SpO2) using AI/ML algorithms to automatically score sleep stages (Wake, N1-N3, REM), arousals, respiratory events (apnea/hypopnea), and leg movements. Physicians review, edit, or delete auto-scored events and generate summary reports for clinical assessment. Used in healthcare facilities, the device assists clinicians in diagnosing sleep disorders by automating labor-intensive scoring tasks, potentially improving diagnostic efficiency and consistency.

Clinical Evidence

Clinical evidence includes two retrospective cross-sectional studies. The U.S. STAGES study (100 adults) compared SOMNUM to a 3-technologist consensus reference standard. Results showed high agreement: sleep stage classification (81.4–93.7% accuracy), arousal detection (83.8% PPA), and respiratory event detection (PPA 75.7–86.3%). A 48-case Korean study confirmed performance across epoch-level, subject-level, and patient-level endpoints. Bland-Altman and Deming regression confirmed clinical agreement for sleep variables. Diagnostic performance for sleep apnea (AHI) showed high sensitivity (up to 100%) and specificity, with likelihood ratios supporting clinical reliability.

Technological Characteristics

Standalone software application; processes EDF (European Data Format) files. Inputs: EEG (F3, F4, M1, M2, C3, C4, O1, O2), EOG, Chin EMG, ECG, respiratory effort (chest/abdomen), SpO2, airflow, thermistor, leg EMG. AI/ML-based algorithms for sleep staging, arousal, respiratory event, and leg movement detection. Rule-based subclassification for apnea (obstructive, central, mixed). PC-based, non-networked (standalone).

Indications for Use

Indicated for adult patients (22+ years) to aid in the diagnosis of sleep and respiratory-related sleep disorders by analyzing polysomnography (PSG) data. Used under physician supervision.

Regulatory Classification

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.

Predicate Devices

• SOMNUM (V.1.1.2.) (K223922)

Reference Devices

• EnsoSleep (K210034)
• MICHELE SLEEP SCORING SYSTEM (K112102)

Submission Summary (Full Text)

{0}

**FDA** **U.S. FOOD & DRUG**
ADMINISTRATION

June 27, 2026

Honeynaps co., Ltd.
Young Jun Lee
Chief Executive Officer
4F, Marin B/D, 529, Nonhyeon-ro, Gangnam-gu
Seoul, 06126
Republic Of Korea

Re: K253390

Trade/Device Name: Somnum (somnum)

Regulation Number: 21 CFR 882.1400

Regulation Name: Electroencephalograph

Regulatory Class: Class II

Product Code: OLZ

Dated: May 25, 2026

Received: May 26, 2026

Dear Young Jun 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 (the 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 available 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.

{1}

K253390 - Young Jun Lee

Page 2

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled 'Deciding When to Submit a 510(k) for a Change to an Existing Device' (https://www.fda.gov/media/99812/download) and 'Deciding When to Submit a 510(k) for a Software Change to an Existing Device' (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13485 clause 8.3 (Nonconforming product), ISO 13485 clause 8.5.2 (Corrective action), and ISO 13485 clause 8.5.3 (Preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and ISO 13485 clause 7.5) and document changes and approvals in the Medical Device File (ISO 13485 clause 4.2.3).

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 Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ('UDI Rule'). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.

Also, please note the regulation entitled, 'Misbranding by reference to premarket notification' (21 CFR 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-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/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

{2}

K253390 - Young Jun Lee

Page 3

the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email ([e-mail]) or phone [phone] 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

{3}

# Indications for Use

| Please type in the marketing application/submission number, if it is known. This textbox will be left blank for original applications/submissions. | | K253390 | ? |
| --- | --- | --- | --- |
| Please provide the device trade name(s). | | | ? |
| SOMNUM (SOMNUM) | | | |
| Please provide your Indications for Use below. | | | ? |
| SOMNUM is an AI-enabled software program intended for use as an aid in the diagnosis of sleep and respiratory-related sleep disorders. SOMNUM is intended to be used for analysis — including automatic scoring using AI/ML algorithms for sleep stage classification, arousal detection, respiratory event detection, and leg movement event detection, as well as manual scoring/re-scoring, display, redisplay (retrieve), summarization, and report 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 data obtained from adult patients. | | | |
| Please select the types of uses (select one or both, as applicable). | ☑ Prescription Use (21 CFR 801 Subpart D) ☐ Over-The-Counter Use (21 CFR 801 Subpart C) | | ? |
| Please select the age group(s) for which the device(s) is to be used. | ☐ Neonates/Newborns (Birth to < 29 days old) ☐ Infants (29 days old to < 2 years old) ☐ Children (2 years old to < 12 years old) ☐ Adolescents (12 years old to < 22 years old) ☑ Adults (22 years old and greater) | | ? |

