K260563 · FIND Surgical Sciences Inc. D/B/A FIND Neuro · OLX · Aug 16, 2026 · Neurology
Device Facts
Record ID
K260563
Device Name
CN-Suite™
Applicant
FIND Surgical Sciences Inc. D/B/A FIND Neuro
Product Code
OLX · Neurology
Decision Date
Aug 16, 2026
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 882.1400
Device Class
Class 2
Attributes
AI/ML, Software as a Medical Device, Real-World Evidence, Pediatric
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K260563 · Aug 16, 2026
CN-Suite™
FIND Surgical Sciences Inc. D/B/A FIND Neuro
Retrospective medical records; Intracranial EEG (iEEG) recordings; Surgical outcome data
Retrospective clinical data from four epilepsy centers were used to validate the device's performance by comparing its output (Criticality Values) against known surgical outcomes (favorable vs. unfavorable) in patients who underwent epilepsy surgery.
Retrospective, multicenter, observational clinical performance study; Retrospective, observational, multicenter study; Follow-up/Duration: Minimum of 12 months of postoperative follow-up
Adult and pediatric patients with focal or multifocal epilepsy who underwent invasive iEEG evaluation followed by curative-intent epilepsy surgery; Sample Size: 60 subjects (42 favorable outcomes, 18 unfavorable outcomes); Number of Sites: 4 U.S. epilepsy surgery centers
Not applicable for this study
Ability of patient-level Confidence Score to distinguish between favorable and unfavorable surgical outcomes; contact-level localization performance
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Criticality Values
Locked XGBoost inference model
Standardized effect size > 0.205
Standardized effect size of 1.00 (95% CI: 0.48 to 1.46)
Retrospective clinical data
—
Retrospective, multicenter, observational clinical performance study: 60 subjects (42 favorable outcomes, 18 unfavorable outcomes) from four U.S. epilepsy surgery centers.
—
Indications for Use
The CN-Suite™ is intended for use by trained and qualified clinicians (e.g., EEG technologists, epileptologists, and neurosurgeons) on adult and pediatric patients (aged 3 years and older) with focal or multifocal epilepsy for the visualization and quantitative analysis of brain network dynamics derived from intracranial electrophysiological recordings (iEEG). CN-Suite™ calculates and displays patient-specific Criticality Values for each analysis node. Criticality Values are continuous quantitative metrics derived from delay-adjusted, non-linear directed causality analysis of spatiotemporal electrophysiological patterns and are intended to assist trained clinicians in identifying and prioritizing brain regions that may be relevant during presurgical evaluation. Device outputs are intended to be interpreted in conjunction with the original electrophysiological recordings, neuroimaging data, and other available clinical information. CN-Suite™ provides quantitative clinical decision-support information and does not provide autonomous diagnostic conclusions or treatment recommendations. The software does not independently determine the epileptogenic zone or recommend surgical intervention. Device outputs are intended to support, but not replace, multidisciplinary clinical judgment and should always be interpreted together with other available clinical information.
Device Story
Software as a medical device (SaMD) for epilepsy presurgical planning; analyzes multimodal data including iEEG, MRI, and CT. Inputs: iEEG recordings, neuroimaging. Processing: constructs seizure-related network via delay-adjusted wavelet-based transfer entropy (dWTE); computes 'Criticality Values' (0-10 scale) per analysis node using a locked XGBoost inference model. Output: 3D anatomical renderings with color-coded Criticality Value overlays. Used in Level IV epilepsy centers/neurosurgical environments by epileptologists, neurosurgeons, and EEG technologists. Workflow: local on-premise server for data ingestion/visualization; secure transmission of de-identified data to AWS cloud for computationally intensive analysis. Output serves as clinical decision support; interpreted alongside original recordings/imaging to assist in identifying brain regions for potential resection or ablation. Benefits: provides quantitative network dynamics to support multidisciplinary surgical planning.
