K254198 · Trexo Robotics, Inc. · PHL · Sep 2, 2026 · Physical Medicine
Device Facts
Record ID
K254198
Device Name
Trexo Theo
Applicant
Trexo Robotics, Inc.
Product Code
PHL · Physical Medicine
Decision Date
Sep 2, 2026
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 890.3480
Device Class
Class 2
Attributes
Therapeutic, Real-World Evidence, Pediatric
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K254198 · Sep 2, 2026
Trexo Theo
Trexo Robotics, Inc.
Retrospective analysis of device-generated usage data (2019-2025); Published clinical literature
The retrospective study evaluated functional ambulation performance (total steps), device use patterns, and adverse event rates in 124 users with cerebral palsy across clinical and home settings. Published literature was used to support safety and functional mobility outcomes.
The Trexo Theo is a powered exoskeleton intended to perform ambulatory functions in patients 12 years and older with cerebral palsy. The Trexo Theo is intended to be used in a community setting under the supervision of a trained companion who has been certified to the companion training program prior to use of the device. The device is also intended to be used in a clinical setting under the supervision of a trained therapist who has been certified to the therapist training program prior to use of the device. The Trexo Theo is not intended for sports or stair climbing.
Device Story
Battery-powered, wearable lower-limb exoskeleton; assists gait in individuals with impaired walking. Worn over legs; used with rigid, four-wheeled, lockable walker frame for body-weight support and fall prevention. Controlled by trained operator via dedicated tablet connected via Wi-Fi; operator selects gait settings, initiates ambulation, adjusts speed. Real-time status/metrics displayed on tablet; visual LED indicators on device legs. Safety features: automatic cessation of actuation upon communication loss, safe stop on battery depletion, physical E-Stop button on battery box. In safe-stop, joints become non-actuated while walker/chest prompt maintains support. Used in clinical and community settings under supervision of certified therapist or companion. Benefits: enables repeatable overground stepping volumes and sustained stepping for patients with functional limitations.
Clinical Evidence
Retrospective analysis of real-world data (2019-2025) from 124 users (aged 12+, cerebral palsy). 70 home/community users, 54 clinical/rehabilitation school users. 77% GMFCS III-IV. Primary efficacy: total cumulative steps 21,669,731; median 710 steps/session (GMFCS III/IV median 1,253/1,198). Primary safety: 0% serious device-related AEs. AE rate 0.002 per 1,000 steps; reported events (19.4% of users) were minor (pain, skin abrasions, bruising). Literature review (n=1 to 171) supports consistent stepping volumes and functional mobility improvements.
Technological Characteristics
Battery-powered, wearable lower-limb exoskeleton. Provides powered assistance at hip and knee joints. Includes walker frame, chest prompt, saddle, and accessories. Connectivity: Wi-Fi for tablet control. Software: IEC 62304 compliant. Biocompatibility: ISO 10993-1. Electrical safety: IEC 60601-1, IEC 80601-2-78. EMC: IEC 60601-1-2. Battery: IEC 62133-2/UN 38.3. Ingress protection: IEC 60529.
Indications for Use
Indicated for patients 12 years and older with cerebral palsy to perform ambulatory functions. Not intended for sports or stair climbing.
Regulatory Classification
Identification
A powered lower extremity exoskeleton is a prescription device that is composed of an external, powered, motorized orthosis that is placed over a person's paralyzed or weakened limbs for medical purposes.
Special Controls
In combination with the general controls of the FD&C Act, the Powered Exoskeleton is subject to the following special controls:
*Classification.* Class II (special controls). The special controls for this device are:(1) Elements of the device materials that may contact the patient must be demonstrated to be biocompatible.
(2) Appropriate analysis/testing must validate electromagnetic compatibility/interference (EMC/EMI), electrical safety, thermal safety, mechanical safety, battery performance and safety, and wireless performance, if applicable.
(3) Appropriate software verification, validation, and hazard analysis must be performed.
(4) Design characteristics must ensure geometry and materials composition are consistent with intended use.
(5) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use. Performance testing must include:
(i) Mechanical bench testing (including durability testing) to demonstrate that the device will withstand forces, conditions, and environments encountered during use;
(ii) Simulated use testing (
*i.e.,* cyclic loading testing) to demonstrate performance of device commands and safeguard under worst case conditions and after durability testing;(iii) Verification and validation of manual override controls are necessary, if present;
(iv) The accuracy of device features and safeguards; and
(v) Device functionality in terms of flame retardant materials, liquid/particle ingress prevention, sensor and actuator performance, and motor performance.
