CliniscanSM EEG is a clinical decision support system for medical data, to assist healthcare professionals in the visualization and analysis of EEG data.
The Seizure Detection component of CliniscanSM EEG 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.
CliniscanSM EEG is intended for use on EEG recordings acquired using full scalp montage according to the standard 10/20 system.
The user may annotate the data, and the annotations are stored with the EEG recording in the cloud.
CliniscanSM EEG displays standard qEGG features to the user including FFT Power Spectrum. Coherence Mapping (EEG Activity Mapping), Density Spectral Array, EEG Localization Maps, and Wavelet Subband Decomposition (Delta, Theta, Alpha, Beta, and Gamma).
CliniscanSM EEG detects seizure events for review by qualified medical professionals.
CliniscanSM EEG is designed to provide analytics data derived from a patient's input EEG data. It is NOT designed to provide definitive diagnoses of diseases or treatments of ailments.

Device Description

Cliniscan®M EEG, a Picofemto product, is a clinical decision support system for medical data, designed to assist healthcare professionals in the visualization and analysis of EEG data. The device provides seizure event detection and calculates many qEEG (quantitative EEG) parameters for display to the user. All analysis (seizure detection and qEEG) are displayed in conjunction with the original EEG recording for review by experts and are designed to be reviewed in the context of the original data.

The Cliniscan®% EEG visualizer provides a user-friendly environment for displaying the available qEEG parameters along with the original EEG recording (see below). The EEG recording display window, time bar, and User Annotations frames remained fixed within the visualizer; however, the bottom portion of the screen contains tabs for the user to navigate the qEEG features. The user may access the FFT Power Spectrum, Coherence Maps, and EEG Topography Maps under the "Combo" tab; Wavelet Subband Decomposition and the FFT Power Spectrum (again) are located under the "Power" tab; the "DSA" tab contains only the Density Spectral Array display.

After uploaded an EEG in EDF format, the user may view the following qEEG Parameters:

FFT Power Spectrum
Coherence Maps
EEG Topographical Maps
Wavelet Subband Decomposition
Density Spectral Array (DSA)
User Annotations
Seizure Event Detection
Info

Cliniscan®ª EEG is designed to provide industry standard analytics data derived from a patient's input EEG data. It is NOT designed to provide definitive diagnoses of diseases or treatments of ailments.

Cliniscan§™ EEG detects and marks possible seizure events on previously acquired EEG recordings for review by qualified medical professionals.

AI/ML Overview

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

Acceptance Criteria and Device Performance

The core acceptance criteria for the CliniScanSM EEG, specifically for its Seizure Detection component, revolve around its ability to accurately identify seizures (Positive Percent Agreement - PPA) and limit false alarms (False Positives per Hour - Fp/H) when compared to a ground truth established by experts. While specific numerical acceptance thresholds are not explicitly stated in the provided text as pass/fail criteria, the study results are presented with a 95% confidence interval, indicating an evaluation against expected performance. The comparison to predicate devices also implies that performance within a similar range is considered acceptable.

Metric	Acceptance Criteria (Implied)	Reported Device Performance (95% C.I.)
Positive Percent Agreement (PPA)	Sufficiently high to assist qualified clinical practitioners. Validated against expert inter-rater variability.	[0.687, 0.857] (Original Mean: 0.7835)
False Positives per Hour (Fp/H)	Sufficiently low to avoid overwhelming clinicians with false alarms. Validated against expert inter-rater variability.	[0.325, 0.540] (Original Mean: 0.4164)
Essentially, the device performance is considered "sufficient" if its PPA and Fp/H are comparable to expected inter-rater variability among experts and to predicate devices.

