K222101 · Graymatters Health , Ltd. · HCC · Mar 17, 2023 · Neurology
Device Facts
Record ID
K222101
Device Name
Prism
Applicant
Graymatters Health , Ltd.
Product Code
HCC · Neurology
Decision Date
Mar 17, 2023
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 882.5050
Device Class
Class 2
Attributes
Software as a Medical Device, Therapeutic
Indications for Use
Prism is a neurofeedback software device intended for relaxation and stress reduction through the use of EEG biofeedback. The device is indicated as an adjunctive treatment of symptoms associated with posttraumatic stress disorder (PTSD), to be used under the direction of a healthcare professional, together with other pharmacological and/or non-pharmacological interventions.
Device Story
Prism is a neurofeedback software device for PTSD symptom management. It operates by receiving real-time EEG signal inputs from an external, FDA-cleared EEG headset (g.Nautilus PRO). The software processes these EEG signals to generate interactive audio/visual feedback displayed on a laptop. Patients use this feedback to learn mental strategies for regulating their brain activity, aiming for relaxation and stress reduction. Therapy consists of 15 sessions (30 minutes each), typically twice weekly. The device is used in clinical settings under the direction of a healthcare professional. By providing real-time biofeedback, the device assists patients in developing self-regulation skills, which may lead to a reduction in PTSD-related symptoms. It does not provide diagnostic conclusions or clinical interpretations.
Clinical Evidence
Prospective, single-arm, open-label study (n=79) evaluated safety and effectiveness of 15 Prism sessions in chronic PTSD patients. Primary endpoint: proportion of subjects with ≥6-point reduction in CAPS-5 score from baseline to 3-month follow-up. Results: 66.67% of subjects met the primary endpoint at 3 months. Secondary endpoints included PCL-5, PHQ-9, and CGI scores. Safety profile was acceptable; 2.53% SAE rate (none device-related); 50.6% reported mild AEs (headache, fatigue).
Technological Characteristics
Software-only device; runs on laptop; interfaces with external EEG headset (g.Nautilus PRO). EEG input: 8-16 channels, 250 Hz sampling rate, 0-60 Hz bandwidth. Biofeedback principle: visual/auditory signal processing. Software developed per IEC 62304. No diagnostic or classification algorithms.
Indications for Use
Indicated for patients (ages 22-65) with chronic PTSD (1-20 years post-trauma) as an adjunctive treatment for symptom reduction under professional supervision.
Regulatory Classification
Identification
A biofeedback device is an instrument that provides a visual or auditory signal corresponding to the status of one or more of a patient's physiological parameters (e.g., brain alpha wave activity, muscle activity, skin temperature, etc.) so that the patient can control voluntarily these physiological parameters.
Special Controls
*Classification.* Class II (special controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter when it is a prescription battery powered device that is indicated for relaxation training and muscle reeducation and prescription use, subject to § 882.9.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
March 17, 2023
GrayMatters Health Ltd. % Allison Komiyama, PhD Principal Consultant ROM+ 2251 San Diego Ave, Suite B-257 San Diego, California 92110
Re: K222101
Trade/Device Name: Prism Regulation Number: 21 CFR 882.5050 Regulation Name: Biofeedback device Regulatory Class: Class II Product Code: HCC Dated: February 13, 2023 Received: February 14, 2023
Dear Dr. Komiyama:
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. 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 located 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.
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
{1}------------------------------------------------
requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/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-device-advice-comprehensive-regulatoryassistance/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).
Sincerely,
# Pamela D. Scott -S
Pamela Scott Assistant Director DHT5B: Division of Neuromodulation and Physical Medicine Devices OHT5: Office of Neurological and Physical Medicine Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
## Indications for Use
510(k) Number (if known) K222101
Device Name Prism
Indications for Use (Describe)
Prism is a neurofeedback software device intended for relaxation and stress reduction through the use of EEG biofeedback. The device is indicated as an adjunctive treatment of symptoms associated with posttraumatic stress disorder (PTSD), to be used under the direction of a healthcare professional, together with other pharmacological and/or non-pharmacological interventions.
| Type of Use (Select one or both, as applicable) | |
|-----------------------------------------------------------------------------------|----------------------------------------------------------------------------------|
| <div> <span> ☑ Prescription Use (Part 21 CFR 801 Subpart D) </span> </div> | <div> <span> ☐ Over-The-Counter Use (21 CFR 801 Subpart C) </span> </div> |
#### CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
#### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
Image /page/3/Picture/0 description: The image shows the logo for Gray Matters Health. The logo features a stylized, three-dimensional geometric shape in blue, resembling a maze or a brain structure. A small portion of the shape is colored in red, adding a pop of contrast. Below the geometric shape, the text "GrayMatters Health" is written in a simple, sans-serif font, with "GrayMatters" on the top line and "Health" on the bottom line.
