The QP-160AK EEG Trend Program is a software-only device intended to calculate and display EEG data obtained from the Nihon Kohden specified host device. The QP-160AK is intended to be used by qualified medical practitioners, trained in electroencephalography, who will exercise professional judgment when using the information. The intended use is as follows:

· The EEG and aEEG waveforms are intended to help the user monitor the state of the brain.

· The user-defined Fast Fourier Transform (FFT) parameters of this software (FFT power) are intended to help the user analyze the EEG waveform.

• The burst suppression parameters of this software (interval and bursts per minute) are intended to aid in the identification and characterization of areas of burst-suppression pattern in the EEG.

• The seizure detection component of QP-160AK is intended to mark previously acquired EEG waveforms of adult (greater than or equal to 18 years) that may correspond to electrographic seizures in order to aid in identification of seizure events and help review and annotation of EEG traces by user. EEG should be recorded with full scalp montage at the standard 10/20 system. The notifications for seizure detection are provided. QP-160AK notifications cannot be used as a substitute for real time monitoring of the underlying EEG by a trained expert.

This device does not provide any diagnostic conclusion about the patient's condition to the user.

The device is intended for use by medical personnel in any location within a medical facility, laboratory, clinic or nursing home or outside of a medical facility under direct supervision of a medical professional.

Device Description

The QP-160AK EEG Trend Program is a software-only device. When installed in Nihon Kohden neurology products with EEG measurement function, the device calculates and displays EEG data obtained from the neurology product's system. In addition, the QP-160AK EEG Trend Program identifies trends in the EEG data over extended periods of time in order for trained healthcare professionals to observe changes over time.

The program's existing main features are listed below:

Calculate and display aEEG, DSA, FFT and burst suppression ratio trend .
Display up to 64 channel EEG ●
. Display SpO2 and ETCO2 trends
Operation by touch panel buttons
. Data management with Neuro Workbench software

The modification is to add:

Seizure detection and notification .

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Device: Nihon Kohden QP-160AK EEG Trend Program
Specific New Feature Tested: Seizure detection component.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the seizure detection component are implicitly defined by the reported performance statistics in comparison to the predicate device or generally accepted clinical utility. While explicit pass/fail thresholds are not given for Nihon Kohden QP-160AK, the comparison to "a similar level of performance" to the predicate, Persyst 12, is key.

Performance Statistics	Acceptance Criteria (Implicit, based on predicate performance context)	Reported Device Performance (Nihon Kohden QP-160AK Seizure Detection)
Positive Percent Agreement (PPA)	Expected to be clinically useful and comparable to predicate.	Mean: 77.2% (95% CI: 69.0 - 83.5%)
False Detection Rate (FDR) (False Positives/hr)	Expected to be clinically useful and comparable to predicate.	Mean: 0.451 (95% CI: 0.320 - 0.669)

The provided graphs (Figures 0 and 3 on page 9) visually compare the QP-160AK's PPA and FDR to several other devices, including its predicate (Persyst12). This comparison serves as evidence for the "substantially equivalent" claim, suggesting that the QP-160AK's performance falls within an acceptable range relative to legally marketed predicate devices.

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

Sample Size: 139 patients.
Data Provenance: Archived EEG recordings from patients (18 years and older) admitted to an Epilepsy Monitoring Unit. The country of origin is not explicitly stated in the provided text. The data is retrospective, being "archived EEG recordings."
Total EEG Recording Time: 556 hours (139 recordings * approximately 4 hours per recording).
Total Seizures Identified: 145

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

Number of Experts: Three independent EEG experts.
Qualifications: "EEG experts" – no further specific qualifications (e.g., years of experience, board certification) are provided in the text.

4. Adjudication Method for the Test Set

Adjudication Method: Two-third majority rule. This means that for an event to be considered ground truth (a "true seizure"), at least two of the three independent EEG experts had to agree on its presence.

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

Was an MRMC study done? No, a traditional MRMC comparative effectiveness study where human readers' performance with AI assistance is compared to without AI assistance was not explicitly described.
Effect size of human readers improvement with AI vs. without AI assistance: Not applicable, as this type of study was not reported. The study focused on the standalone performance of the algorithm against expert-established ground truth.

6. Standalone Performance Study

Was a standalone performance study done? Yes. The seizure detection component of the QP-160AK was evaluated by comparing its output directly against the "clinical reference standard (ground truth)" established by the expert consensus. The reported PPA and FDR metrics quantify this standalone performance.

7. Type of Ground Truth Used

Type of Ground Truth: Expert consensus. Specifically, "a two-third majority rule" among three independent EEG experts.