{4}

HONEY NAPS

Doc. No. 510(k) Summary

# 510(k) Summary

# 1. Submitter Information

| Submitter | Name | Honeynaps |
| --- | --- | --- |
| | Address | 529, Nonhyeon-ro, Gangnam-gu, Seoul, Republic of Korea 06126 |
| | Tel | [phone] |
| Contact Person | Name | Young Jun Lee |
| | Title | CEO (Chief Executive Officer) |
| | Email | [e-mail] |
| Primary Contact Person | Name | Joo Hoon Song |
| | Title | Team Leader / Quality Innovation Team |
| | Email | [e-mail] |

# 2. Subject Device Information

| 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 Polysomnography with Electroencephalography |
| Review Panel | Neurology |

# 3. Predicated Device and Reference Device Information

# 3.1 Predicated Device

| 510(k) Number | K223922 |
| --- | --- |
| Applicant | Honeynaps Co., Ltd |
| Device Name | SOMNUM (V.1.1.2.) |

Confidential – Honeynaps Co., Ltd.

Page 1 / 19

{5}

**HONEY
NAPS**

Doc. No. 510(k) Summary

| Regulation Number | 21 CFR 882.1400 |
| --- | --- |
| Regulation Name | Electroencephalograph |
| Regulation Class | II |
| Classification Product Code | OLZ |
| Device Classification Name | Automatic Event Detection Software for Polysomnography with Electroencephalography |

### 3.2 Reference Device 1

| 510(k) Number | K210034 |
| --- | --- |
| Applicant | EnsoData, Inc |
| 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 Polysomnography with Electroencephalography |

### 3.3 Reference Device 2

| 510(k) Number | K112102 |
| --- | --- |
| Applicant | YOUNES SLEEP TECHNOLOGIES |
| Device Name | MICHELE SLEEP SCORING SYSTEM |
| Regulation Number | 21 CFR 868.2375 |
| Regulation Name | Beathing frequency monitor |
| Regulation Class | II |
| Classification Product Code | MNR |
| Device Classification Name | ventilatory effort recorder |

Confidential – Honeynaps Co., Ltd.

Page 2 / 19

{6}

HONEY
NAPS

Doc. No. 510(k) Summary

# 4. Device Description

SOMNUM is an AI-enabled stand-alone software application that analyzes previously recorded physiological data obtained during level 1 sleep studies from adults (polysomnography, PSG records). SOMNUM automatically detects events and displays scoring results using artificial intelligence (AI)-based algorithms across all functional modules. Physicians can review, edit, or delete auto-scored events and generate a sleep summary report, which includes tables and graphs used for clinical assessment of sleep disorders.

Automated AI algorithms are applied to raw signals to identify specific events. In particular, the Sleep Stage Classification module, the Arousal Detection module, the Respiratory Event Detection module, and the Leg Movement Detection module are all powered by AI/ML algorithms. The software automates recognition of the following events:

- Sleep Stage Classification (AI/ML-based): Wake, N1, N2, N3, REM
Arousal Event (AI/ML-based): Arousal
- Respiratory Events (AI/ML-based): Apnea, Hypopnea
- Apnea subclassification (Rule-based): Obstructive, Central, Mixed
- Leg Movement Event (AI/ML-based): Periodic Leg Movements during Sleep (PLMs)

# 5. Indications for Use

SOMNUM is an AI-enabled software program intended for use as an aid in the diagnosis of sleep and respiratory-related sleep disorders. SOMNUM is intended to be used for analysis — including automatic scoring using AI/ML algorithms for sleep stage classification, arousal detection, respiratory event detection, and leg movement event detection, as well as manual scoring/re-scoring, display, redisplay (retrieve), summarization, and report 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 data obtained from adult patients.