## 510(k) Summary K222101
#### DATE PREPARED
March 16, 2023
#### MANUFACTURER AND 510(k) OWNER
GrayMatters 82 Ha' Atzmaut Street, Haifa, Israel Telephone: Official Contact: Adar Shani, VP Clinical and Regulatory affairs
#### REPRESENTATIVE/CONSULTANT
Allison C. Komiyama, Ph.D., RAC Pierre Bounaud, Ph.D. Matthieu Kirkland, M.S. RQM+ Telephone: +1 (412) 816-8253 Email: akomiyama@rqmplus.com
#### DEVICE INFORMATION
| Proprietary Name/Trade Name: | Prism |
|------------------------------|-------------------------------------------------------|
| Common Name: | Device, Biofeedback |
| Regulation Number: | 21 CFR 882.5050 |
| Class: | Class 2 |
| Product Code: | HCC |
| Premarket Review: | Neurological and Physical Medicine Devices (OHT5) |
| | Neuromodulation and Physical Medicine Devices (DHT5B) |
| Review Panel: | Neurology |
#### PREDICATE DEVICE IDENTIFICATION
Prism is substantially equivalent to the following predicates:
| 510(k) Number | Predicate Device Name / Manufacturer | Predicate |
|---------------|---------------------------------------------|---------------------|
| K122879 | EEGer4 / EEG Software LLC. | Primary Predicate |
| K180173 | Freespira / Palo Alto Health Sciences, Inc. | Secondary Predicate |
The predicate devices have not been subject to a design related recall.
#### DEVICE DESCRIPTION
Prism is a software as medical device, to be prescribed for treatment of patients with PTSD by clinicians as adjunct to standard of care. Prism is a software device running on a laptop that uses EEG signal input from an EEG device (g.Nautilos PRO (K171669)).
{4}------------------------------------------------
Prism therapy consists of 15, 30-minute sessions and optional periodic refresher sessions. During a session, the patient is connected to 8 or more EEG channels and views an interactive audio/visual interface.
#### INDICATIONS FOR USE
Prism is a neurofeedback software device intended for relaxation and stress reduction through the use of EEG biofeedback.
The device is indicated as an adjunctive treatment of symptoms associated with posttraumatic stress disorder (PTSD), to be used under the direction of a healthcare professional, together with other pharmacological and/or non-pharmacological interventions.
#### COMPARISON OF SUBSTANTIAL EQUIVALENCE
GrayMatters believes that Prism is substantially equivalent to the predicate devices based on the information summarized here:
The subject device has the same intended use and similar indications for use as the predicate devices. Both the subject and predicate devices utilize biofeedback technology based on visual and/or auditory signals to help patients regulate and voluntarily control their physiological parameters.
The subject device has the same technological characteristics as compared to the primary predicate device and the same intended use. Both the subject device and the primary predicate cleared in K122879 have the same principle of operation and train patients to find strategies to regulate their physiological parameters. The subject device and the primary predicate utilize the same energy input and output. Namely, both the subject device and primary predicate provide biofeedback training to patients supported by EEG data collected from an EEG device. Both devices use, measure, and process EEG signals to produce frequency band energy indications for biofeedback purposes.
Both the subject device and predicate devices do not provide any diagnostic conclusions nor provide any classification, diagnosis, or clinical interpretation of data. Finally, the subject device does not incorporate any changes in method of operation, material or design that could affect safety or effectiveness.
These technological characteristics have undergone testing to ensure the device is as safe and effective as the primary predicate. Based on the testing performed (i.e., software verification and validation, and clinical testing), it can be concluded that the subject device does not raise different questions of safety or effectiveness.
{5}------------------------------------------------
The similar indications for use, mode of operation (i.e., biofeedback device), and performance characteristics for the proposed Prism are assessed to be substantially equivalent to the predicate devices under product code HCC.
## SUMMARY OF NON-CLINICAL TESTING
Software Verification: The software development and testing were executed according to FDA's Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices and according to IEC 62304 Medical device software — Software life cycle processes.
The results of these tests indicate that Prism is substantially equivalent to the predicate device.
## SUMMARY OF CLINICAL TESTING
GrayMatters Health performed a prospective, single arm study, open label, unblinded study to assess of the Safety and Effectiveness of Prism, as an Adjunct to Standard of Care, in Subjects with Posttraumatic Stress Disorder (PTSD). The purpose of the study was to assess the safety and effectiveness of fifteen (15) EEG-Neurofeedback training sessions using the Prism software in reducing PTSD-related symptoms. Fifteen neurofeedback sessions were delivered twice per week, on non-consecutive days, over 8 consecutive weeks. Subjects (ages 22 to 65) had been diagnosed with PTSD from 1 year to 20 years after index trauma, (i.e., patients with Chronic PTSD). Diagnosis of PTSD was established according to the DSM-5 criteria and CAPS-5. The study was conducted at 4 outside the United States (OUS) sites in Israel and one US site.