Study Details

Sample size used for the test set and the data provenance:
- Sample Size: 144 subjects, totaling approximately 293 hours of EEG recordings.
- Data Provenance: Archived clinical data from multiple sites, specifically from an Epilepsy Monitoring Unit (EMU). The recordings are from subjects 18 years of age and greater. Roughly 20% of the recordings are "normal" (from subjects with no history of seizures), and each recording contains no more than 4 seizures to reduce bias. After ground truth determination, 134 seizures were identified.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Three independent and blinded EEG experts.
- Qualifications: "EEG experts" – no further specific details (e.g., years of experience, board certification) are provided in the text.
Adjudication method for the test set:
- Adjudication Method: A "two-thirds majority rule" was used to determine the ground truth for seizure presence. Each expert manually marked any seizure events, and if at least two out of the three experts marked a seizure in a particular segment, it was considered ground truth.
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No, a multi-reader multi-case (MRMC) comparative effectiveness study with human readers assisted by AI was not explicitly described. The study primarily focused on the standalone performance of the algorithm against an expert-established ground truth. The inter-rater performance among the experts themselves was assessed, but not a human-in-the-loop scenario with the AI.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance evaluation of the CliniScanSM EEG seizure detection algorithm was conducted. The algorithm's results were directly compared to the compiled ground truth, and PPA and Fp/H were calculated. The provided results table ([0.687,0.857] for PPA and [0.325,0.540] for Fp/H) represents this standalone performance.
The type of ground truth used:
- Type of Ground Truth: Expert consensus, specifically a "two-thirds majority rule" among three independent and blinded EEG experts.
The sample size for the training set:
- The document states that "archived clinical data from multiple sites was used to train and validate the internal parameters involved in seizure detection." However, the specific sample size for the training set is not provided.
How the ground truth for the training set was established:
- The document implies that archived clinical data was used for training, but it does not explicitly detail how the ground truth for this training set was established. It only mentions that the test set ground truth was established by three independent and blinded EEG experts using a two-thirds majority rule.

Summary

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

Image /page/0/Picture/1 description: The image is a black and white logo for the U.S. Department of Health & Human Services. The logo features a stylized caduceus symbol, which is often associated with medicine and healthcare. The text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" is arranged around the symbol in a circular fashion. The overall design is simple and professional, reflecting the organization's role in public health and human services.

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

May 15, 2015

Picofemto LLC Srikant Krishna Founder and CEO 228 East 45th St., 2nd Floor New York, NY 10001

Re: K141883

Trade/Device Name: CliniScan5M EEG Regulation Number: 21 CFR 882.1400 Regulation Name: Electroencephalograph Regulatory Class: Class II Product Code: OMB, OLT Dated: April 13, 2015 Received: April 14, 2015

Dear Mr. Krishna:

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. Isting 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 (reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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

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/Resourcesfor You/Industry/default.htm. Also, please note the regulation entitled. "Misbranding by reference to premarket notification" (21CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to

http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of 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 yours,

Felipe Aquel -S

Carlos L. Peña, PhD, MS for 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) K141883

Device Name CliniScanSM EEG

Indications for Use (Describe)

CliniscanSM EEG is a clinical decision support system for medical data, to assist healthcare professionals in the visualization and analysis of EEG data.
The Seizure Detection component of CliniscanSM EEG 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.
CliniscanSM EEG is intended for use on EEG recordings acquired using full scalp montage according to the standard 10/20 system.
The user may annotate the data, and the annotations are stored with the EEG recording in the cloud.
CliniscanSM EEG displays standard qEGG features to the user including FFT Power Spectrum. Coherence Mapping (EEG Activity Mapping), Density Spectral Array, EEG Localization Maps, and Wavelet Subband Decomposition (Delta, Theta, Alpha, Beta, and Gamma).
CliniscanSM EEG detects seizure events for review by qualified medical professionals.
CliniscanSM EEG is designed to provide analytics data derived from a patient's input EEG data. It is NOT designed to provide definitive diagnoses of diseases or treatments of ailments.

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}------------------------------------------------

Image /page/3/Picture/0 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and orange circles on the left, followed by the text "PICOFEMTO" in a large, bold, blue font. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller, lighter blue font. The overall design is clean and modern, suggesting a focus on precision and innovation in the biomedical field.