Confidential – Honeynaps Co., Ltd.

Page 3 / 19

{7}

**HONEY
NAPS**

Doc. No. 510(k) Summary

# **6. Comparison of Technological Characteristics to the Predicated Device**

| | Result | Subject Device | Predicated Device | Reference Device 1 | Reference Device 2 |
| --- | --- | --- | --- | --- | --- |
| **General Information** | | | | | |
| Trade Name | - | SOMNUM | SOMNUM | EnsoSleep | MICHELE SLEEP SCORING SYSTEM |
| 510(k) Number | - | K253390 | K223922 | K210034 | K112102 |
| 510(k) Submitter | - | Honeynaps | Honeynaps | EnsoData, Inc | YOUNES SLEEP TECHNOLOGIES |
| Classification Product Code | - | OLZ | OLZ | OLZ | MNR |
| Indication for Use | Same | SOMNUM is an AI-enabled software program intended for use as an aid in the diagnosis of sleep and respiratory-related sleep disorders. SOMNUM is intended to be used for analysis — including automatic scoring using AI/ML | 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, | EnsoSleep is intended for use in the diagnostic evaluation by a physician to assess sleep quality and as an aid for physicians in the diagnosis of sleep disorders and respiratory related sleep disorders in pediatric and adult patients as follows: | 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 |

Confidential – Honeynaps Co., Ltd.

Page 4 / 19

{8}

**HONEY
NAPS**

Doc. No. 510(k) Summary

| | | algorithms for sleep stage classification, arousal detection, respiratory event detection, and leg movement event detection, as well as manual scoring/re-scoring, display, redisplay (retrieve), summarization, and report 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 | 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. | •Pediatric patients ages 13 years and older with polysomnography (PSG) tests obtained in a Hospital or Sleep Clinic •Adult patients with PSGs obtained in a Hospital or Sleep Clinic •Adult patients with Home Sleep Tests •EnsoSleep is a softwareonly medical device to be used under the supervision of a clinician to analyze physiological signals and automatically score sleep study results, including the staging of sleep, detection of arousals, leg movements, and sleep disordered breathing events including | (automatic scoring and manual re-scoring), 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. |
| --- | --- | --- | --- | --- | --- |

Confidential – Honeynaps Co., Ltd.

Page 5 / 19

{9}

HONEY NAPS

Doc. No. 510(k) Summary

| | | physician. Use is restricted to files obtained from adult patients. | | obstructive apneas (OSA), central sleep apneas (CSA), and hypopneas. Central sleep apneas (CSA) should be manually reviewed and modified as appropriate by a clinician. All events can be manually marked or edited within records during review. Photoplethysmography (PPG) total sleep time is not intended for use when electroencephalograph (EEG) data is recorded. PPG total sleep time is not intended to be used as the sole or primary basis for diagnosing any sleep related breathing | |
| --- | --- | --- | --- | --- | --- |

Confidential – Honeynaps Co., Ltd.

Page 6 / 19

{10}

**HONEY
NAPS**

Doc. No. 510(k) Summary

| | | | | disorder, prescribing treatment, or determining whether additional diagnostic assessment is warranted. | |
| --- | --- | --- | --- | --- | --- |
| Intended Use | Same | Analyze physiological data previously recorded during sleep and present a report. | Analyze physiological data previously recorded during sleep and present a report. | Analyze pre-recorded physiological data acquired during sleep. | Analyze physiological data previously recorded during sleep and present a report. |
| Environment of Use | Same as Predicated Device | Healthcare Facility | Healthcare Facility | Physician office (data analysis and reporting). No limitation on where data are acquired. | Healthcare Facility |
| **Input & Output Data (Result)** | | | | | |
| Data format (Input) | Same as Predicated Device | EDF (European Data Format) | EDF (European Data Format) | EDF (European Data Format) | EDF (European Data Format) |
| Input Channel | Same (AASM Guidance) | EEG(F3, F4, M1, M2, C3, C4, O1, O2) EOG(E1, E2, M1, M2) Chin EMG ECG | EEG(F3, F4, M1, M2, C3, C4, O1, O2) EOG(E1, E2, M1, M2) Chin EMG ECG | EEG, ECG, EOG, EMG waveforms; SpO2; Respiratory effort; Airflow; | EEG EOG Chin EMG ECG Chest and abdomen |

Confidential – Honeynaps Co., Ltd.