Clinical Evidence
Retrospective, multicenter, observational study (N=60) using previously acquired iEEG and surgical outcome data. Primary endpoint: ability of patient-level Confidence Score to distinguish favorable vs. unfavorable surgical outcomes. Results: Mean Confidence Score 0.781 (favorable) vs 0.538 (unfavorable); effect size 1.00 (95% CI: 0.48-1.46; p=0.002), exceeding performance goal of 0.205. Secondary contact-level sensitivity 63.9% and specificity 84.4%. No device-related adverse events reported.
Technological Characteristics
Software-only; web-based platform (Windows/macOS/Linux). Integrates iEEG (EDF+, FIFF) and neuroimaging (DICOM, NIfTI). Uses rigid CT-to-MRI registration. Connectivity: local on-premise server with AWS cloud for analysis. Algorithm: locked XGBoost inference model using delay-adjusted wavelet-based transfer entropy (dWTE). Visualization: 3D MRI-based cortical surface and 2D synchronized slice views.
Indications for Use
Indicated for adult and pediatric patients (aged 3 years and older) with focal or multifocal epilepsy to assist clinicians in identifying and prioritizing brain regions relevant during presurgical evaluation.
Regulatory Classification
Identification
An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.
{0}
**FDA U.S. FOOD & DRUG**
ADMINISTRATION
August 16, 2026
FIND Surgical Sciences Inc. D/B/A FIND Neuro
% Brittany Valdez Nava
Director - Quality Business Unit
Healthcare Innovation Catalysts, Inc.
8024 Summer Mill Court
Bethesda, Maryland 20817
Re: K260563
Trade/Device Name: CN-Suite™
Regulation Number: 21 CFR 882.1400
Regulation Name: Electroencephalograph
Regulatory Class: Class II
Product Code: OLX
Dated: July 16, 2026
Received: July 17, 2026
Dear Brittany Valdez Nava:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device"
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
{1}
K260563 - Brittany Valdez Nava
Page 2
(https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13485 clause 8.3 (Nonconforming product), ISO 13485 clause 8.5.2 (Corrective action), and ISO 13485 clause 8.5.3 (Preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and ISO 13485 clause 7.5) and document changes and approvals in the Medical Device File (ISO 13485 clause 4.2.3).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
{2}
K260563 - Brittany Valdez Nava
Page 3
Sincerely,
# Patrick Antkowiak -S
Patrick Antkowiak
Assistant Director
DHT5A: Division of Neurosurgical,
Neurointerventional, and
Neurodiagnostic Devices
OHT5: Office of Neurological and
Physical Medicine Devices
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
Enclosure
{3}
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
# Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 06/30/2023
See PRA Statement below.
510(k) Number (if known)
K260563
Device Name
CN-Suite™
Indications for Use (Describe)
The CN-Suite™ is intended for use by trained and qualified clinicians (e.g., EEG technologists, epileptologists, and neurosurgeons) on adult and pediatric patients (aged 3 years and older) with focal or multifocal epilepsy for the visualization and quantitative analysis of brain network dynamics derived from intracranial electrophysiological recordings (iEEG).
CN-Suite™ calculates and displays patient-specific Criticality Values for each analysis node. Criticality Values are continuous quantitative metrics derived from delay-adjusted, non-linear directed causality analysis of spatiotemporal electrophysiological patterns and are intended to assist trained clinicians in identifying and prioritizing brain regions that may be relevant during presurgical evaluation. Device outputs are intended to be interpreted in conjunction with the original electrophysiological recordings, neuroimaging data, and other available clinical information.
CN-Suite™ provides quantitative clinical decision-support information and does not provide autonomous diagnostic conclusions or treatment recommendations. The software does not independently determine the epileptogenic zone or recommend surgical intervention. Device outputs are intended to support, but not replace, multidisciplinary clinical judgment and should always be interpreted together with other available clinical information.
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."
FORM FDA 3881 (6/20)
Page 1 of 1
PSC Publishing Services (301) 443-6740
EF
{4}
FIND
NEURO
### 1.0 510(K) SUMMARY
This 510(k) summary is in accordance with the requirements of the Safe Medical Device Act (SMDA) of 1990. The content of this 510(k) summary is provided in conformance with 21 CFR § 807.92.
