The ICTA software is intended as a review tool to mark previously acquired sections of the adult (greater than or equal to 18 years) EEG recordings (surface or intracranial) that may correspond to electrographic seizures, in order to assist qualified clinical practitioners, who will exercise professional judgment in using the information, in the assessment of EEG traces.

Surface recordings must be obtained with full montage according to the standard 10/20 . system.
Intracranial recordings must be obtained with depth electrodes (strips and/or grids). .
This device does not provide any diagnostic conclusion about the patient's condition to the user.

Device Description

ICTA is a software only product. It runs on a personal computer and requires no specialized hardware. It identifies electroencephalographic activity that might correspond to seizures (referred as "events"). These events are then reviewed, accepted, modified and/or deleted by the qualified medical practitioner. The software does not make any final decisions that result in any automatic diagnosis or treatment. The EEG input is read from a file on the personal computer (or available across the network).
ICTA employs Bayesian formulation to provide a detection variable based on the probabilities that a given section of EEG contains a seizure-like activity. The a priori probabilities that a certain set of features represent seizure or non-seizure data were computed from the training data set. These probabilities are used by the detection method for all seizure detections.
The software has two components: ICTA-S for analysis of surface EEG recordings and ICTA-D for analysis of intracranial recordings. Whether a particular module is active is determined by the user. The user also determines parameters that are needed for the algorithm to perform its intended task. None of the components is responsible for data acquisition, review or any other function different from analysis.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the ICTA device, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for ICTA were established through a comparison with a predicate device (NeuroWorks Seizure Detector, K090019) and the "gold standard" of expert neurophysiologists. The key performance metrics are Positive Percent Agreement (PPA) and False Detection Rate (FDR).

Performance Metric	Acceptance Criteria (Predicate)	ICTA-Surface Reported Performance	ICTA-Depth Reported Performance
PPA (%)	76%	75%	75%
FDR (FP/h)	0.6 FP/h	2.0 FP/h	1.8 FP/h

Note: The document states "Equivalent" for both metrics when comparing to the predicate, even though the FDRs are numerically different. This suggests the FDA considers these values acceptable within the context of seizure detection assistance tools.

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

ICTA-S (Surface EEG):
- Number of Seizures: 615
- Total Number of Patients: 102
- Total Number of Hours: 395
- Data Provenance: Retrospective, patients with medically refractory seizures admitted to an Epilepsy Monitoring Unit. The specific country of origin is not explicitly stated, but Natus Medical Incorporated DBA Excel-Tech Ltd. is based in Oakville, Ontario, Canada.
ICTA-D (Intracranial EEG):
- Number of Seizures: 429
- Total Number of Patients: 93 (57 Male, 36 Female)
- Total Number of Hours: 619 hours
- Data Provenance: Retrospective, adult patients seen for routine clinical evaluation at Epilepsy Monitoring Units of Toronto Western General Hospital (Canada) and NewYork-Presbyterian Hospital (USA).

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

Number of Experts: Three independent, blinded EEG experts were used for both ICTA-S and ICTA-D studies.
Qualifications: All experts were board-certified Neurophysiologists (or neurologists/epileptologists). The document does not specify their years of experience.

4. Adjudication Method for the Test Set

Adjudication Method: A "majority rule (at least 2 out of 3)" was applied. This means that for a seizure to be considered a "true" electrographic seizure (ground truth), at least two of the three independent experts had to agree on its presence.

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

The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The study focuses on evaluating the standalone performance of the ICTA algorithm against a human-established ground truth and comparing it to a predicate device's reported performance.

6. Standalone Performance Study

Yes, a standalone (algorithm only without human-in-the-loop performance) study was done. The entire clinical testing section describes the evaluation of the ICTA-S and ICTA-D algorithms' performance (PPA and FDR) independently against the ground truth established by the expert panel. The results presented in the tables (e.g., PPA 75% / FDR 2.0 FP/h for ICTA-S) are for the algorithm in standalone mode.

7. Type of Ground Truth Used

Type of Ground Truth: Expert consensus. Specifically, electrographic seizures identified by a panel of three board-certified Neurophysiologists, with a majority rule for final determination.