Page 7 / 19

{11}

**HONEY
NAPS**

Doc. No. 510(k) Summary

| | | Chest and abdomen movements measured by respiratory band Oxygen Saturation Respiratory Airflow Thermistor Leg EMG(Left/Right) | Chest and abdomen movements measured by respiratory band Oxygen Saturation Respiratory Airflow Thermistor Leg EMG(Left/Right) | Heart / pulse rate; Snoring loudness; Head movement and position. | movements measured by respiratory band Oxygen Saturation Respiratory Airflow Thermistor Audio Body Position Airway CO2 Leg EMG(Left/Right) |
| --- | --- | --- | --- | --- | --- |
| Output Result | Same as Predicated Device | Sleep Stage Arousal Apnea (Obstructive, Central, Mixed) / Hypopnea PLMs | Sleep Stage Arousal SBD (Sleep Breathing Disorder) PLMs | Sleep Stage Arousal Apnea (Obstructive, Central) / Hypopnea PLMs | Sleep Stage Arousal Apnea (Obstructive, Central, Mixed) / Hypopnea PLMs |
| **Auto Scoring Algorithm** | | | | | |
| Sleep Stage | Same | Five-stage Sleep Stage Scoring (Wake, Sleep Stage N1, N2, N3, REM) | Five-stage Sleep Stage Scoring (Wake, Sleep Stage N1, N2, N3, REM) | Five-stage Sleep Stage Scoring (Wake, Sleep Stage N1, N2, N3, REM) | Five-stage Sleep Stage Scoring (Wake, Sleep Stage N1, N2, N3, REM) |
| Arousal | Same as Predicated | Detects arousal event | Detects arousal event | Detects arousal event Respiratory-effort related | Detects arousal event |

Confidential – Honeynaps Co., Ltd.

Page 8 / 19

{12}

**HONEY
NAPS**

Doc. No. 510(k) Summary

| | device | | | arousal (RERA) Limb movement arousal Spontaneous cortical arousal | |
| --- | --- | --- | --- | --- | --- |
| Apnea | Same as Predicated device | Yes | Yes | Yes | Yes |
| Obstructive Apnea | Same as Reference device | Yes Detects OSA event | No. OSA must be manually scored | Yes Detects OSA event | Yes Detects OSA event |
| Central Apnea | Same as Reference device | Yes Detects CSA event | No. CSA must be manually scored | Yes Detects CSA event | Yes Detects CSA event |
| Mixed Apnea | Same as Predicated device | Yes Detects MSA event | No. MSA must be manually scored | No. MSA must be manually scored | Yes Detects MSA event |
| Hypopnea | Same | Yes | Yes | Yes | Yes |
| LM | Same | Yes | Yes | Yes | Yes |
| PLMs | Same | Yes | Yes | Yes | Yes |
| **Manual Scoring (Edit)** | | | | | |
| Event Edit (Add, Edit, | Same as Predicated | Yes Available Manual | Yes Available Manual Re- | No | No |

Confidential – Honeynaps Co., Ltd.

Page 9 / 19

{13}

**HONEY
NAPS**

Doc. No. 510(k) Summary

| Delete) | device | Scoring | Scoring | | |
| --- | --- | --- | --- | --- | --- |
| **Report** | | | | | |
| AASM Polysomnography Report | Same | Yes | Yes | Yes | Yes |
| Customized Report | Same | Yes | Yes | Yes | No |
| **Others** | | | | | |
| Network | Same as Predicated device | No PC Stand-Alone | No PC Stand-Alone | Yes | Yes |

Confidential – Honeynaps Co., Ltd.