### 1.1 Submitter's Information
Company Name: FIND Surgical Sciences Inc. d/b/a FIND Neuro
Address: 1770 Massachusetts Ave, Suite 806
Cambridge, MA 02140 USA
Company Contact: Noam Peled
Chief Executive Officer
FIND Surgical Sciences Inc. d/b/a FIND Neuro
1770 Massachusetts Ave, Suite 806
Cambridge, MA 02140 USA
Phone: +1 617-959-0457
Email: noam@findneuro.com
Official Correspondent: Brittany Valdez Nava, MRSc
Director – Quality Business Unit
Healthcare Innovation Catalysts, Inc.
8024 Summer Mill Court
Bethesda, MD 20817
Date prepared: July 3rd, 2026
### 1.2 Subject Device Name
Trade Name: CN-Suite™
Regulation Name: Electroencephalograph
Regulation Number: 21 CFR 882.1400
Device Class: Class 2
Product Code: OLX
Product Code Name: Source localization software for electroencephalograph or magnetoencephalograph
510(k) Review Panel: Neurology
CN-Suite™ - K260563
Page 1 of 12
{5}
FIND
NEURO
### 1.3 Legally Marketed Predicate/Reference Devices
#### 1.3.1 EZTrack
The primary predicate device for the CN-Suite™ is the EZTrack cleared under K201910.
510(k) Number K201910
Trade Name: EZTrack
Regulation Name: Electroencephalograph
Regulation Number: 21 CFR 882.1400
Device Class: Class 2
Product Code: OLX
Product Code Name: Source localization software for electroencephalograph or magnetoencephalograph
510(k) Review Panel: Neurology
#### 1.3.2 MEGreview
An additional predicate device for the CN-Suite™ is the MEGreview cleared under K233985.
510(k) Number K233985
Trade Name: TRIUX™ neo (NM27000N ); MEGreview (SW26241N-B)
Regulation Name: Electroencephalograph
Regulation Number: 21 CFR 882.1400
Device Class: Class 2
Product Code: OLX, OLY
Product Code Name: Source localization software for electroencephalograph or magnetoencephalography
510(k) Review Panel: Neurology
CN-Suite™ - K260563
Page 2 of 12
{6}
FIND
NEURO
# 1.4 Device Description
# 1.4.1 Brief Written Description of the Device
CN-Suite™ is a software as a medical device (SaMD) designed to analyze multimodal neuroimaging and intracranial electrophysiology data, including intracranial electroencephalography (iEEG), magnetic resonance imaging (MRI), and computed tomography (CT), to compute patient-specific criticality values per analysis node that represent the relative influence of each analyzed node within the seizure-related network. Criticality Values are continuous quantitative metrics that characterize the relative influence of spatially localized intracranial electrophysiological activity within a modeled seizure-related network. These outputs are intended to assist trained clinicians in identifying and prioritizing brain regions that may be relevant during presurgical evaluation and surgical planning for patients with focal or multifocal epilepsy.
CN-Suite™ integrates co-registered iEEG, MRI, and CT data and computes patient-specific Criticality Values per analysis node based on directed network interactions quantified using delay-adjusted wavelet-based transfer entropy (dWTE). Criticality Values are computed on a continuous 0-10 scale and displayed as color-coded overlays on three-dimensional anatomical renderings in MRI space, enabling clinicians to evaluate the relative network criticality of analyzed regions within the context of the complete patient-specific visualization and other available clinical information.
CN-Suite™ is intended for use by trained clinicians, including EEG technologists, epileptologists, and neurosurgeons, as part of the multidisciplinary presurgical evaluation process. CN-Suite™ provides quantitative clinical decision-support information and does not provide autonomous diagnostic conclusions or treatment recommendations. Device outputs are intended to be interpreted in conjunction with electrophysiological recordings, neuroimaging data, and other available clinical information as part of the multidisciplinary presurgical evaluation process. The software supports clinical judgment by providing continuous quantitative information regarding relative network criticality and does not independently determine the epileptogenic zone or recommend surgical intervention.
The CN-Suite™ is comprised of two integrated software modules:
1. Critical Nodes (CN) Analytics Engine – A computational engine that constructs a modeled seizure-related network by estimating delay-adjusted directed interactions among analysis nodes derived from iEEG recordings using delay-adjusted wavelet-based transfer entropy (dWTE). The engine computes quantitative network metrics, including time-series metrics and connectivity-based metrics, which are used to derive a Criticality Value for each node.