8. Sample Size for the Training Set

The text does not explicitly state the sample size used for the training set. It only describes the test set.

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

The text does not describe how the ground truth for the training set was established. It focuses solely on the ground truth establishment for the test set used for performance evaluation.

Summary

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

Image /page/0/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo features a stylized graphic of three human profiles facing right, layered on top of each other. The profiles are black and have a flowing, abstract design. The text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" is arranged in a circular pattern around the graphic.

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

May 19, 2017

Nihon Kohden Corporation % Tom Bento Sr. Vice President, Quality and Regulatory Nihon Kohden America, Inc. 15353 Barranca Parkway Irvine, California 92618

Re: K163644

Trade/Device Name: Nihon Kohden QP-160AK EEG Trend Program Regulation Number: 21 CFR 882.1400 Regulation Name: Electroencephalograph Regulatory Class: Class II Product Code: OMB, OMA, OLT, ORT Dated: April 21, 2017 Received: April 21, 2017

Dear Mr. Bento:

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.

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 of medical devicerelated adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in

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

the quality systems (OS) 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 contact the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm. 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

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 Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.

Sincerely.

Michael J. Hoffmann -S

for Carlos L. Peña, PhD, MS Director Division of Neurological and Physical Medicine Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known) K163644

Device Name

Nihon Kohden QP-160AK EEG Trend Program

Indications for Use (Describe)

· The EEG and aEEG waveforms are intended to help the user monitor the state of the brain.

· The user-defined Fast Fourier Transform (FFT) parameters of this software (FFT power) are intended to help the user analyze the EEG waveform.

• The burst suppression parameters of this software (interval and bursts per minute) are intended to aid in the identification and characterization of areas of burst-suppression pattern in the EEG.

This device does not provide any diagnostic conclusion about the patient's condition to the user.

Type of Use (Select one or both, as applicable)
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}------------------------------------------------

510(k) Summary for Nihon Kohden EEG Trend Program QP-160AK

Submitter:	Nihon Kohden Corporation
Address:	1-31-4 Nishiochiai, 1-Chome, Shinjuku-KuTokyo, Japan 161-8560
Phone number:	81-2-59968020
Contact person:	Tom Bento
Phone number:	(949) 680-9048
Fax number:	(913) 273-0732
Date prepared:	December 21, 2016
Device name:	Nihon Kohden QP-160AK EEG Trend Program
Common name:	Electroencephalograph (EEG)
Primary product codes:	OMB, OLT, ORT, OMA
Regulation numbers:	21 CFR 882.1400
Substantial equivalence claimed to:	Nihon Kohden QP-160AK EEG Trend Program (K120485Persyst 12 EEG Review and Analysis Software (K133793)

Description:

The program's existing main features are listed below:

Calculate and display aEEG, DSA, FFT and burst suppression ratio trend .
Display up to 64 channel EEG ●
. Display SpO2 and ETCO2 trends
Operation by touch panel buttons
. Data management with Neuro Workbench software

The modification is to add:

Seizure detection and notification .

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

Indications for Use:

The QP-160AK EEG Trend program is a software-only device intended to calculate, and display EEG data obtained from the Nihon Kohden specified host device. The QP-160AK is intended to be used by qualified medical practitioners, trained in Electroencephalography, who will exercise professional judgment when using the information.

The intended use is as follows:

. The EEG and aEEG waveforms are intended to help the user monitor the state of the brain.
. The user-defined Fast Fourier Transform (FFT) parameters of this software (FFT power) are intended to help the user analyze the EEG waveform.
. The burst suppression parameters of this software (interburst interval and bursts per minute) are intended to aid in the identification and characterization of areas of burstsuppression pattern in the EEG.
. The seizure detection component of QP-160AK is intended to mark previously acquired EEG waveforms of adult (greater than or equal to 18 years) that may correspond to electrographic seizures in order to aid in identification of seizure events and help review and annotation of EEG traces by user. EEG should be recorded with full scalp montage at the standard 10/20 system. The notifications for seizure detection are provided. QP-160AK notifications cannot be used as a substitute for real time monitoring of the underlying EEG by a trained expert.

This device does not provide any diagnostic conclusion about the patient's condition to the user.

The device is intended for use by medical personnel within a medical facility, laboratory, clinic or nursing home or outside of a medical facility under direct supervision of a medical professional.

Technological Characteristics - Substantial Equivalence Discussion

The Nihon Kohden QP-160AK EEG Trend Program is substantially equivalent to the predicate device of the same name (K120485) with the additional features of seizure detection and notification. For the seizure detection and notification, QP-160AK is substantially equivalent to the other listed predicate devices, Persyst 12 EEG Review and Analysis Software (K133793). Differences between the devices are minor and do not raise questions regarding safety or efficacy.