The following activities were performed as part of the Baseline Assessment:
- . Clinician assessments performed and documented by the investigator or qualified and trained designee: CAPS-5, CGI-S
- Subjects instructed to complete all questionnaires on the ePRO system: PCL-5, ERQ, . PHQ-9
During the study, the subjects were provided with a short pre-training session during the baseline assessment visit or combined with the 1st Prism EEG-NF training to become familiar with the system operation prior to the actual Prism EEG-NF training sessions.
#### Device
Prism software processes EEG signals to provide visual feedback to the patient to aid the patient in learning to control the EEG activity. The EEG signal was provided by the g.Nautilus PRO EEG device.
## Primary Performance Measures
The primary measure of this study was to assess the proportion of subjects who demonstrate a 6-point reduction in the Clinician Administered PTSD Scale (CAPS-5) score from Baseline to the 3 months follow-up visit.
{6}------------------------------------------------
## Safety Performance Measures
The safety objectives of this study were to assess the safety of Prism Neurofeedback training by evaluating the incidence, severity, and frequency of adverse events.
## Secondary Performance Measures
- 1. Assess the proportion of subjects who demonstrate a 10-point reduction or more in the PTSD Checklist for DSM-5 (PCL-5).
- 2. Assess the change from Baseline to the 3 months follow-up in the following scores:
- a. Clinician Administered PTSD Scale (CAPS-5)
- b. PTSD Checklist for DSM-5 (PCL-5)
- Emotion Regulation Questionnaire (ERQ) C.
- Patient Health Questionnaire (PHQ-9) d.
- e. Clinical Global Impression (CGI)
## Analysis Set
There were 101 subjects screened for the study with 79 included in the full analysis dataset, 66 included in the efficacy analysis set, and 63 in the per protocol analysis set. The mean time from traumatic event in these subjects was 10 years and ranged between 1 and 20 years with the mean time from first PTSD symptoms being 8.8 years. The majority of the US and OUS patients reported military related PTSD symptoms.
## Primary Endpoint
The response rate, i.e., the percent of subjects (50%) with at least 6 points improvement in CAPS-5 from baseline to the 3 months follow up visit (primary effectiveness endpoint) as well as at 8 weeks (exploratory endpoint) was deemed to have been successfully met.
| Efficacy Analysis Set (EF) | Response (reduction ≥) | | | | |
|----------------------------|------------------------|-----------|-----------|-----------|-----------|
| | 6 points | 10 points | 13 points | 16 points | 21 points |
| 8 weeks | 69.70% | 50.00% | 45.45% | 33.33% | 22.73% |
| 3 months follow-up | 66.67% | 54.55% | 50.00% | 40.91% | 27.27% |
## Safety Conclusions
The serious adverse event (SAE) rate was 2.53% (2/79). None of the SAEs were considered related to the software or to the EEG device. While 50.6% (40/79) of the subjects experienced adverse events (AE's), the majority were mild AEs (headache, fatigue) and recovered right after the training sessions with no further intervention. The pre-specified safety goals of this study were met, and the safety profile was found to be acceptable.
{7}------------------------------------------------
## Study Conclusion
The primary endpoint of this study was responder rate based on a quantitative improvement as measured using the Clinician Administered PTSD Scale (CAPS-5). Using this scale, "Response" was defined as a reduction of 6 or more points. The primary effectiveness hypothesis was that from baseline to the 3 months follow-up, at least 50% of study participants will experience a response to the treatment (defined as a 6-point reduction in CAPS-5 score from baseline). From baseline to the 3-month follow-up, 54.55% of study participants experienced a reduction in the CAPS-5 of 10 points or more and 50% of study participants experienced a reduction of 13 points or more
The totality of the clinical data collected in the study demonstrates that Prism is substantially equivalent to the predicate device in terms of safety and effectiveness.
#### CONCLUSION
Based on the testing performed, including software verification and clinical testing, it can be concluded that the subject device does not raise different questions of safety or effectiveness compared to the predicate devices. The similar indications for use, technological characteristics, and performance characteristics for the proposed Prism are assessed to be substantially equivalent to the predicate devices.
