Routine clinical EEG recordings from an epilepsy monitoring unit
Retrospective clinical EEG recordings were used to validate the performance of the spike and seizure detection algorithm against a reference set established by expert review.
Patients 18 years or over with scalp EEG recordings; Sample Size: 76 records from unique patients
Persyst Reveal (K011397) and three human experts
Positive percent agreement (sensitivity) and negative disagreement rate (false detection rate) for spike and seizure detection
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Spike detection
—
—
—
—
—
76 records from unique patients (age 18-92, 6-71 hours duration) acquired in an epilepsy monitoring unit.
3 (human experts)
Seizure detection
—
—
—
—
—
76 records from unique patients (age 18-92, 6-71 hours duration) acquired in an epilepsy monitoring unit.
3 (human experts)
Indications for Use
Cadwell Spike and Seizure Detector is a software-only product with an algorithm intended to analyze and mark evens that may correspond to epileptiform discharge (spike) and clectrographic seizure for the purpose of reviewing scale EFG recordings. The marked events are reviewed, deleted, and interpreted by qualified clinical practitioners who will exercise professional judgment in using the information. This device does not control the delivery of energy, administration of drugs, or another form of life sustaining function to the patient. It is intended for use in patients who are 18 years or over. This device does not provide any diagnostic conclusion about the patient to the user.
Device Story
Software-only device; analyzes scalp EEG recordings (10/20 electrode placement) to identify and mark potential spikes and electrographic seizures. Operates post-hoc on recorded data; does not provide diagnostic conclusions; does not control life-sustaining functions. Used by neurologists, clinicians, and EEG technicians in clinical settings (e.g., epilepsy monitoring units). Output consists of annotated events on the EEG record; clinicians review, edit, or delete these marks using professional judgment to interpret the data. Benefits include improved efficiency in reviewing long-duration EEG recordings.
Clinical Evidence
Bench testing using 76 retrospective EEG records (18-92 years old; 6-71 hours duration) from an epilepsy monitoring unit. Reference set established by three human experts (majority rule). Performance metrics (sensitivity and false detection rate) compared against human experts and the predicate device (Persyst Reveal) using bootstrap methods. Results demonstrated device effectiveness and substantial equivalence.
Technological Characteristics
Software-only; post-hoc analysis of scalp EEG data; 10/20 electrode montage; standalone software application; no energy delivery or life-sustaining functions.
Indications for Use
Indicated for patients 18 years or older to assist qualified clinical practitioners in reviewing scalp EEG recordings by analyzing and marking events potentially corresponding to epileptiform discharges (spikes) and electrographic seizures.
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}------------------------------------------------
Image /page/0/Picture/0 description: The image shows the logo for "OCADVELL" on the left and the text "510k Summary" on the right. The logo consists of a circle with a heartbeat symbol inside, followed by the text "OCADVELL" in bold, sans-serif font. The text "510k Summary" is also in a bold, sans-serif font and is positioned to the right of the logo.
:
| Submitter: | Cadwell Laboratories, Inc. | K140552<br>JUL 2 3 2014 |
|------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------|
| Contact Person: | Chris Bolkan<br>Safety / Regulatory Specialist<br>Cadwell Laboratories, Inc.<br>909 N. Kellogg Street<br>Kennewick, WA 99336<br>Phone: (509) 735-6481<br>Fax: (509) 783-6503 | |
| Date Prepared: | February 27, 2014 | |
| Trade Name: | Cadwell Spike and Seizure Detector | |
| Common Name: | Spike and Seizure Detector | |
| Classification Name<br>and Number: | Electroencephalograph, Class II, 21 CFR 882.1400 | |
| Product Code: | OMB | |
| Classification Panel: | Neurology | |
| Predicate Device: | Persyst Reveal (K011397) | |
| Device Description: | Cadwell Spike and Seizure Detector is a software-only<br>product with an algorithm intended to analyze and mark<br>events that correspond to spikes and seizures for the<br>purpose of reviewing EEG recording. This application is for<br>use by trained users such as neurologists, clinicians,<br>registered EEG technicians. It requires EEG data recorded<br>with a standard montage using the 10/20 electrode<br>placement. The detected events are annotated on the EEG<br>record for review by a trained user. | |
| Indications for Use: | Cadwell Spike and Seizure Detector is a software-only<br>product with an algorithm intended to analyze and mark<br>events that may correspond to epileptiform discharge | |
(spike) and electrographic seizure for the purpose of reviewing scalp EEG recordings. The marked events are reviewed, deleted, and interpreted by qualified clinical
{1}------------------------------------------------
Image /page/1/Picture/0 description: The image shows the logo for CADWELL along with the text "510k Summary". The CADWELL logo is on the left side of the image, and the text "510k Summary" is on the right side of the image. The text is in a larger font than the logo.