(6) Clinical testing must demonstrate a reasonable assurance of safe and effective use and capture any adverse events observed during clinical use when used under the proposed conditions of use, which must include considerations for:
(i) Level of supervision necessary, and
(ii) Environment of use (
*e.g.,* indoors and/or outdoors) including obstacles and terrain representative of the intended use environment.(7) A training program must be included with sufficient educational elements so that upon completion of training program, the clinician, user, and companion can:
(i) Identify the safe environments for device use,
(ii) Use all safety features of device, and
(iii) Operate the device in simulated or actual use environments representative of indicated environments and use.
(8) Labeling for the Physician and User must include the following:
(i) Appropriate instructions, warning, cautions, limitations, and information related to the necessary safeguards of the device, including warning against activities and environments that may put the user at greater risk.
(ii) Specific instructions and the clinical training needed for the safe use of the device, which includes:
(A) Instructions on assembling the device in all available configurations;
(B) Instructions on fitting the patient;
(C) Instructions and explanations of all available programs and how to program the device;
(D) Instructions and explanation of all controls, input, and outputs;
(E) Instructions on all available modes or states of the device;
(F) Instructions on all safety features of the device; and
(G) Instructions for properly maintaining the device.
(iii) Information on the patient population for which the device has been demonstrated to have a reasonable assurance of safety and effectiveness.
(iv) Pertinent non-clinical testing information (
*e.g.,* EMC, battery longevity).(v) A detailed summary of the clinical testing including:
(A) Adverse events encountered under use conditions,
(B) Summary of study outcomes and endpoints, and
(C) Information pertinent to use of the device including the conditions under which the device was studied (
*e.g.,* level of supervision or assistance, and environment of use (*e.g.,* indoors and/or outdoors) including obstacles and terrain).
{0}
**U.S. FOOD & DRUG**
ADMINISTRATION
September 2, 2026
Trexo Robotics, Inc.
Linda Wu
Director of Regulatory, Quality and Clinical Affairs
6705 Milcreek Dr.
Unit 3
Mississauga, ON L5N 5M4
Canada
Re: K254198
Trade/Device Name: Trexo Theo
Regulation Number: 21 CFR 890.3480
Regulation Name: Powered Lower Extremity Exoskeleton
Regulatory Class: Class II
Product Code: PHL
Dated: July 31, 2026
Received: August 3, 2026
Dear Linda Wu:
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.
{1}
K254198 - Linda Wu
Page 2
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" (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-
{2}
K254198 - Linda Wu
Page 3
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).
Sincerely,
# Tushar Bansal -S
Tushar Bansal, PhD
Acting Assistant Director, Acute Injury Devices Team
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
{3}
| Indications for Use | | |
| --- | --- | --- |
| Please type in the marketing application/submission number, if it is known. This textbox will be left blank for original applications/submissions. | K254198 | ? |
| Please provide the device trade name(s). | | ? |
| Trexo Theo | | |
| Please provide your Indications for Use below. | | ? |
| The Trexo Theo is a powered exoskeleton intended to perform ambulatory functions in patients 12 years and older with cerebral palsy. The Trexo Theo is intended to be used in a community setting under the supervision of a trained companion who has been certified to the companion training program prior to use of the device. The device is also intended to be used in a clinical setting under the supervision of a trained therapist who has been certified to the therapist training program prior to use of the device. The Trexo Theo is not intended for sports or stair climbing. | | |
| Please select the types of uses (select one or both, as applicable). | ☑ Prescription Use (21 CFR 801 Subpart D) ☐ Over-The-Counter Use (21 CFR 801 Subpart C) | ? |
{4}
510k Summary
Trexo Robotics
# 510(k) Summary
# K254198
# 1. Submitter Information
| Company Name | Trexo Robotics |
| --- | --- |
| Company Address | 6705 Millcreek Drive, Unit 3, Mississauga, L5N 5M4 |
| Company Phone | 1 844-844-0607 |
| Contact Person | Linda Wu (Director of Regulatory, Quality and Clinical) |
| Date Prepared | August 28, 2026 |
# 2. Device Information
| Device Trade Name | Trexo Theo |
| --- | --- |
| Device Common Name | Powered Exoskeleton |
| Device Classification | Powered lower extremity exoskeleton |
| Product Code | PHL |
| Classification Panel | Neurology/Physical Medicine (OHT5) |
| Class | 2 |
| Regulation Number | 21 CFR 890.3480 |
# 3. Predicate Devices
| Name | Manufacturer | 510(k) |
| --- | --- | --- |
| Medical HAL Lower Limb Type (HAL-ML) | Cyberdyne Inc. | K233695 |
| Rewalk P6.0 | Rewalk Robotics Ltd. | K221696 |
# 4. Indications for Use Statement
The Trexo Theo is a powered exoskeleton intended to perform ambulatory functions in patients 12 years and older with cerebral palsy.