These differences include:

1. The QP-160AK EEG Trend Program is the same as the previous submission of QP-160AK cleared under K120485, but has two additional functions: seizure detection and notification of seizure detection.
1. For these new functions, we refer to Persyst 12 EEG Review and Analysis Software

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

(K133793) as the predicate.

1. Other functions of QP-160AK remain the same as the previously cleared submission, K120485; thus QP-160AK of K120485 is referenced as the predicate for the functions other than seizure detection and notification of seizure detection.

Specifications	Nihon Kohden QP-160AK	Persyst 12 EEG (Predicate device K133793)
Indications for Use	The QP-160AK EEG Trend program is a software-only device intended to calculate, and display EEG data obtained from the Nihon Kohden specified host device. The QP-160AK is intended to be used by qualified medical practitioners, trained in Electroencephalography, who will exercise professional judgment when using the information.The intended use is as follows: The EEG and aEEG waveforms are intended to help the user monitor the state of the brain. The user-defined Fast Fourier Transform (FFT) parameters of this software (FFT power) are intended to help the user analyze the EEG waveform. The burst suppression parameters of this software (interburst interval and bursts per minute) are intended to aid in the identification and characterization of areas of burst-suppression pattern in the EEG. The seizure detection component of QP-160AK is intended to mark EEG waveforms of adult (greater than or equal to 18 years)	1. Persyst 12 EEG Review and Analysis Software is intended for the review, monitoring and analysis of EEG recordings made by electroencephalogram (EEG) devices using scalp electrodes and to aid neurologists in the assessment of EEG. This device is intended to be used by qualified medical practitioners who will exercise professional judgment in using the information.2. The Seizure Detection and Seizure Probability component of Persyst 12 is intended to mark previously acquired sections of adult (greater than or equal to 18 years) EEG recordings that may correspond to electrographic seizures, in order to assist qualified clinical practitioners in the assessment of EEG traces. EEG recordings should be obtained with a full scalp montage according to the standard 10/20 system.3. The Spike Detection component of Persyst 12 is intended to mark previously acquired sections of the patient's EEG recordings that may correspond to spikes, in order to assist qualified clinical practitioners in the assessment of EEG traces. The Spike Detection component is intended to be used in patients at least one month old. Persyst 12 Spike
Specifications	Nihon Kohden QP-160AK	Persyst 12 EEG(Predicate deviceK133793)
	electrographic seizures inorder to aid in identification ofseizure events and helpreview and annotation of EEGtraces by user. EEG shouldbe recorded with full scalpmontage at the standard10/20 system. Thenotifications for seizuredetection are provided.	Detection performance has not beenassessed for intracranial recordings.
	This device does not provide anydiagnostic conclusion about thepatient's condition to the user.	4. Persyst 12 includes the calculationand display of a set of quantitativemeasures intended to monitor andanalyze the EEG waveform. Theseinclude FFT, Automatic event markingis not applicable to the quantitativemeasures. These quantitative EEGmeasures should always beinterpreted in conjunction with reviewof the original EEG waveforms.
	The device is intended for use bymedical personnel within a medicalfacility, laboratory, clinic or nursinghome or outside of a medical facilityunder direct supervision of a medicalprofessional.	5. The aEEG functionality included inthe Persyst 12 is intended to monitorthe state of the brain. The automatedevent marking function of Persyst 12is not applicable to aEEG.
		6. Persyst 12 provides notifications forseizure detection, quantitative EEGand aEEG that can be used whenprocessing a record duringacquisition. These include an onscreen display and the optionalsending of an email message. Delaysof up t several minutes can occurbetween the beginning of a seizureand when the Persyst 12 notificationswill be shown to a user. Persyst 12notifications cannot be used as asubstitute for real time monitoring ofthe underlying EEG by a trainedexpert.
		7. Persyst AR (Artifact Reduction) isintended to reduce EMG, eyemovement, and electrode artifacts ina standard 10-20 EEG recording. ARdoes not remove the entire artifactsignal, and is not effective for othertypes of artifacts. AR may modifyportions of waveforms representingcerebral activity. Waveforms must stillbe read by a qualified medical
Specifications	Nihon Kohden QP-160AK	Persyst 12 EEG(Predicate deviceK133793)practitioner trained in recognizingartifact, and any interpretation ordiagnosis must be made withreference to the original waveforms.8. This device does not provide anydiagnostic conclusion about thepatient's condition to the user.
Identify Seizures	Yes	Yes
Provides SeizureNotifications	Yes	Yes
Identify Spikes	No	Yes
Montage/ChannelArray	Scalp 10/20 Array	Scalp 10/20 Array
Number of EEGChannels	Up to 32/64 EEG channels(dependent on amplifier)	Up to 32/64 EEG channels(dependent on amplifier)
Number of DCChannels	Up to 8 channels (dependent onamplifier)	Up to 8 channels (dependent onamplifier)
Density SpectralArray (DSA) Trend	Yes	Yes
Density SpectralArray (DSA)Asymmetry Trend	Yes	Yes
Spectral EdgeFrequency TrendAmplitude	Yes	Yes
Integrated EEG(aEEG) Trend	Yes	Yes
Burst SuppressionRatio (BSR) Trend	Yes	Yes
Inter-Burst Interval(IBI) Trend	Yes	No
Burst Per Minute(BPM) Trend	Yes	No
FFT Power Trend	Yes	Yes
FFT PowerAsymmetry Trend	Yes	Yes
FFT Power ratio(e.g. Alpha/Delta,Alpha/Beta) Trend	Yes	Yes
External Input (DCInput) Display	Yes	Yes
Number of Trends	More than 16	More than 16
User SelectableTrend Group(Panel)	Yes	Yes
Time Interval ofTrends	1 minute/page to 24 hours/page,1cm/hour to 300cm/hour	1 minute/page to 24 hours/page,1cm/hour to 60cm/hour
User SelectableTrends Time Scale	Yes	No
Specifications	Nihon Kohden QP-160AK	Persyst 12 EEG(Predicate deviceK133793)
Annotation List	Yes	Yes
Raw EEG datadisplay look-backwhile recordingsynchronized video	Yes	Yes