practitioners who will exercise professional judgment in using the information.
This device does not control the delivery of energy, administration of drugs, or another form of life sustaining function to the patient. It is intended for use in patients who are 18 years or over.
This device does not provide any diagnostic conclusion about the patient to the user.
#### Summary of technology characteristics:
| | Comparison | |
|-----------------------------------|-------------------------------------------------|-----------------------------|
| Key Attributes | Cadwell Spike and Seizure<br>Detector (K123927) | Persyst Reveal<br>(K011397) |
| Identifies spikes | Yes | Yes |
| Identifies seizures | Yes | Yes |
| Displays calculated EEG measures | No | No |
| User-adjustable seizure detection | No | Yes |
| Users can add/delete events | Yes | Yes |
| Type of EEG recording supported | Scalp EEG only | Unknown |
| Type of EEG analysis | Post-hoc only | Post-hoc only |
| Population age | Adult | Unknown |
| Product Code | OMB | GWS |
Table 1: Device Comparison Table
Substantial Equivalence: The Cadwell Spike and Seizure Detector is a software package that identifies spike and seizures in scalp EEG recordings. Persyst Reveal is commercially available software package that identifies spike and seizures in scalp EEG recordings and is an accepted standard in automated spike and seizure detection programs.
> The Cadwell Spike and Seizure Detector is substantially equivalent to the Persyst Revel in terms of:
- Indications for use t
- Technology characteristics .
- . Performance characteristics
Cadwell Spike and Seizure Detector 510k Summary Rev. 4
Page 2 of 6
{2}------------------------------------------------
### VELL 510k Summary
- . Testing results from clinical data
Validation:
76 records were selected from unique patients with the following inclusion criteria:
- Patient age 18 years or over on the date of recording ●
- . Full montage scalp EEG using the 10-20 montage was acquired
- . Total recording duration of minimum 6 hours
All recordings were acquired in an epilepsy monitoring unit as part of routine clinical protocol using the standard 10-20 montage. The patient age range for the selected recordings was 18-92 years with an average age of 48.2 years. The recording duration was in the range of 6-71 hours with an average of 24.6 hours.
Three human experts reviewed the complete raw EEG for each record and marked spike and seizure events. Majority rule (agreement between any two of three experts) using any overlap method was applied to construct the reference set.
The reference set for spike detector validation contained a total of 946 events. Figures 1 and 2 show the performance for each of the experts, Persyst Reveal and Cadwell Spike Detector.
{3}------------------------------------------------
## 510k Summary
Image /page/3/Figure/1 description: The image is a plot titled "Spike Detection Sensitivity". The plot shows the positive percent agreement and 95% confidence interval for different experts and systems. The x-axis ranges from 40% to 100%, and the y-axis lists the experts and systems: Expert 1, Expert 2, Expert 3, Persyst, and Cadwell.
Figure 1: Positive percent agreement and 95% confidence interval using bootstrap method.
Image /page/3/Figure/3 description: The image is a plot titled "False Detection Rate for Spike Detection". The x-axis is labeled "Negative Disagreement Rate and 95% Confidence Interval" and ranges from 0 to 300. There are 5 different experts/systems plotted on the y-axis: Expert 1, Expert 2, Expert 3, Persyst, and Cadwell. Each expert/system has a range of values plotted, with a diamond indicating the mean value.
Figure 2: Negative disagreement rate and 95% confidence interval using bootstrop method.