8. Sample Size for the Training Set

The document states that Bayesian formulation was used, and "The a priori probabilities that a certain set of features represent seizure or non-seizure data were computed from the training data set."
However, the specific sample size for the training set is not provided in the summary.

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

The document states that probabilities were computed from the "training data set." It does not explicitly detail the method for establishing ground truth for this training set. However, given the nature of the device and the methods described for the test set, it is highly probable that the ground truth for the training set was also established through expert review and annotation of EEG recordings, likely by qualified medical practitioners. The summary implies that this training data was used to establish the "a priori probabilities" for the Bayesian model.

Summary

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

Image /page/0/Picture/0 description: The image shows the logo for "xltek, a division of natus". The logo features a stylized image to the left of the word "xltek". The words "a division of natus" are in a smaller font below the word "xltek".

510K Summary

JUN 2 9 2012

Date: June 19, 2012

Submitted by: Natus Medical Incorporated DBA Excel-Tech Ltd. (XLTEK) 2568 Bristol Circle Oakville, Ontario Canada L6H 5S1

Contact Person: Daniel Ramirez, MD, PhD Clinical Scientist Natus Medical Inc. Tel.: (905) 829-5300 ext 356 Fax .: (905) 829-5304 E-mail: dramirez@natus.com

Propietary Name: ICTA

Common Name: EEG software or Electroencephalogram

Classification Name: Automatic event detection software for full-montage electroencephalograph.

Product code: OMB

Device Class: II

Predicate Devices: NeuroWorks Seizure Detector (K090019)

Description

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

Image /page/1/Picture/0 description: The image shows the logo for "xltek, a division of natus". The logo features a stylized symbol resembling an upward-pointing arrow with a starburst effect above it. The text "xltek" is written in a simple, sans-serif font to the right of the symbol. Below the text and symbol, the phrase "a division of natus" is written in a smaller font size.

ICTA employs Bayesian formulation to provide a detection variable based on the probabilities that a given section of EEG contains a seizure-like activity. The a priori probabilities that a certain set of features represent seizure or non-seizure data were computed from the training data set. These probabilities are used by the detection method for all seizure detections.

The software has two components: ICTA-S for analysis of surface EEG recordings and ICTA-D for analysis of intracranial recordings. Whether a particular module is active is determined by the user. The user also determines parameters that are needed for the algorithm to perform its intended task. None of the components is responsible for data acquisition, review or any other function different from analysis.

Indications for Use

Surface recordings must be obtained with full montage according to the standard 10/20 . system.
Intracranial recordings must be obtained with depth electrodes (strips and/or grids). . This device does not provide any diagnostic conclusion about the patient's condition to the user.

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

Image /page/2/Picture/0 description: The image shows the logo for "xltek", with a stylized "A" symbol to the left of the text. A horizontal line is drawn underneath the text. Below the line, in smaller font, is the text "a division of natus".

Predicate Comparison

	Predicate device	Subject device	Comment
	Neuroworks SeizureDetector(K090019)	ICTA
DeviceClass	Class II	Class II
Class Name	Automatic eventdetection software forfull-montageelectroencephalograph	Automatic event detectionsoftware for full-montageelectroencephalograph	Same
User Input	Mouse/keyboard	Mouse/keyboard	Same
Intended use	The Seizure Detectioncomponent ofNeuroworks isintended to markpreviously acquiredsections of the adult(greater than or equalto 18 years) EEGrecordings that maycorrespond toelectrographicseizures, in order toassist qualified clinicalpractitioners in theassessment of EEGtraces. EEGrecordings should beobtained with full scalpmontage according tothe standard 10/20system.	The ICTA software isintended as a review toolto mark previouslyacquired sections of theadult (greater than or equalto 18 years) EEGrecordings (surface orintracranial) that maycorrespond toelectrographic seizures, inorder to assist qualifiedclinical practitioners, whowill exercise professionaljudgment in using theinformation, in theassessment of EEGtraces.Surface recordings mustbe obtained with fullmontage according to thestandard 10/20 system.Intracranial recordingsmust be obtained withdepth electrodes (stripsand/or grids). This devicedoes not provide anydiagnostic conclusionabout the patient'scondition to the user.	Equivalent.Both devices areintended to forcomputer -assistedevent marking that aqualified user canuse for diagnosis.ICTA is able toanalyze surfacerecording andintracranialrecordings.
IFU-Intendeduser	Medical professionaltrained in EEGanalysis	Medical professionaltrained in EEG analysis	Same
Number ofchannels	Up to 128 channels	Up to 128 channels	Same
	Predicate device	Subject device	Comment
	Neuroworks SeizureDetector(K090019)	ICTA
Functionaloutput	Spikes, spike burst,rhythmic burst	Seizures (i.e genericallyrefer to as stellate event inthe software)	Equivalent. Onlydifference is due toICTA not used in thedetection of spikes.
User controlof detectionparameters	Detection montagecustomization.User defines detectorsettings.	Detection montagecustomization.User defines detectorsettings.	Same
Eventdetectionsensitivity%*	76%	ICTA-Surface / ICTA-Depth*75% / 75%	Equivalent
Falsepositive ratefor events*	0.6 FP/h	ICTA-Surface / ICTA-Depth*2.0 / 1.8 FP/h	Equivalent