2. MMVT Platform – An interactive visualization platform that integrates the output of the CN Analytics Engine with multimodal neuroimaging and electrophysiology data. The MMVT Platform provides software features for interactive visualization, exploration, annotation, and reporting of Criticality Values and associated network representations in MRI space.
The algorithm underlying CN-Suite™ was developed using retrospective clinical data and its clinical performance was validated using retrospective clinical outcome data from patients who underwent resection or ablation. The software is intended to support presurgical evaluation broadly and does not prescribe, limit, or assume any specific therapeutic approach.
CN-Suite™ - K260563
Page 3 of 12
{7}
FIND
NEURO
The system implements a hybrid deployment architecture consisting of:
- On-Premise Server - Backend software services deployed within the healthcare institution, including databases and object storage used for regulated study data.
- CN Cloud - FIND Neuro's HIPAA-compliant cloud infrastructure hosted on Amazon Web Services (AWS), used exclusively for execution of computationally intensive Critical Nodes analysis workflows.
CN-Suite™ is intended for use in Level IV epilepsy centers and neurosurgical planning environments. Data ingestion, de-identification, preprocessing, and routine visualization are performed locally on an on-premise server.
For computationally intensive analyses, the system securely transmits de-identified iEEG data segments together with electrode localization information and gray/non-gray matter classification metadata to the CN Cloud, where the locked CN algorithm is executed. Computed Criticality Values are then securely returned to the local server for visualization and clinical review.
### 1.4.2 Indications for Use
The CN-Suite™ is intended for use by trained and qualified clinicians (e.g., EEG technologists, epileptologists, and neurosurgeons) on adult and pediatric patients (aged 3 years and older) with focal or multifocal epilepsy for the visualization and quantitative analysis of brain network dynamics derived from intracranial electrophysiological recordings (iEEG).
CN-Suite™ calculates and displays patient-specific Criticality Values for each analysis node. Criticality Values are continuous quantitative metrics derived from delay-adjusted, non-linear directed causality analysis of spatiotemporal electrophysiological patterns and are intended to assist trained clinicians in identifying and prioritizing brain regions that may be relevant during presurgical evaluation. Device outputs are intended to be interpreted in conjunction with the original electrophysiological recordings, neuroimaging data, and other available clinical information.
CN-Suite™ provides quantitative clinical decision-support information and does not provide autonomous diagnostic conclusions or treatment recommendations. The software does not independently determine the epileptogenic zone or recommend surgical intervention. Device outputs are intended to support, but not replace, multidisciplinary clinical judgment and should always be interpreted together with other available clinical information.
### 1.4.3 Environment of Use
The CN-Suite™ is intended for use in professional healthcare environments within Level IV epilepsy centers, epilepsy monitoring units, and neurosurgical planning environments by trained and qualified clinicians experienced in the presurgical evaluation and management of patients with focal or multifocal epilepsy. Home use is not supported.
### 1.5 Key Performance Characteristics
The key performance specifications and characteristics of the CN-Suite™ are outlined in Table 1.