228 E. 45th St., 2nd Floor, NY 10017 ● (P) 212-502-3770 ● (F) 212-502-0818 ● contact@picofemto.com

510(k) Summary

A summary of safety and effectiveness information in accordance with 21 CFR 807.92

Submitter: Picofemto LLC
Address: 228 East 45th St., 2nd Floor

New York, New York 10017

Contact Person: Srikant Krishna
Phone Number: (212) 502-3770
Fax Number: (212) 502-0818
Date Prepared: 04/13/2015
Trade Name: CliniscanSM EEG
Common Name: Electroencephalogram (EEG) signal spectrum and source analyzer
Classification (OMB) Automatic event detection software for full-montage electroencephalograph and (OLT) qEEG Name:
Regulation 21 CFR 882.1400

Number:

Predicate The Cliniscan560 EEG is substantially equivalent to the Persyst ® Reveal [FDA 510(k) Devices: number K011397] and Neurosoft Curry 7 [FDA 510(k) number K001781].
Image /page/3/Picture/16 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and light blue circles with one orange circle, arranged in a circular pattern on the left. To the right of the circles, the text "PICOFEMTO" is written in a combination of black and blue, with "BIOMEDICAL ANALYTICS" in smaller, light blue letters underneath.

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

Device Cliniscan®M EEG, a Picofemto product, is a clinical decision support system for medical Description data, designed to assist healthcare professionals in the visualization and analysis of EEG data. The device provides seizure event detection and calculates many qEEG (quantitative EEG) parameters for display to the user. All analysis (seizure detection and qEEG) are displayed in conjunction with the original EEG recording for review by experts and are designed to be reviewed in the context of the original data.

The Cliniscan®% EEG visualizer provides a user-friendly environment for displaying the available qEEG parameters along with the original EEG recording (see below). The EEG recording display window, time bar, and User Annotations frames remained fixed within the visualizer; however, the bottom portion of the screen contains tabs for the user to navigate the qEEG features. The user may access the FFT Power Spectrum, Coherence Maps, and EEG Topography Maps under the "Combo" tab; Wavelet Subband Decomposition and the FFT Power Spectrum (again) are located under the "Power" tab; the "DSA" tab contains only the Density Spectral Array display.

Image /page/4/Figure/2 description: The image shows an EEG analysis interface. The interface displays EEG waveforms over time, with timestamps indicating the duration of the recording. Below the waveforms, there are several plots including FFT power spectrum, coherence maps, EEG localization, and scaled average plots. The FFT power spectrum shows the power of different frequency bands, while the coherence maps display the connectivity between different brain regions.

After uploaded an EEG in EDF format, the user may view the following qEEG Parameters:

1. FFT Power Spectrum The user can select any two channels to view an FFT Power Spectrum of Power vs. Frequency between the two channels.
  Image /page/4/Picture/5 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and orange circles on the left, followed by the text "PICOFEMTO" in black and blue. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller, lighter blue font. The logo is clean and modern, with a focus on the company's name and area of expertise.

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

Image /page/5/Figure/0 description: The image shows a graph of an FFT Power Spectrum from +00:00:00.000 to +00:00:10.000. The y-axis is labeled "Power (10*log_10(µV^2/Hz)" and ranges from -10 to 15. The x-axis is labeled "Frequency (hz)" and ranges from 0 to 35. There are two lines on the graph, one green and one purple, representing the channel selections F7-T3 and T3-T5, respectively.

1. Coherence Maps Coherence maps are displayed to the user, allowing the user to define cut-off values ranging from 0-1 and the frequency of interest (composite, delta, theta, alpha, beta, or gamma). As the user-defined parameters are adjusted, the six maps display the corresponding coherence. The user may also select to view Lateral, Sagittal, or both types of coherence.
  Image /page/5/Figure/2 description: The image shows a series of coherence maps, displaying brain activity over time. The time frame is from +00:00:00.000 to +00:00:10.000. The maps are arranged in a grid, with labels such as c_s1_e4, c_s4_e8, c_s8_e15, c_s15_e30, and c_s30_e60. The frequency is set to composite, and both lateral and sagittal views are selected.

Image /page/5/Picture/3 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and light blue circles with one orange circle, followed by the text "PICOFEMTO" in a dark blue sans-serif font. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller, lighter blue sans-serif font.