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

Image /page/3/Picture/0 description: The image shows the logo for "xltek, a division of natus". The logo consists of a stylized star-like symbol to the left of the word "xltek". Below the word "xltek" is the phrase "a division of natus" in a smaller font. The logo is black and white.

Brief Summary of Non-Clinical and Clinical Performance Tests

All functionalities and performance of the ICTA software have been verify/validated through Bench

and clinical performance tests according to the intended use- and user- of the device.

Non-Clinical: The ICTA Algorithms rely upon underlying mathematical analyses, including signal reqularity, maximum frequency, and amplitude variation. Each mathematical analysis was independently calculated and verified against results generated from published methods.

Clinical: Natus conducted an extensive clinical test to: 1) Evaluate the positive percent agreement (i.e., detection sensitivity) and false detection rate of both components (ICTA-S and ICTA-D) of ICTA Algorithms; and, 2) Demonstrate equivalence of the seizure detection performance, in terms of positive percent agreement and false detection rates, of ICTA Algorithms to that of a predicate device and/or to the gold standard, defined as seizures detected by a panel of 3 board certified Neurophysiologists.

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

Image /page/4/Picture/0 description: The image shows the logo for "xltek", which is described as a division of "natus". The logo features a stylized symbol resembling a mountain or a stylized letter "A" with three small circles above it, followed by the text "xltek" in a simple, sans-serif font. Below the text, in a smaller, more stylized font, is the phrase "a division of natus".

ICTA-S Study.

Subject Population and Test Dataset

The seizure detection performance of ICTA-S Seizure detection algorithm was evaluated on scalp EEG recordings from patients with medically refractory seizures. All patients 18 years of age or older with a history of seizures admitted to an Epilepsy Monitoring Unit for long term EEG-video recordings for diagnostic or pre-surgical evaluation were asked to participate. The validation data set includes EEG studies with full montage (21 channels).

Dataset Description

Number of Seizures: 615 Total Number of Patients: 102 Total Number of Hours: 395 (mean ± SD =3.18 ± 0.03; range 2.0 ~5.2)

Under the constraint that no more than 3% of the total seizures were included from one subject; detection performance was tested on 615 seizures in a total of 395 hours of scalp EEG recordings from 102 patients. Otherwise, no additional inclusion criteria were applied in the data selection process.

Reference Standard

Each of the EEG recordings was reviewed by three independent, blinded EEG experts (all neurologists/epileptologists) to identify electrographic seizures and spikes. The end point of this independent review was to identify, it any, the seizure onset times in each of the sampled EEG segments. Due to the anticipated inter-rater variability among EEG experts, a majority rule (at least 2 out of 3) was applied to make the final determination of "true" electrographic seizure.

Statistical Analysis for Seizure Detection Algorithm

1. Inter Rater Performance for Seizure detection: Inter-rater Positive Percent Agreement (PPA) ranged between 73 and 85%, while False Detection per hour (FD/h) was very close for all three raters (0.3 FD/h, on average) for Seizure Detection.