CN-Suite™ - K260563
Page 4 of 12
{8}
FIND
NEURO
Table 1: Key Performance Characteristics
| Feature | Specification/Characteristic |
| --- | --- |
| Operating System | Web-Based Platform, accessible on Windows, macOS, and Linux |
| Software Only | Yes |
| Data Acquisition System | Intracranial electroencephalography (iEEG) and standard clinical neuroimaging systems |
| Data Input Format (iEEG) | EDF+, FIFF |
| Data Input Format (Imaging) | DICOM, NIfTI |
| MRI Visualization | 3D visualization in MRI space |
| Rigid MRI-CT Registration | Yes, rigid CT-to-MRI registration |
| Data Storage | Study data are stored locally on the on-premise server. De-identified data required for computational analysis are securely transmitted to FIND Neuro's HIPAA-compliant cloud infrastructure. |
| Quantitative Output | Continuous Criticality Values for each analysis node, computed on a per-seizure basis using time-series and connectivity-based metrics derived from delay-adjusted wavelet-based transfer entropy (dWTE) and a locked XGBoost inference model |
| Mean Processing Time | <15 minutes per 60-second iEEG recording per seizure (typical configuration) |
| iEEG Visualization (2D and 3D) | Yes, interactive MRI-based 3D anatomical visualization with color-coded Criticality Values. Supports rotation, zoom, slice navigation, and co-display of anatomical regions of interest |
| 3D Cortical Activity Maps | Yes - interactive MRI-based cortical surface with color-coded Criticality Values; supports rotation, zoom, slice view, and co-display of anatomical ROIs. |
| 2D Signal View | Yes, synchronized 2D slice views with localized analysis nodes overlaid and color-coded by Criticality Values |
CN-Suite™ - K260563
Page 5 of 12
{9}
FIND
NEURO
# 1.6 Comparison of Key Technological Characteristics with the Predicate Device(s)
# 1.6.1 EZTrack
The CN-Suite™ is substantially equivalent to the EZTrack [201910].
The CN-Suite™ and EZTrack have similar intended use and indications for use and share similar overall principles of operation as software-only devices intended to support presurgical evaluation of epilepsy using electrophysiological data. Both devices rely on interpretation by trained clinicians and do not provide diagnostic conclusions or treatment recommendations.
The EZTrack has similar designs, configurations, technological characteristics, and principles of operation for the following functions available in the CN-Suite™:
- Both devices are intended for use by a trained/qualified EEG technologist or physician on both adult and pediatric subjects at least 3 years of age for the visualization of human brain function from analysis of electroencephalographic (EEG) signals
- Both devices are software-only medical devices that operate on standard clinical computing infrastructure. Neither device includes patient-contacting hardware or dedicated acquisition equipment
- Both devices accept intracranial electrophysiology data (e.g., sEEG/iEEG) acquired using existing clinical systems to perform post-hoc computational analysis of user-selected data segments. Both have node-based quantitative metrics derived from multivariate data (e.g., EEG channels)
- Both devices present quantitative outputs intended to be interpreted by trained clinicians in conjunction with other clinical data and neither device independently identifies seizure onset zones nor provides diagnostic or treatment recommendations
- Both devices produce spatial representations of analysis results mapped to electrode locations. Outputs are presented to highlight regions that may be relevant to epileptogenic network behavior.
Main Differences between CN-Suite™ and EZTrack
The following technical characteristics in the CN-Suite™ differ from those in the EZTrack:
- Directed Network Analysis
- CN-Suite™ performs directed functional connectivity analysis using delay-adjusted wavelet-based transfer entropy (dWTE), enabling estimation of directionality and temporal propagation within seizure-related networks. EZTrack evaluates electrophysiological activity without implementing directed causality modeling.
- Directed connectivity analysis does not alter the clinical role of the device or the nature of clinician decision-making. The outputs remain quantitative visualizations intended for expert interpretation and do not assert seizure onset zone identification or clinical conclusions.
- Criticality Metric Computation
- CN-Suite™ computes a criticality value per analysis node using a fixed, locked machine-learning inference model trained on retrospective clinical outcome data.
CN-Suite™ - K260563
Page 6 of 12
{10}
FIND
NEURO
○ The criticality value is a relative ranking metric intended to highlight nodes of potential relevance within a modeled seizure network. They are presented as visual overlays to support interpretation and do not constitute diagnostic outputs, predictions, or treatment recommendations. It does not provide diagnostic output, treatment recommendations, or automated clinical decisions.
# • 3D Anatomical Visualization
○ CN-Suite™ integrates iEEG data with co-registered MRI and CT imaging and displays results as color-coded overlays in three-dimensional anatomical space. EZTrack primarily presents results in two-dimensional electrode-based visualizations.
○ Three-dimensional anatomical visualization enhances contextual understanding of electrophysiological data but does not modify the underlying analysis or generate new clinical measurements. The visualization is passive and clinician-driven, serving the same adjunctive role as two-dimensional displays.