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

1. EEG Topographical Maps EEG Topographical Maps maps and a corresponding Power vs. Frequency graph are displayed to the user. The maps are calculated using independent component analysis, and the top four components along with the scaled average are displayed to the user. The relative powers of the independent components are displayed in which the higher power corresponds to the top (red) part of the spectrum. The absolute power of these components is not necessary, and, therefore, is not displayed to the user.
  Image /page/6/Figure/1 description: The image shows an EEG localization analysis. On the left, there is a graph of power spectral density versus frequency, with multiple lines representing different EEG channels. The x-axis is labeled "Frequency (Hz)" ranging from 0 to 35, and the y-axis is labeled "Power (10*log_10(µV^2/Hz)". On the right, there are topographical maps showing the spatial distribution of EEG activity for different components, labeled as "Scaled Average", "Component 0", "Component 1", "Component 2", "Component 3", and "Component 4".
Wavelet Subband Decomposition –The user may select a channel of interest to 4) view the different frequencies of said channel broken down into the five main frequency bands of interest: Delta, Theta, Alpha, Beta, and Gamma. The original channel is displayed at the top of the graph, with the corresponding frequency ranges displayed in the same time frame beneath the channel.
Image /page/6/Figure/3 description: The image shows a graph of wavelet subbands over time. The graph displays the frequency bands F7-T3, Delta, Theta, Alpha, and Beta. The x-axis represents time, ranging from +00:00:00.000 to +00:00:10.0. The y-axis represents the amplitude of the wavelet subbands.
1. Density Spectral Array (DSA) – The DSA display updates for each user-selected time-window. Additionally, the user may select which channels to include in
  Image /page/6/Picture/5 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and light blue circles with one orange circle, followed by the text "PICOFEMTO" in a dark gray sans-serif font. Below the text is the phrase "BIOMEDICAL ANALYTICS" in a smaller, lighter blue sans-serif font.

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

the DSA calculation.

Image /page/7/Figure/1 description: The image shows a density spectral array with a color gradient from blue to red. The y-axis represents frequency in Hz, ranging from 5 to 55. The x-axis represents time, with labels such as '+00:13:20.000' and '+00:40:00.000'. The color intensity indicates the density or intensity of the spectral data at each frequency and time point.

User Annotations The user may add annotations including the time of the ର) event, the subject name, and any important details. These annotations are saved with the recording in the cloud.

User Annotations

New Annotation

Time	+00: 00:05 .000
Subject
Details

Create
Notes

1. Seizure Event Detection The visualizer automatically displays the results of the seizure event detection algorithm for the user to review. The event is indicated by a small red block marked on the overall time bar, followed by a larger red block marked on the user-selected time-bar. Within the channel display, the onset and offset of the detected seizure are indicated using red dashed lines, and the inclusive time window is highlighted a tan color to differentiate from the non-seizure windows.
  Image /page/7/Picture/5 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue circles of varying sizes on the left, with one orange circle among them. To the right of the circles is the text "PICOFEMTO" in a sans-serif font, with "BIOMEDICAL ANALYTICS" in a smaller font below it. The text is also in blue, matching the color of the circles.

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

000 00:00 000	=00 18:40 000		·00 33:20 000		*00: 50:00 000	>01:06:40:000		+01: 23:20 /000		=01:40:00 /000	=01: 56 40 ,000
-02 28:00 200	=32: 26:05 000	·00: 20: 12 /000	·00: 20:15 ,000	+00: 20:20 :000	+00: 28:24 /000	+00 20 20 000	-00 20:36 000	=00: 20:40 /000	-00: 28:45 ,000	=00:28:00 000	·00 20:30 000

+00: 28.05 .000				«00: 25:10 000				400 25:15 DOC



										a promosing por home super life play and lease specifical program of all payments as pay
	And Children ChildrenA									かつきているというというというときてくるとことできたくさしたときてきてくるときていましたとことできていましたとことできていました
										and and and of any minute in the sun a solly got and into and in the same
										からないというときてきましたときてくるときてしましたとことできてくるとことをしてきていましたときていましたときていましたときていました
			Ball man alle for the mailer							かつきたときているとしていましたときてきたけるときちゃんできましたときていますときていますときてくてきていましたときているand and and and on the mark hand hand has and won the world of the many of the market of the market of the count