	Seizure
	Rater		Rater2		Rater3
	PPA	FD/h	PPA	FD/h	PPA	FD/h
Rater 1	-	-	0.85	0.2	0.80	0.4
Rater 2	0.78	0.4	-	-	0.73	0.5
Rater 3	0.80	0.3	0.80	0.3	-	-

1. Detection Performance for Seizure detection Algorithm: Based on the seizure samples determined by the independent EEG review panel, the positive percentage agreement (i.e., detection sensitivity) and false detection rate were estimated for both ICTA-S algorithm and the predicate device. Bootstrap method was applied to construct 95% confidence intervals for the estimated performance statistic.

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

Image /page/5/Picture/0 description: The image shows the title of a document, which is "510(K): ICTA SEIZURE DETECTION ALGORITHM". Below the title, it says "510K SUMMARY". The image also indicates that it is page 6 of 8.

Image /page/5/Figure/1 description: The image shows the logo for "xltek", with a stylized arrow pointing upwards to the left of the text. A dashed line underlines the text, and below the line is the text "a division of natus" in a smaller font size. The logo appears to be for a company or organization named "xltek", which is a division of "natus".

Results of Seizure Detection Algorithm - Summary

Image /page/5/Figure/3 description: The image is a plot of PPA (%) vs FDR (FP/h) for ICTA-S. The plot shows a line with three data points, with the detection threshold indicated by the shape of the data point. The data points are (0.6, 0.63), (1.0, 0.69), and (2.0, 0.75), with corresponding false positive rates of 0.5 FP/h, 1.0 FP/h, and 2.0 FP/h.

ICTA-S seizure detection algorithm performance as a function of detection threshold level.

One characteristic of the ICTA-S algorithm is the possibility for the user to adjust the detection threshold (Th) value. Changing the threshold value affects performance of the algorithm. As can be seen on the figure above, there is a tradeoff between PPA and the FDR. At lower values of the detection threshold the PPA improves (i.e at Th = 2, PPA= 75%) while the FDR increases. Higher values of Th result in the opposite behavior, that is, PPA decreases and the FDR improves (at Th= 4, FDR= 0.5 FP/h). The ICTA-S Algorithm had a 75% PPA and an FDR of 2.0 FD/h compared to the reference standard. Detailed performance data of the ICTA-S seizure detector is shown on the table below.

DetectionThreshold	PPA (95% CI)	FDR (FP/h)
Th_2	75 (70 – 80)	2.0 (1.5 - 2.4)
Th_3	69 (62 - 72)	1.0 (0.7 - 1.3)
Th_4	63 (54 - 66)	0.5 (0.3 - 0.7)

(95% C.I.) - 95% Bootstrap Confidence Interval

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

Image /page/6/Picture/0 description: The image shows the logo for "xltek", which is described as a division of "natus". The logo features a stylized letter "A" with a small circle above it, resembling a person with outstretched arms. To the right of the symbol is the word "xltek" in a simple, sans-serif font. Below the word "xltek" is the phrase "a division of natus" in a smaller font size.

ICTA-D Study

Subject Population and Test Dataset

All EEGs used for validation were collected from adult patients seen for routine clinical evaluation at the Epilepsy Monitoring Units of Toronto Western General Hospital and NewYork-Presbyterian Hospital. A physician not taking part on the subsequent review/scoring of the data conducted database query and study inclusion from a patient database of consecutive recordings. All studies consisted on electrocorticographic (ECoG) recordings obtained using Natus proprietary hardware/software, with full intracranial electrodes (strips and/or grids), and were included independently of ECoG patterns and technical quality.

Dataset Description

Number of Seizures: 429 Total Number of Patients: 93 Number of Hours: 619 hours

AGE (Mean ± SD)	40.8 ± 11.1*
GENDER	57 (Male)36 (Female)

All subjects involved in this study were adult patients (≥18 years old).

To avoid over-weighting recordings containing many events, a maximum of 12 events per recording were permitted.

Reference Standard

Each of the ECoG recordings was reviewed by three independent, blinded EEG experts (all neurologists/epileptologists) to identify electrographic seizures. The end point of this independent review was to identify, if any, the presence of seizures in each of the sampled ECoG segments. Due to the anticipated inter-rater variability among EEG experts, a majority rule (at least 2 out of 3) was applied to make the final determination of "true" electrographic seizure.