# • Electrode Localization and Tissue Context
○ CN-Suite™ localizes bipolar electrode contacts in MRI space and incorporates gray versus non-gray matter classification into its analytical workflow.
○ Incorporation of anatomical tissue context refines spatial interpretation of electrophysiological signals but does not alter the source data, create new measurements, or prescribe clinical action. The outputs remain adjunctive and are interpreted by trained clinicians alongside standard imaging and electrophysiology review.
# 1.6.2 MEGreview
The CN-Suite™ is substantially equivalent to the MEGreview™ [K233985].
The CN-Suite™ (subject device) and the MEGreview™ (predicate device) have similar intended use and indication for use. The MEGreview™ has similar designs, configurations, technological characteristics, and principles of operation for the following functions available in the CN-Suite™:
- Both devices are intended for the visualization and clinical planning support using electrophysiological data
- Both devices analyze clinician-selected electrophysiological recordings acquired using standard clinical systems
- Both devices accept electrophysiological data in standard clinical file formats and integrate MRI data provided in DICOM or equivalent clinical imaging formats
- Both devices rely on trained clinicians to interpret results in conjunction with other imaging and clinical data and neither device provides diagnostic conclusions or treatment recommendations
- Both devices integrate electrophysiological data with MRI-based anatomical information to support spatial interpretation
- Both devices provide three-dimensional visualization of cortical or intracranial activity mapped to anatomical space to support presurgical review and planning
CN-Suite™ - K260563
Page 7 of 12
{11}
FIND
NEURO
# Main Differences between CN-Suite™ and MEGreview™
The following technical characteristics in the CN-Suite™ differ from those in the MEGreview™:
- Data Modality
○ CN-Suite™ analyzes intracranial electrophysiological recordings, including intracranial EEG (iEEG/sEEG), acquired using implanted electrodes. MEGreview analyzes magnetoencephalography (MEG) data acquired non-invasively using external MEG systems.
○ The difference reflects the source and acquisition method of the input data rather than a difference in intended clinical role. In both cases, the software performs post-hoc analysis of clinician-selected data acquired using standard clinical equipment. The software does not control data acquisition, does not influence electrode placement or sensor configuration, and does not introduce new patient risks beyond those associated with standard clinical practice.
- Directed Network Analysis Methodology
○ CN-Suite™ performs directed functional connectivity analysis using delay-adjusted wavelet-based transfer entropy (dWTE) to estimate directionality and temporal propagation of interactions within seizure-related networks. MEGreview evaluates MEG-derived activity patterns and source localization results without implementing directed causality modeling.
○ The resulting outputs are quantitative visualizations intended to support expert interpretation and multidisciplinary discussion. CN-Suite™ does not identify seizure onset zones, provide diagnostic conclusions, or prescribe clinical actions. As with MEGreview, interpretation of results remains the responsibility of trained clinicians using complementary clinical data.
- Criticality Metric Computation
○ CN-Suite™ computes a criticality value per analysis node using a fixed, locked machine-learning inference model trained on retrospective clinical outcome data.
○ The criticality value is a relative ranking metric intended to highlight nodes of potential relevance within a modeled seizure network. They are presented as visual overlays to support interpretation and do not constitute diagnostic outputs, predictions, or treatment recommendations. It does not provide diagnostic output, treatment recommendations, or automated clinical decisions.
- Anatomical Integration and Visualization
○ CN-Suite™ integrates iEEG data with co-registered MRI and CT imaging and displays results as color-coded overlays in three-dimensional anatomical MRI space. MEGreview integrates MEG data with MRI-based source localization and visualization.
○ Differences in visualization reflect modality-specific workflows rather than differences in intended use or clinical function. The visualizations are passive, clinician-driven tools that do not generate new measurements or modify source data.
CN-Suite™ - K260563
Page 8 of 12
{12}
FIND
NEURO
# • Spatial Modeling
○ CN-Suite™ analyzes bipolar electrode-derived analysis nodes localized to intracranial anatomy, whereas MEGreview visualizes distributed cortical source estimates derived from MEG data.
○ In both devices, analysis nodes represent spatially localized summaries of neurophysiological activity intended for visualization and interpretation by trained clinicians. Neither device prescribes clinical action based on node values, nor does either automate clinical decision-making.