										していましたときてくるとことできるときてきてくるとことできるというとしていました
										and and the works and with and with and with and with and with and will and will and world and a



									Mark Francisco Minimal Particle Particle Mar
A La Partier Street State State State The										ここでもなくなってきていましたときていますが、そうですが、ここでもないというというというということできていましたときていましたこことなってきてきてきてきてきましたときてきてきてきてきてきてきてきていましたときてくるときてくるときてく
										いていますときてくるとことできるとしてきましたときてくるときてくるときてくるとしてきてくってくって




-00 2806.000				-00 28:10 :000				+00, 28:15 ,000
										Sortes By Recommended Gan 5	Range Frèe Form

1. Info Under the "Info" tab, additional details are available to the user as selectable text (may be copied and pasted). This information includes Analysis Details, Incidents (seizure events with onset and offset time), and Channels.
  Cliniscan®ª EEG is designed to provide industry standard analytics data derived from a patient's input EEG data. It is NOT designed to provide definitive diagnoses of diseases or treatments of ailments.

Cliniscan§™ EEG detects and marks possible seizure events on previously acquired EEG Technology Description recordings for review by qualified medical professionals.

Image /page/8/Picture/4 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and orange circles on the left, followed by the text "PICOFEMTO" in a bold, sans-serif font. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller, lighter font. The overall design is clean and modern, suggesting a focus on precision and innovation in the biomedical field.

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

Intended Use/Indications for Use:

1. Cliniscan®ª EEG is a clinical decision support system for medical data, to assist healthcare professionals in the visualization and analysis of EEG data.
1. The Seizure Detection component of Cliniscan500 EEG 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.
1. Cliniscan®ª EEG is intended for use on EEG recordings acquired using full scalp montage according to the standard 10/20 system.
1. The user may annotate the data, and the annotations are stored with the EEG recording in the cloud.
1. Cliniscan3M EEG displays standard qEEG features to the user including FFT Power Spectrum, Coherence Mapping (EEG Activity Mapping), Density Spectral Array, EEG Topography Maps, and Wavelet Subband Decomposition (Delta, Theta, Alpha, Beta, and Gamma).
1. Cliniscan5M EEG detects seizure events for review by qualified medical professionals.
1. Cliniscan5M EEG is designed to provide analytics data derived from a patient's input EEG data. It is NOT designed to provide definitive diagnoses of diseases or treatments of ailments.

Image /page/9/Picture/8 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and light blue circles with one orange circle, followed by the text "PICOFEMTO" in black and blue. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller, lighter blue font.

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

Device Comparison to Predicate Device:

Features	Persyst RevealEEG Review andAnalysis SoftwareK011397	Curry 7MultimodalNeurolmagingSoftwareK001781	CliniscanSM EEGElectroencephalogram(EEG) signal spectrumand source analyzerK141883
1. Product Code	OMB/OLT	OLX	OMB/OLT
2. Product Class	II	II	II
3. EEG Modality Compatible	Yes	Yes	Yes
4. Identifies seizures	Yes	No	Yes
5. Intended Use Age Range	Pediatric and Adult	Pediatric and Adult	Adult (18+)
6. Montage/Channel Array	Scalp 10/20 Array	Custom and Scalp10/20 Array	Scalp 10/20 Array
7. Type of EEG analysis	Post-hoc	Real-time and post hoc	Post-hoc
8. Data storage	Yes	Yes	Yes
9. Artifact Reduction	Yes	Yes	Yes
10. Wavelet sub banddecomposition	Yes	Yes	Yes
11. Density spectral maps	Yes	No	Yes
12. FFT Power Spectrum	Yes	Yes	Yes
13. EEG Topographical Maps	Yes	Yes	Yes
14. Coherence Maps (EEGBrain Mapping)	No	Yes	Yes
15. User-defined parametersfor display purposes	Yes	Yes	Yes
16. Cloud based	No	No, but includes anonline signal processingpackage	Yes
17. Operating Systems	Unknown	Unknown	Windows and MacOS
18. Applicable Web Browsers	N/A	Unknown	Firefox ESR Version24Chrome Version 35
19. Computer hardwareneeded but not provided.	unknown	Unknown	Yes