The reference set for seizure detector validation contained a total of 332 events. Figures 3 and 4 show the performance for each of the experts, Persyst Reveal and Cadwell Seizure Detector. «
Cadwell Spike and Seizure Detector 510k Summary Rev. 4
Page 4 of 6
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image shows the word "CADWELL" in a bold, sans-serif font. To the left of the word is a circle with a line going through it that resembles a heartbeat. The letters are all capitalized and black, and the background is white. The font is uniform in size and thickness.
## 510k Summary
Image /page/4/Figure/2 description: The image is a plot titled "Seizure Detection Sensitivity". The x-axis is labeled "Positive Percent Agreement and 95% Confidence Interval" and ranges from 40% to 100%. The y-axis shows the labels Expert 1, Expert 2, Expert 3, Persyst, and Cadwell. Each label has a line with a diamond in the middle, representing the range of values for each label.
Figure 3: Positive percent agreement and 95% confidence interval using bootstrap method.
Image /page/4/Figure/4 description: The image is a plot titled "False Detection Rate for Seizure Detection". The x-axis is labeled "Negative Disagreement Rate and 95% Confidence Interval" and ranges from 0 to 8. The y-axis shows the names of experts and systems, including Expert 1, Expert 2, Expert 3, Persyst, and Cadwell. Each expert and system has a horizontal line representing the disagreement rate and confidence interval.
Figure 4: Negative disagreement rate and 95% confidence interval using bootstrap method.
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the word "CADWELL" in a bold, sans-serif font. To the left of the word, there is a circular graphic with a waveform inside, resembling an EKG or heart rhythm tracing. The letters are closely spaced, creating a solid block of text.
Conclusion:
The validation results show that the Cadwell Spike and Seizure Detector meets the objective for device effectiveness and substantial equivalence.
510k Summary
| Test Criteria | Spike Detector | Seizure Detector |
|-------------------------|----------------|------------------|
| Device effectiveness | Pass | Pass |
| Substantial equivalence | Pass | Pass |
Table 2: Summary of the test results for the Cadwell Spike and Seizure Detector
{6}------------------------------------------------
Public Health Service
Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002
July 23, 2014
Cadwell Laboratories Jinesh Jain. Software Manager 909 N. Kellogg Street Kennewick, WA 99336
Re: K140552
Trade/Device Name: Cadwell Spike and Scizure Detector Software Regulation Number: 21 CFR 882.1400 Regulation Name: Electroencephalograph Regulatory Class: Class II Product Code: OMB Dated: June 9, 2014 Received: June 17. 2014
Dear Mr. Jain:
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 cither 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
Image /page/6/Picture/11 description: The image shows the seal of the Department of Health & Human Services (HHS). The seal features a stylized eagle with three lines representing its body and wings. The words "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" are arranged in a circular pattern around the eagle.
{7}------------------------------------------------
Page 2 - Jinesh Jain
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 contact the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address
http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (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/Resourcesfor You/Industry/default.htm.
Sincerely yours,
#### Felipe Aquel - S
for Carlos L. Peña, PhD, MS Director Division of Neurological and Physical Medicine Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{8}------------------------------------------------
#### DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration
#### Indications for Use
Form Approved: OMB No. 0910-0120 Expiration Date: January 31, 2017 See PRA Statement below.
510(k) Number (if known) K140552
Device Name Cadwell Spike and Seizure Detector
#### Indications for Use (Describe)
Cadwell Spike and Scizure Detector is a software-only product with an algorithm intended to analyze and mark evens that may correspond to epileptiform discharge (spike) and clectrographic seizure for the purpose of reviewing scale EFG recordings. The marked events are reviewed, deleted, and interpreted by qualified clinical practitioners who will exercise professional judgment in using the information.
This device does not control the delivery of energy, administration of drugs, or another form of life sustaining function to the patient. It is intended for use in patients who are 18 years or over.
This device does not provide any diagnostic conclusion about the patient to the user.
Type of Use (Select one or both, as applicable)
2 Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON A SEPARATE PAGE IF NEEDED.
#### FOR FDA USE ONLY
Concurrence of Center for Devices and Radiological Health (CDRH) (Signature)
# - Date: 2014.07.23 19:45:51
> -04'00'
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@Ida.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."
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.