20

Page 10 /

{14}

HONEY
NAPS

Doc. No. 510(k) Summary

# 7. Performance Data

# 7.1 Software Verification & Validation

The subject device software underwent verification and validation testing at the unit, integration, and system levels in accordance with FDA guidance and IEC 62304 processes. Testing was conducted on the final release version, and all test protocols were successfully executed with acceptable pass results. A regression analysis and regression testing were performed to ensure that modifications did not introduce unintended effects. Any anomalies identified during testing were resolved or determined, through risk assessment, not to impact safety or effectiveness. Collectively, the results demonstrate that the software performs as intended and supports substantial equivalence to the predicate device.

# 7.2 Clinical Study Summary of – U.S. STAGES Study

# Study Design

An independent retrospective cross-sectional validation study was conducted to evaluate the clinical performance of SOMNUM (V.3.0.0) using 100 full-night PSG recordings selected from the National Sleep Research Resource (NSRR) STAGES dataset. PSG recordings were collected from four U.S. sleep centers: Bogan Sleep Consulting, Geisinger Health, MedSleep, and St. Luke's Hospital.

# Reference Standard Generation

The reference standard was independently generated by three RPSGT-certified PSG technologists in accordance with AASM Scoring Manual criteria, without access to SOMNUM automatic scoring output. A 2/3 majority consensus approach was used to establish the final reference label for each epoch. Of 92,383 total epochs, 1,938 epochs (2.10%) were identified as non-consensus epochs and were independently adjudicated by a board-certified sleep physician serving as the final adjudicator. Reported performance metrics are based on consensus-scorable epochs and may not fully reflect device performance in the most clinically ambiguous cases. Non-consensus epochs occurred most frequently during N1 sleep stage classification (56.3% of non-consensus epochs), and device performance estimates may therefore be more optimistic in clinically ambiguous sleep stage classification cases than in routine clinical practice.

# Patient Characteristics

The validation cohort included 100 adult subjects (50 male, 50 female). The mean age was 46.9 ± 14.17 years for male subjects and 49.1 ± 13.16 years for female subjects.

# Performance Summary

# 1) Test Data Utilized

Confidential – Honeynaps Co., Ltd.

Page 11 / 19

{15}

HONEY NAPS

Doc. No. 510(k) Summary

| All | Sex | Age | BMI |
| --- | --- | --- | --- |
| | Male: 50 | 46.9(±14.17) | 31.52(±7.56) |
| | Female: 50 | 49.1 (±13.16) | 33.83(±8.27) |

A total of 100 patient datasets were included, consisting of 50 males (mean age 46.9 years old) and 50 females (mean age 49.1 years old).

Race, Sex and BMI covered a wide range representing the characteristics typically observed in clinical practice.

Dataset included BMI values ranging from normal weight to overweight/obese, demonstrating that the algorithm's performance is not limited to a specific population subgroup. This dataset incorporated multi-center and multi-ethnic populations, supporting the generalizability of the software performance evaluation.

### 7.3 Test Result Summary

1) Data for End Point 1.

Confidential – Honeynaps Co., Ltd.

Page 12 / 19

{16}

**HONEY
NAPS**

Doc. No. 510(k) Summary

# - Sleep Stage

**Table 1 Performance Comparison of Sleep Stage**

| | SOMNUM | | | | | Reference | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | W | N1 | N2 | N3 | R | W | N1 | N2 | N3 | R |
| **W** | 93.6 % [93.3– 93.9] | 4.1% [3.8– 4.3] | 1.5% [1.3– 1.6] | 0.3% [0.2– 0.4] | 0.6% [0.5– 0.7] | 82. 2 | 35. 9 | 4.0 | 0.5 | 5.8 |
| **N 1** | 4.3% [3.9– 4.7] | 81.4% [80.6 – 82.2] | 12.4 % [11.7– 13.1] | 0.4% [0.3– 0.6] | 1.5% [1.2– 1.7] | 9.6 | 26. 1 | 4.7 | 0.4 | 8.7 |
| **N 2** | 0.8% [0.8– 0.9] | 1.2% [1.1– 1.3] | 93.7% [93.5– 94.0] | 1.8% [1.7– 2.0] | 2.4% [2.3– 2.6] | 3.8 | 33. 2 | 85. 0 | 16. 0 | 12. 3 |
| **N 3** | 1.9% [1.6– 2.3] | 0.7% [0.5– 0.9] | 6.7% [6.2– 7.3] | 87.9% [87.1 – 88.6] | 2.8% [2.5– 3.2] | 0.2 | 0.2 | 5.4 | 82. 3 | 0.0 |
| **R** | 4.3% [4.0– 4.7] | 0.7% [0.6– 0.9] | 4.2% [3.9– 4.6] | 0.9% [0.7– 1.1] | 89.8 % [89.3– 90.3] | 4.2 | 4.7 | 0.8 | 0.8 | 73. 2 |