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image shows the logo for GrayMatters Health. The logo features a blue geometric shape resembling a stylized brain or interconnected network, with a small red cube embedded within it. Below the logo, the text "GrayMatters Health" is written in a simple, sans-serif font, with "GrayMatters" on the first line and "Health" on the second.
| | Subject Device | Primary Predicate Device<br>Secondary Predicate Device | | Statement of Equivalence | |
|-----------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------|--|
| | GrayMatters Health Ltd. | EEG Software LLC | Palo Alto Health Sciences, Inc. | | |
| | Prism for PTSD | EEGer4<br>K122879 | Freespira<br>K180173 | | |
| Intended Use | Utilize biofeedback technology based on<br>visual and/or auditory signals to help<br>patients regulate and voluntarily control<br>their physiological parameters | Utilize biofeedback technology based on<br>visual and/or auditory signals to help<br>patients regulate and voluntarily control<br>their physiological parameters | Utilize biofeedback technology based on<br>visual and/or auditory signals to help<br>patients regulate and voluntarily control<br>their physiological parameters | Identical to the predicate devices. | |
| Indications for<br>Use | Prism is a neurofeedback software<br>device intended for relaxation and<br>stress reduction through the use of EEG<br>biofeedback. The device is indicated as<br>an adjunctive treatment of symptoms<br>associated with posttraumatic stress<br>disorder (PTSD), to be used under the<br>direction of a healthcare professional,<br>together with other pharmacological<br>and/or non-pharmacological<br>interventions. | This device is to be used for general<br>relaxation training when used with<br>supported amplifier/encoders. | Freespira is intended for use as a<br>relaxation treatment for the reduction of<br>stress by leading the user through guided<br>and monitored breathing exercises. The<br>device is indicated as an adjunctive<br>treatment of symptoms associated with<br>panic disorder (PD) and/or post-<br>traumatic stress disorder (PTSD), to be<br>used under the direction of a healthcare<br>professional, together with other<br>pharmacological and/or non-<br>pharmacological interventions. | Substantially equivalent to the predicate<br>devices. No impact on safety and<br>effectiveness. | |
| Product Codes<br>/ Regulation<br>Number | HCC / 21 CFR 882.5050 | HCC / 21 CFR 882.5050 | HCC / 21 CFR 882.5050<br>CCK / 21 CFR 868.1400 | Identical to the predicate devices. No<br>impact on safety and effectiveness. | |
| Class | Class 2 | Class 2 | Class 2 | Identical to the predicate devices. No<br>impact on safety and effectiveness. | |
| Regulation<br>Description | Device, Biofeedback | Device, Biofeedback | Device, Biofeedback | Identical to the predicate devices. No<br>impact on safety and effectiveness. | |
| Principle of<br>Operation | This system trains patients to find<br>mental strategies to regulate their<br>physiological parameters (e.g., brain<br>activity level) to reduce symptoms<br>associated with PTSD | This system trains patients to find mental<br>strategies to regulate their general<br>relaxation | This system trains patients to control and<br>normalize their physiological parameters<br>(e.g., breathing patterns) to reduce<br>symptoms associated with PTSD | Substantially equivalent to the predicate<br>devices. No impact on safety and<br>effectiveness. | |
| Intended User | Healthcare professional | Healthcare professional | Patient | Identical to the primary predicate device.<br>No impact on safety and effectiveness. | |
| Assessment<br>Mode for<br>Biofeedback | This is a software-only component that<br>receives EEG signals from the g.Nautilus<br>PRO EEG and processes those signals to<br>visual and audio feedback that are used<br>for biofeedback training. | This software-only component of an EEG<br>biofeedback system accepts EEG data<br>from an external FDA-approved<br>amplifier/encoder and provides<br>biofeedback information. | Respiratory information using<br>capnography | Identical to the primary predicate device.<br>No impact on safety and effectiveness. | |
| Supported<br>Devices | FDA-cleared medical-grade wearable<br>EEG headset to record brain activity in<br>medical and clinical environments. | FDA-cleared medical-grade wearable EEG<br>headsets to record brain activity in<br>medical and clinical environments. | N/A | Identical to the primary predicate device.<br>No impact on safety and effectiveness. | |
| Number of<br>EEG Channels | 8 - 16 | 4 | N/A | Substantially equivalent to the primary<br>predicate device. No impact on safety and<br>effectiveness. | |
| Sampling Rate | 250 Hz | 256 Hz | N/A | Substantially equivalent to the primary<br>predicate device. No impact on safety and<br>effectiveness. | |
| Bandwidth | 0 – 60 Hz | 0 - 50 Hz | N/A | Substantially equivalent to the primary<br>predicate device. No impact on safety and<br>effectiveness. | |
{9}------------------------------------------------
Image /page/9/Picture/0 description: The image shows the logo for GrayMatters Health. The logo consists of a stylized cube shape in blue with a small red square inside. Below the logo, the words "GrayMatters Health" are written in a simple, sans-serif font, with "GrayMatters" in a larger font size than "Health".
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.