The difference in technological characteristics between the subject and predicate devices will be evaluated through performance bench testing and clinical validation studies. The results of these studies will verify that these differences do not raise new or different questions of safety and effectiveness when the CN-Suite™ is used as intended.
# 1.7 Performance Data
# 1.7.1 Human Factors/Usability
A Usability Evaluation performed on the CN-Suite™ found no impact on the safe and effective use of the device. FIND Neuro concludes that the system is safe and effective for the intended users, uses, and use environments.
# 1.7.2 Software Verification and Validation Testing
Unit, integration, and system level software verification testing were performed to demonstrate the efficacy of the software and to confirm operation of the machine. The following testing was performed:
• Functional and Performance Verification
- Regression Testing
- Code Reviews
Software verification information within this submission is provided in accordance with the following FDA guidance documents:
- Content of Premarket Submissions for Device Software Functions (14 June 2023)
• Guidance for Off-The-Shelf Software Use in Medical Devices (11 August 2023)
- Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions (26 June 2025)
# 1.7.3 Cybersecurity
Cybersecurity documentation has been provided with this application as recommended by the FDA's Guidance for Industry and FDA Staff, "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions". All the CN-Suite™ software components underwent appropriate cybersecurity assessment and testing.
# 1.7.4 Animal Studies
No animal studies were performed on this device.
CN-Suite™ - K260563
Page 9 of 12
{13}
FIND
NEURO
### 1.7.5 Clinical Studies
Clinical performance of CN-Suite™ was evaluated in a retrospective, multicenter, observational clinical performance study using previously acquired, de-identified intracranial EEG (iEEG) and surgical outcome data from four U.S. epilepsy surgery centers.
The primary objective of the study was to evaluate the ability of the patient-level Confidence Score, derived from the device's contact-level Criticality Values, to distinguish between subjects with favorable and unfavorable surgical outcomes using a predicate-aligned effectiveness endpoint. Secondary objectives were to evaluate contact-level localization performance of the Criticality Values relative to surgically treated brain regions and to descriptively summarize performance across the intended use population.
The analysis population included 60 subjects (42 with favorable outcomes and 18 with unfavorable outcomes) who underwent invasive iEEG evaluation followed by curative-intent epilepsy surgery with a minimum of 12 months of postoperative follow-up. The primary effectiveness endpoint was met. Mean Confidence Score was 0.781 in subjects with favorable outcomes and 0.538 in subjects with unfavorable outcomes, yielding an observed standardized effect size of 1.00. The mean bootstrap effect size was 1.01 (95% CI: 0.48 to 1.46; p=0.002). The lower confidence bound of 0.48 exceeded the prespecified performance goal of 0.205. Secondary analyses demonstrated a contact-level sensitivity of 63.9% and specificity of 84.4%, providing supportive evidence that CN-Suite™ assists clinicians in identifying and prioritizing brain regions that may be relevant during presurgical evaluation.
Table 2: Primary Endpoint and Age-Subgroup Analysis
| Analysis | Favorable mean | Unfavorable mean | SD | Effect size | Mean bootstrap effect size | 95% CI | p-value |
| --- | --- | --- | --- | --- | --- | --- | --- |
| All subjects (N=60) | 0.781 | 0.538 | 0.243 | 1.00 | 1.01 | 0.48, 1.46 | 0.002 |
| Adults, age 22+ (n=47; 33 favorable/14 unfavorable) | 0.766 | 0.628 | 0.219 | 0.63 | 0.64 | 0.01, 1.22 | 0.088 |
| Pediatric, ages 4 to 21 (n=13; 9 favorable/4 unfavorable) | 0.837 | 0.222 | 0.317 | 1.94 | 1.96 | 1.85, 2.04^{1} | <0.001^{1} |
$^{1}$ The estimate is descriptive and should be interpreted cautiously because the subgroup included only 13 subjects, including 4 with unfavorable outcomes. No independent inferential or comparative conclusion is drawn.