# - Arousal

**Table 2. Performance Comparison of Arousal**

| SOMNUM | | | Reference [16] | | |
| --- | --- | --- | --- | --- | --- |
| PPA | NPA | OPA | PPA | NPA | OPA |
| 83.8% [82.62– 84.97] | 99.4% [99.35– 99.45] | 98.74 [98.67– 98.82] | 76.82 | 82.48 | - |

Confidential – Honeynaps Co., Ltd.

Page 13 / 19

{17}

**HONEY
NAPS**

Doc. No. 510(k) Summary

# - Respiratory Event

**Table 3. Performance Comparison of Respiratory Event**

| Respiratory Events | SOMNUM | | | Reference [17] | | |
| --- | --- | --- | --- | --- | --- | --- |
| | OPA | PPA | NPA | OPA | PPA | NPA |
| Hypopnea | 98.58% [98.50–98.65] | 81.71% [80.55–82.90] | 99.29% [99.23–99.34] | 95.5% [95.4- 95.6] | 66.3% [64.9-67.6] | 97.1% [97.0-97.2] |
| Obstructive Apnea | 97.42% [97.31–97.51] | 86.26% [85.58–86.99] | 98.66% [98.58–98.73] | 98.8% [98.7-98.8] | 74.1% [72.1-76.1] | 99.3% [99.2-99.3] |
| Central Apnea | 99.83% [99.80–99.86] | 82.19% [78.85–85.29] | 99.93% [99.91–99.95] | 98.9% [98.8- 99.0] | 65.3% [63.1-67.6] | 99.5% [99.5-99.0] |
| Mixed Apnea | 99.94% [99.93–99.96] | 75.67% [67.31–83.72] | 99.97% [99.96–99.98] | - | 76.3% | 96.6% |

# - PLMs

**Table 4. Performance Comparison of PLMS**

| SOMNUM | | | Reference [A10] | | |
| --- | --- | --- | --- | --- | --- |
| OPA | PPA | NPA | OPA | PPA | NPA |
| 97.63% [97.53 – 97.73] | 87.18% [86.44–87.93] | 98.61% [98.53–98.69] | 91.7% [91.5 - 91.8] | 82.0% [81.0 - 83.0] | 92.4% [92.2- 92.6] |

# - Conclusion

For Sleep Stage, Arousal, Respiratory Events and PLMS, SOMNUM exceeded all performance targets. “Compared with the clinical target of PPA, sleep staging showed an average improvement of 9.75% in concordance except for N1, while arousal and PLMS demonstrated performance improvements of 7%, and 5%, respectively. For respiratory event classification, SOMNUM demonstrated performance that was approximately 12–17% superior to the reference across all event categories except mixed sleep apnea (MSA).

For MSA classification, SOMNUM performance was within the confidence interval range

Confidential – Honeynaps Co., Ltd.

Page 14 / 19

{18}

HONEY NAPS

Doc. No. 510(k) Summary

of the reference results, indicating comparable performance to the reference scoring.

- In conclusion, SOMNUM passed all pass/fail criteria for Endpoint 1.
- The number of epochs to calculate PPA/NPA for Endpoint1

2) Data for End Point 2.