Results

1. Inter Rater Performance

Each Rater was compared against the "consensus" marking of the remaining two raters. The results are shown on table below. Rater 1 showed the highest possible PPA with 77%, which was also accompanied by higher FDR though within the performance of the other reviewers. PPA and FDR for the other reviewers were similar with 70% PPA. Reviewer 2 (compared to Reviewer 1 + Reviewer 3) showed the lowest FDR of 0.7 FP/h.

	PPA (95% CI)*	FDR (95% CI)*
REV1(vs. Rev2+Rev3)	77 (74-86)	0.8 (0.6 - 1.0)
REV2(vs. Rev1+Rev3)	70 (66-80)	0.7 (0.5 -0.9)
REV3(vs. Rev1+Rev2)	71 (67-82)	0.8 (0.5 - 1.0)

Inter-rater Positive Percent Agreement and False Detection Rate

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

Image /page/7/Picture/0 description: The image shows the logo for Xltek, a division of Natus. The logo features a stylized arrow pointing upwards, followed by the text "xltek" in lowercase letters. Below the text is the phrase "a division of natus" in a smaller font size.

Image /page/7/Figure/2 description: The image is a summary of the results of a seizure detection algorithm. The plot shows PPA on the y-axis and FDR on the x-axis. There are three data points for the estimated values, with the data point at FDR of 0.6 and PPA of 0.64, the data point at FDR of 1.1 and PPA of 0.70, and the data point at FDR of 1.8 and PPA of 0.75.

With detection threshold at 2, ICTA-D achieved 75% positive percent agreement and a false detection rate of 1.8 FP/hr. As was the case for ICTA scalp detector, for ICTA-D also the variation of "threshold detection" levels translated into a trade-off between PPA and FDR. At lower threshold values (i.e. =2) PPA increases at same time that the "specificity" decreases, that is, the number of false detections increases.

Unlike other algorithms reported in the scientific literature, ICTA-D was built to allow for user tuneability, which gives the flexibility of regulating performance as desired. Users can control algorithm behavior by adjusting thresholds to tune performance as they see fit. At default thresholds, results comparable to expert reviewers were obtained with no need of altering the algorithm at run time.

Conclusion

Based on the results of the non-clinical and clinical testing we conclude that ICTA (ICTA-S and ICTA-D) seizure detection algorithm is substantially equivalent to the predicate device and reference standard.

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

DEPARTMENT OF HEALTH & HUMAN SERVICES

Image /page/8/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a stylized eagle or bird-like symbol with three overlapping, curved lines forming its body and wings. The logo is encircled by the text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" in a circular arrangement. The text is in all capital letters and is evenly spaced around the circle.

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

Excel-tech Ltd. c/o Daniel Ramirez, MD, PhD Clinical Scientist, Division of Natus Medical Inc. 2568 Bristol Circle Oakville, Ontario Canada L6H 5S1

JUN 2 9 2012

Re: K120260 Trade/Device Name: ICTA Regulation Number: 21 CFR 882.1400 Regulation Name: Electroencephalograph Regulatory Class: Class II Product Code: OMB Dated: April 6, 2012 Received: June 14, 2012

Dear Dr. Ramirez:

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.

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

Page 2 - Daniel Ramirez, MD, PhD

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

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

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

You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

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

Sincerely yours,
Kesia Alexander

Image /page/9/Picture/7 description: The image shows a signature in black ink on a white background. The signature appears to be stylized and cursive, with a prominent loop at the top and a flowing line extending downwards. The overall impression is that of a quick, practiced signature.

Malvina B. Eydelman, M.D. Director Division of Ophthalmic, Neurological, and Ear, Nose and Throat Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

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

Indications for Use Statement

510(k) Number (if known):

K120260

Device Name: ICTA

Indications for Use:

Surface recordings must be obtained with full montage according to the standard 10/20 . system.
Intracranial recordings must be obtained with depth electrodes (strips and/or grids). .

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

Prescription Use (Per 21 CFR 801.109) OR

Over-The Counter Use

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

Concurrence of CDRH, Office of Device Evaluation (ODE)

John Grimes, Ph.D.

(Division Sign-Off) Division of Ophthalmic, Neurological and Ear, Nose and Throat Devices

510(k) Number K120260

(Optional Format 1-2-96)

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).