We have found that Cliniscan® EEG is substantially equivalent to Persyst Reveal for all of the features (1-19) with the exception of Coherence Mapping; however, Cliniscan®º EEG is substantially equivalent to Curry 7 regarding the Coherence Mapping feature (See Explanation 14. Coherence Mapping below).

Image /page/10/Picture/3 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and light blue circles with one orange circle, followed by the text "PICOFEMTO" in a combination of black and blue. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller font size.

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

1. Product Code: Persyst Reveal and Picofemto's Cliniscan® EEG both fall under product code OMB with a secondary product code OLT. Both devices mark events in previously acquired EEG recordings with supplemental quantitative EEG analysis.
1. Product Class: Both devices are a product class II due to the possibility of a medical professional relying on device output to determine patient diagnosis. Neither device attempts to diagnose a disease or ailment of any kind, and results must always be reviewed by qualified medical professionals.
1. EEG Modality Compatible: Both devices are intended to take previously acquired EEG recordings and analytically process the data.
Identifies Seizures: Both devices detect seizure activity. Cliniscan® EEG detects seizures by 4. highlighting the window of the suggested event location. Persyst Reveal provides an equivalent single bar with the seizure event indicated.
1. Intended Use Age Range: Both devices are intended for use in adults; however, Persyst Reveal includes pediatric use for seizure detection.
1. Montage/Channel Array: Both devices are compatible with a standard 21-channel 10/20 monopolar montage using scalp electrodes.
1. Type of EEG Analysis: Both devices are intended for use in post-hoc analysis of EEG recordings. Neither device is meant to detect events in real-time analysis or to administer any medication based on detected events.
1. Data Storage: Both devices offer data storage so the user only needs to upload the EEG recording one-time. In Cliniscan® EEG, data is stored safely on the cloud for the user to access from any compatible device.
1. Artifact Reduction: Both products offer artifact reduction using overlapping epochs to remove artifacts resulting from muscle twitches, eye movement, electrical, heartbeat, tongue and chewing. Persyst Reveal offers artifact reduction based on a user selection using blind source separation algorithms. Cliniscan500 uses measures of Kurtosis in back-end processing to automatically remove artifacts.
1. Wavelet Sub-band Decomposition: Both devices decompose brain waves into alpha (8-12 Hz), beta (13-30 Hz), delta (<3 Hz), theta (4-7 Hz), and gamma (30-100 Hz) waves.
1. Density Spectral Maps: Persyst Reveal and Cliniscan® EEG both derive a color density spectral array map using the results from the Fast Fourier Transform to calculate and display the power spectrum.
1. FFT Power Spectrum: Both devices use FFT to produce a graphical output of amplitude verses frequency (Power Spectrum) for a reader to view the overview of a long period EEG in the frequency range.
1. EEG Topographical Maps: Persyst Reveal and Cliniscan® EEG topographical maps available to the user. Cliniscan300 EEG uses independent component analysis to generate a heat map indicating the relative power of independent activity at each electrode. Persyst Reveal uses a similar approach by displaying a topographic map of the voltage and frequency concentrated at each electrode. There is no substantial technological difference between how each device chooses to calculate and display EEG Topographical Maps.
1. Coherence Mapping: All three devices calculate coherence using the same methodology; however, Cliniscan®® EEG and Curry 7 provide a simple coherence visualization for the user to view. They both display coherence values on a generic image merely to aid the user in identifying electrode locations, as opposed to placing them in a table. Although Curry 7 is a

Image /page/11/Picture/14 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and orange circles on the left, followed by the text "PICOFEMTO" in a bold, sans-serif font. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller, lighter font.