Table 5. Performance Comparison of Relevant Scoring Variables Between SOMNUM and Performance Target for Endpoint 2.

| Variable | Type Of Limit | SOMNUM | abs. MAX | Target | abs. MAX | Unit |
| --- | --- | --- | --- | --- | --- | --- |
| TST | U | 18 | 18 | 60 | 120 | [min] |
| | L | -6 | | -120 | | |
| SE | U | 2.5 | 2.5 | 10 | 13 | % |
| | L | -1.5 | | -13 | | |
| SOL | U | 8 | 8 | 40 | 40 | [min] |
| | L | -8 | | -5 | | |
| ROL | U | 6 | 6 | 170 | 170 | [min] |
| | L | -5 | | -130 | | |
| Wake | U | 6 | 18 | 60 | 60 | [min] |
| | L | -18 | | -45 | | |
| N1 | U | 10 | 10 | 80 | 80 | [min] |
| | L | -7 | | -60 | | |
| N2 | U | 10 | 10 | 70 | 120 | [min] |
| | L | -8 | | -120 | | |
| N1_N2 | U | 15 | 15 | 70 | 70 | [min] |
| | L | -8 | | -60 | | |
| N3 | U | 4.5 | 5 | 140 | 140 | [min] |
| | L | -5 | | -10 | | |
| REM | U | 8 | 8 | 50 | 80 | [min] |
| | L | -6 | | -80 | | |
| Arousal Index | U | 1.5 | 3 | | | events/hour |
| | L | -3 | | | | |

Confidential – Honeynaps Co., Ltd.

Page 15 / 19

{19}

HONEY NAPS

Doc. No. 510(k) Summary

| PLMS Index | U | 4 | 15 | 7 | 43 | events/hour |
| --- | --- | --- | --- | --- | --- | --- |
| | L | -15 | | -43 | | |
| AHI Index | U | 4 | 4 | 7 | 20 | events/hour |
| | L | -3 | | -20 | | |

# Conclusion

Bland-Altman and Deming regression analysis were performed to evaluate the relationship between SOMNUM-derived parameters and reference PSG measurements. The Bland-Altman analysis demonstrated generally consistent proportional relationships across the evaluated sleep and respiratory parameters without substantial systematic deviation. The Deming regression results demonstrated that all 13 evaluated variables satisfied the predefined linearity criteria.

# 3) Data for End Point 3.

Table 6. Likelihood ratio for AHI.

| Sleep Apnea Diagnostic Agreement Clinical Performance Comparisons | Per-Patient SOMNUM vs 2/3 Majority Sleep Apnea Diagnostic Agreement | | | | Per-Patient K162627 vs 2/3 Majority Sleep Apnea Diagnostic Agreement | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Sleep | | REM | | Sleep | | REM | |
| | AHI >= 5 | AHI >= 15 | AHI >= 5 | AHI >= 15 | AHI >= 5 | AHI >= 15 | AHI >= 5 | AHI >= 15 |
| Sample Size (N) | 100 | 100 | 100 | 100 | 72 | 72 | 72 | 72 |
| Sensitivity | 100.0% (100.0-100. | 98.28% (94.44-100. | 100.0% (100.0-100. | 95.45% (89.39-100. | 91% (82%-98%) | 95% (83%-100%) | 83% (72%-94%) | 79% (56%-94%) |

Confidential – Honeynaps Co., Ltd.

Page 16 / 19

{20}

**HONEY
NAPS**

Doc. No. 510(k) Summary

| | 0) | 0) | 0) | 0) | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Specificity | 95.2 4% (83. 33- 100. 0) | 97.6 2% (92. 10- 100. 0) | 88.8 9% (71. 43- 100. 0) | 97.0 6% (90. 32- 100. 0) | 76% (61 %- 90% ) | 98% (94 %- 100 %) | 89% (79 %- 97% ) | 96% (90% - 100 %) |
| Accuracy | 99.0 0% (97. 00- 100. 0) | 98.0 0% (95. 00- 100. 0) | 98.0 0% (95. 00- 100. 0) | 96.0 0% (92. 00- 99.0 0) | 85% (77 %- 92% ) | 97% (93 %- 100 %) | 86% (79 %- 93% ) | 92% (85% - 97%) |
| Likelihood ratio (+) | 21.0 0 | 41.2 8 | 9.00 | 32.4 5 | 3.76 | 52.2 5 | 7.71 | 22.00 |
| Likelihood ratio (-) | 0.00 | 0.02 | 0.00 | 0.05 | 0.12 | 0.05 | 0.19 | 0.22 |