Device Comparison

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

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

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

Test Summary:

Performance testing for the QP-160AK includes software verification tests, system validation tests, and seizure detection performance tests. Traceability has been documented between all system specifications to validation test protocols.

Verification and validation testing includes:

1. Code inspections
1. Unit level testing
1. Integration level testing
1. System level testing
1. Seizure detection performance testing: The testing was performed using archived EEG recordings obtained from 139 patients of 18 years and older admitted to an Epilepsy Monitoring Unit. All EEG data were recorded with full scalp montage using the standard 10/20 system. Each recording lasts approximately 4 hours for a total of 556 hours of EEG recording. All 139 recordings were manually annotated by three independent EEG experts and the clinical reference standard (ground truth) was determined by using a two-third majority rule. Total 145 seizures were identified. The same EEG recordings were used for seizure detection by the QP-160AK EEG Trend Program and the results were compared against the ground truth by calculating Positive Percent Agreement (PPA) and False Detection Rate (FDR) as below:

$$\text{PPA} = \frac{True \text{ Positives}}{True \text{ Positives} + False \text{ Negatives}}$$

$$\text{FDR} = \frac{\text{False Positives}}{hour \text{ of } EEG \text{ Recording}}$$

The following mean and 95% Confidence Intervals using bootstrap method were obtained:

Performance Statistics	Mean	95% CI
Positive Percent Agreement (%)	77.2	69.0 - 83.5
False Detection Rate (FDR)	0.451	0.320 - 0.669

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

Image /page/9/Figure/0 description: The image is a graph titled "PPA and 95% Confidence Interval for Seizure Detection". The x-axis is labeled "PPA (%)" and ranges from 40 to 100. The y-axis lists different devices: QP-160AK, Persyst12, Cliniscan, Cadwell, IdentEvent, and Persyst Reveal. Each device has a horizontal line representing its 95% confidence interval for seizure detection, with markers indicating the lower and upper bounds.

Comparison of Positive Percent Agreement and 95% Confidence Interval

Comparison of False Detection Rate and 95% Confidence Interval

Image /page/9/Figure/3 description: The image is a plot titled "FDR and 95% Confidence Interval for Seizure Detection". The x-axis is labeled "FDR (Fp/h)" and ranges from 0 to 1. There are six different devices plotted on the graph: Cadwell, IdentEvent, Persyst Reveal, Persyst12, Cliniscan, and QP-160AK. Each device has a different symbol and color associated with it.

Conclusion:

The performance of the Nihon Kohden QP-160AK EEG Trend Program is substantially equivalent to the predicate devices, the Nihon Kohden QP-160AK EEG Trend Program (K120485) and Persyst 12 EEG Review and Analysis Software (K133793), and raises no safety or effectiveness issues.

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).