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

multimodal device, the Signal Processing Module available with Curry 7 only uses the EEG data acquired for qEEG calculations (including coherence), which is equivalent to the coherence calculated and displayed by CliniscanSM EEG.

Coherence Mapping does not change the intended use or safety and effectiveness of the device when compared to Curry 7 because both devices still intend to aid a qualified EEG expert in the visualization and analysis of the electrical activity of the brain found in EEG recordings. Curry 7 provides an almost identical and functionally equivalent Coherence Map for the user to view coherence between electrodes, including 2D maps and user-defined threshold values. Therefore, there is no substantial difference in safety or effectiveness of Cliniscan® EEG's Coherence Mapping versus predicate Curry 7.

1. User-defined parameters for display purposes: Both devices offer user-defined parameters for display purposes. Persyst Reveal offers a user-defined threshold to detect seizure events with an increased sensitivity at a cost of increased false detections per hour. Cliniscan® offers userdefined parameters for determining coherence between different parts of the brain. There is no suggested initial parameter threshold, and the results are displayed based on the user-defined threshold (0-1).
1. Cloud Based: Persyst Reveal requires locally downloaded software; Cliniscan504 EEG is built in the cloud with cloud storage, making it much more easily accessible.
1. Operating Systems: Cliniscan300 EEG is compatible with both Windows and Macintosh operating systems. The compatible operating systems for Peryst Reveal is unknown; however, this feature does not introduce any questions of safety or effectiveness.
1. Web Browsers: Cliniscan50 EEG works on both FireFox ESR 24 and Google Chrome 35. This feature is not applicable to Peryst Reveal since no web browser is necessary; however, this feature does not introduce any questions of safety and effectiveness.
1. Computer hardware needed but not provided: Persyst Reveal: Unknown. Cliniscan50 EEG: Minimum Screen size: 13″, Recommended screen size: 20″, Minimum amount of RAM: 4Gb, Recommended: 8Gb, Minimum Processor Speed: 1Ghz, Minimum display width of 1366 pixels and minimum display height of 768 pixels, Recommended display width is 1920 pixels and recommended display height is 1200 pixels. This feature does not introduce any questions of safety and effectiveness.

Predicate Device Comparison Conclusion: Cliniscan501 EEG has the same intended use/indications for use and technological features as the predicate Persyst Reveal with no new questions of safety and effectiveness. Persyst Reveal and Cliniscan®60 EEG differ in that Cliniscan®6 EEG additionally provides Coherence Mapping equivalent to Curry 7; however, this feature does not introduce any additional questions of safety and effectiveness. Persyst Reveal and Cliniscan® EEG are both designed to assist qualified medical professionals through the use of qEEG tools and automatic seizure event detection for post-hoc analysis of EEG recordings.

Image /page/12/Picture/8 description: The image contains the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and orange circles on the left, followed by the text "PICOFEMTO" in a sans-serif font. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller, sans-serif font. The overall design is clean and modern.

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

Testing was performed at the unit, integration, and functional/system Non-Clinical Performance Data: levels and included verification testing of algorithms and risk control measures. Synthetic data was used to test ICA, Coherence, FFT, and Seizure Detection. Furthermore, archived clinical data from multiple sites was used to train and validate the internal parameters involved in seizure detection.

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

A clinical study was conducted to demonstrate substantial safety and effectiveness when Clinical Study Cliniscan5M EEG's event detection algorithm is compared to ground truth (two-thirds Data: majority rule of manual markings by EEG experts). These claims are supported by evaluating the Positive Percent Agreement (PPA) and False Positives per hour (Fp/H) of Cliniscan®M EEG verses ground truth, each EEG expert verses the compiled ground truth, and comparison to previous results from predicate Persyst Reveal.

Subject Population and Test Data Set

Cliniscan® EEG was evaluated using 144 subjects for seizure determination acquired from the Epilepsy Monitoring Unit (EMU). Recordings are attained as archived clinical data from subjects 18 years of age and greater. Each recording lasts approximately 2 hours for a total of about 293 hours of EEG recordings. Roughly 20% of the recordings are "normal", coming from subjects with no history of seizures; each recording contains no more than 4 seizures to reduce bias and heavily weighted results. After ground truth determination, 134 seizures were identified in the clinical study collection. All recordings were previously acquired using a standard 10-20 montage scalp EEG and saved down in .edf format.