**\* point estimates were calculated directly from the subject-level confusion matrix and 95% confidence intervals were estimated using subject-level bootstrap resampling with 1,000 iterations and the empirical percentile method.**

# - Conclusion

SOMNUM demonstrated high sensitivity and specificity across all evaluation conditions. In addition, LR+ values greater than 10 and LR− values below 0.1 were observed under most analysis conditions, suggesting that the device may provide clinically reliable diagnostic information for sleep apnea assessment. Notably, high sensitivity and low LR− values were maintained in REM sleep analyses, indicating relatively stable sleep apnea assessment performance under REM sleep conditions.

Comparative analysis demonstrated that SOMNUM showed diagnostic performance generally comparable to or better than the predicate device (K162627) across multiple evaluation conditions. In particular, lower LR− values and consistently high sensitivity were observed under several analysis conditions, supporting reliable detection performance with a reduced likelihood of false-negative classification.

Overall, these findings support that SOMNUM provides clinically reliable sleep apnea assessment performance across both Sleep and REM evaluation conditions.

Confidential – Honeynaps Co., Ltd.

Page 17 / 19

{21}

HONEY
NAPS

Doc. No. 510(k) Summary

### 7.4 Clinical Study Summary of Korean 48 case study

#### Korean 48 case study

##### Study Design

A retrospective cross-sectional clinical performance study was conducted to evaluate the performance of SOMNUM using 48 full-night polysomnography (PSG) recordings collected from three sleep laboratories. The validation dataset consisted of 48 PSG recordings selected from a total of 400 PSG studies. Device performance was evaluated by comparing SOMNUM automatic scoring results with an independently generated reference standard established using a 2/3 majority consensus of three qualified PSG technologists. Clinical performance was assessed using predefined statistical methods across three endpoints, including epoch-level agreement, subject-level agreement for sleep variables, and patient-level diagnostic performance for sleep apnea.

##### Patient Characteristics

The study population consisted of 48 adult subjects, including 32 males and 16 females. The mean age was 44.2 ± 12.1 years (range: 21–67 years) for male subjects and 46.8 ± 16.6 years (range: 22–71 years) for female subjects. The mean body mass index (BMI) was 27.5 ± 3.3 kg/m² (range: 18.8–35.6 kg/m²) for male subjects and 25.5 ± 4.1 kg/m² (range: 18.8–35.6 kg/m²) for female subjects. The validation dataset consisted of 48 PSG recordings

##### Sample Size

A total of 48 full-night polysomnography (PSG) recordings were included in the clinical performance study. The validation dataset was selected from a total of 400 PSG recordings collected from three sleep laboratories and consisted of 24 Korean and 24 U.S. PSG recordings.

##### Institutional Source

PSG recordings were collected from three sleep laboratories in the Republic of Korea: Soonchunhyang University Hospital (Bucheon), Ajou University Hospital (Suwon), and Chungnam National University Hospital (Daejeon).

##### Performance Result

SOMNUM met all predefined acceptance criteria across the three clinical performance endpoints. For epoch-level analysis (Endpoint 1), the device demonstrated high agreement with the reference standard for sleep stage classification, arousal detection, respiratory event detection, and periodic limb movement (PLMS) detection, exceeding the predefined

Confidential – Honeynaps Co., Ltd.

Page 18 / 19

{22}

HONEY NAPS

Doc. No. 510(k) Summary

performance targets. For subject-level analysis (Endpoint 2), all evaluated sleep variables demonstrated clinically acceptable agreement with the reference standard based on Bland–Altman analysis and Deming regression. For patient-level analysis (Endpoint 3), SOMNUM demonstrated excellent diagnostic performance for sleep apnea based on the apnea-hypopnea index (AHI), with likelihood ratios meeting or exceeding the predefined acceptance criteria. Overall, SOMNUM met or exceeded the performance of the predicate device across all evaluated endpoints.

## 8. Conclusion

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. Bench testing and clinical performance testing demonstrated substantially equivalent performance to the predicate.

Confidential – Honeynaps Co., Ltd.

Page 19 / 19