CN-Suite™ - K260563
Page 10 of 12
{14}
FIND
NEURO
**Table 3: Sensitivity and Specificity**
*Favorable-outcome subjects only (N=42); GEE estimates clustered by subject.*
| Analysis | Contacts | Correctly classified | Estimate | 95% CI |
| --- | --- | --- | --- | --- |
| All subjects, sensitivity (N=42) | 686 | 364 | 63.9% | 55.2%, 71.8% |
| All subjects, specificity (N=42) | 3,277 | 2,695 | 84.4% | 80.9%, 87.3% |
| Adults, age 22+, sensitivity (N=33) | 631 | 323 | 59.7% | 50.3%, 68.4% |
| Adults, age 22+, specificity (N=33) | 2,003 | 1,720 | 86.3% | 83.0%, 89.0% |
| Pediatric, ages 4 to 21, sensitivity (N=9) | 55 | 41 | 81.6% | 59.7%, 93.0% |
| Pediatric, ages 4 to 21, specificity (N=9) | 1,274 | 975 | 78.4% | 69.6%, 85.1% |
Age-subgroup analyses were descriptive. The full pediatric subgroup comprised 13 subjects ages 4 through 21 (9 favorable and 4 unfavorable outcomes) and the adult subgroup 47 subjects age 22 and older (33 favorable and 14 unfavorable outcomes). The sensitivity and specificity table includes only favorable-outcome subjects and therefore covers 9 pediatric and 33 adult subjects, not the full subgroups of 13 and 47. In the adult subgroup the observed effect size was 0.63, and the lower bound of its 95% confidence interval did not exceed the performance goal of 0.205. Neither subgroup was sized for independent inference. No superiority, non-inferiority, equivalence, or between-age-group claim is made, and the primary effectiveness conclusion rests on the prespecified pooled analysis of all 60 subjects, which is unchanged. Pediatric sample size was limited by the availability of public pediatric surgical-epilepsy datasets, and the pediatric estimates are correspondingly uncertain.
CN-Suite's user-facing output is the contact-level Criticality Value. The Confidence Score is a patient-level clinical-study endpoint derived from Criticality Values; it is not a device output and is not displayed to users. EZTrack's user-facing output is the per-channel Fragility Index, described in its cleared Indications for Use as "a quantitative index based on an analysis of spatiotemporal EEG patterns," computed for each analyzed EEG recording node and displayed to the user in a heatmap, where higher values denote greater estimated network fragility. EZTrack's Confidence Statistic was a patient-level clinical-study measure derived from Fragility Index values.
Both studies evaluated a standardized effect size separating favorable and unfavorable surgical outcomes. EZTrack was evaluated in 91 patients (44 favorable and 47 unfavorable outcomes) and reported an effect size of 0.627 (p=0.02). CN-Suite was evaluated in 60 patients (42 favorable and 18 unfavorable outcomes) and had an observed effect size of 1.00 (mean bootstrap effect size 1.01; 95% CI:
CN-Suite™ - K260563
Page 11 of 12
{15}
FIND
NEURO
0.48 to 1.46; p=0.002), against a prespecified performance goal of 0.205. The observed CN-Suite effect size of 1.00 was numerically greater than the predicate's reported effect size of 0.627. The devices were evaluated in separate cohorts; this was not a head-to-head comparison, and contact-level concordance was not evaluated.
This study was fully retrospective and non-interventional. CN-Suite™ processed previously acquired, de-identified data and did not influence patient management, surgical planning, or clinical decision-making. No device-related adverse events, serious adverse events, unanticipated adverse device effects, or software-related safety concerns were identified.
Overall, the clinical performance study demonstrated that CN-Suite™ achieved its primary effectiveness objective and provided supportive evidence of contact-level localization performance consistent with its intended use as an adjunctive clinical decision-support device. Collectively, these findings support the safety, effectiveness, and substantial equivalence of CN-Suite™ to the predicate device.
### 1.8 Conclusions
Based on above discussion and enclosed sections regarding substantial equivalence to the predicate device, FIND Neuro concludes that the CN-Suite™ is substantially equivalent to the EZTrack and MEGreview and does not raise any new or different questions of safety or effectiveness.
CN-Suite™ - K260563
Page 12 of 12
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.