Image /page/14/Figure/3 description: The image is a bar graph titled "Clinical Study Recording Age Ranges". The x-axis is labeled "Age Ranges (years)" and shows age ranges from 18-25 to 66+. The y-axis is labeled "Number of Recordings" and ranges from 0 to 35. The bar graph shows that the 18-25 age range has the most recordings, with approximately 32 recordings.

Reference Standard (Ground Truth)

Each of the 144 recordings were manually marked for seizure onset and offset by three independent and blinded EEG experts. Each expert was provided with a basic EEG visualizer loaded onto a remote machine along with the previously acquired EEG recordings. The end point for the clinical study was for each EEG expert to manually mark any seizure events located in the collection of EEG recordings. Due to the expected inter-rater variability, a two-thirds majority rule was used to determine the ground truth for seizure presence.

Image /page/14/Picture/6 description: The image contains the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and light blue circles with one orange circle, followed by the text "PICOFEMTO" in black and blue. Below "PICOFEMTO" is the text "BIOMEDICAL ANALYTICS" in a smaller, lighter blue font.

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

Statistical Analysis

1. Inter-rater Performance for Seizure Detection
  Each rater is compared to every other rater to find their relative PPA and Fp/H. The PPAs ranged from 0.77-0.90 and the Fp/H ranged from 0.13-0.20. These ranges are typical for acceptable predicate devices; therefore, the inter-rater agreement is sufficient for compiling a 2/3 majority ground truth.

	Rater 1		Rater 2		Rater 3
	PPA	Fp/H	PPA	Fp/H	PPA	Fp/H
Rater 1	-	-	0.90	0.14	0.84	0.13
Rater 2	0.90	0.14	-	-	0.77	0.16
Rater 3	0.84	0.16	0.77	0.20	-	-

1. Algorithm Seizure Detection Analysis
  The same recordings marked by all three EEG experts were ran through the Cliniscan5M EEG event detection algorithm. The algorithm results are compared to the compiled ground truth using PPA and Fp/H (See eq.1 and eq.2). A bootstrap method is compiled to create a 95% confidence interval to compare the algorithm to ground truth.

$$PPA = \frac{\text{# of True Positives}}{\text{# of True Positives} + \text{False Negatives}} \text{ (Eq. 1)}$$

of False Detections Fp/H = (Eq. 2 hour of EEG Recording

Image /page/15/Picture/8 description: The image contains the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and orange circles on the left, followed by the company name "PICOFEMTO" in a sans-serif font. Below the company name, the words "BIOMEDICAL ANALYTICS" are written in a smaller, lighter blue font. The overall design is clean and modern, suggesting a focus on technology and data analysis in the biomedical field.

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

Results

Cliniscan§™ results are obtained from the clinical study designed specifically for testing Cliniscan5M. The Cliniscan5M EEG's seizure detection algorithm was compared to the ground

	[Lower Limit,Upper Limit]	OriginalMean	Bias	Bias-correctedMean	StandardError
PPA(95% C.I.)	[0.687,0.857]	0.7835	0.0011	0.7846	0.042
Fp/H(95% C.I.)	[0.325,0.540]	0.4164	-0.0002	0.4162	0.054

truth to determine PPA and Fp/H.

Conclusion

Based on the non-clinical testing, we believe Clinican™ EEG provides automatic EEG
seizure event detection which introduces no new questions of safety one, enting no new questions of safety or effectiveness.

Image /page/16/Picture/6 description: The image shows the logo for PicoFemto Biomedical Analytics. The logo consists of a cluster of blue and light blue circles with one orange circle, arranged in a circular pattern on the left. To the right of the circles is the company name, "PICOFEMTO" in black and blue, with the words "BIOMEDICAL ANALYTICS" in smaller blue font underneath.

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).