The Trexo Theo is intended to be used in a community setting under the supervision of a trained companion who has been certified to the companion training program prior to use of the device. The device is also intended to be used in a clinical setting under the supervision of a trained therapist who has been certified to the therapist training program prior to use of the device.
The Trexo Theo is not intended for sports or stair climbing.
# 5. Device Description
The Trexo Theo (herein referred to as 'Trexo') is a battery-powered, wearable lower-limb exoskeleton intended to assist gait in individuals with impaired walking. The device is worn over the legs and is used with a rigid, four-wheeled, lockable walker frame that provides body-weight support and fall-prevention during use. The device is controlled by a trained operator through a dedicated Trexo tablet connected via the device Wi-Fi network, where they can select gait settings, initiate ambulation,
Confidential
(Page 1 of 5)
{5}
510k Summary
Trexo Robotics
and adjust speed. Real-time device status and performance metrics are displayed on the tablet, and visual LED indicators on the device legs communicate operating state. The device incorporates multiple safety features including: automatic cessation of actuation if tablet-to-device communications are lost, safe stop upon battery depletion, and a physical Emergency Stop (E-Stop) button on the battery box that removes power to the actuators. In safe-stop states, joints become non-actuated while the walker and chest prompt continues supporting the user. The device is provided in multiple sizes with size-specific hip and knee torque ceilings and configurable assistance levels appropriate for the indicated population. The device includes accessories such as footplates, shin/thigh cuffs, a chest prompt, saddle, contracture blocks, headrest, arm prompts, steering guide rod, and the Trexo Treadmill.
## 6. Comparison to Predicate Devices
### a. Indications for Use
The subject device is a powered lower-limb exoskeleton intended to perform ambulatory functions in individuals with cerebral palsy who are 12 years and up, under supervision in both clinic and community environments. The primary predicate, HAL-ML, is a powered exoskeleton indicated for improved ambulation in individuals with neuromuscular conditions including cerebral palsy, in rehabilitation and clinical environments under trained supervision. The Trexo device is indicated for use in a subset of the patient population cleared for HAL-ML and supports similar ambulatory functions, including standing and level-ground walking. The secondary predicate, Rewalk, is a powered exoskeleton indicated to perform ambulatory functions in home and community environments under supervision of trained companions. The Trexo device similarly supports supervised assisted ambulation outside of clinical environments. Across the subject and predicate devices, the indications of use are limited to powered assistance for ambulation. Trexo has submitted clinical data to support the safety and effectiveness of the device used in the different intended settings.
### b. Technological Comparison
Trexo and the predicate devices are battery-powered, lower-limb exoskeletons intended to provide assistance for ambulation by generating lower-extremity joint motion through motorized actuation. All devices are used under supervision consistent with their labeled environments of use.
Overall configuration and assisted joints: Trexo is a wearable lower-limb exoskeleton worn over the legs. The device provides powered assistance at the hip and knee joints. HAL-ML and Rewalk are similarly wearable lower-limb exoskeletons that provide powered assistance through actuated hip and knee joints.
User support and stability method: Trexo is used with a rigid, four-wheeled, lockable walker frame that provides external support during use. HAL-ML is designed for use with a body-weight support system and Rewalk is designed for use with crutches to assist with balance during ambulation. These differences reflect different support configurations while maintaining the same fundamental technological approach of powered assistance to lower-limb actuation.
Control and User Interface: Trexo is controlled by a trained operator using a dedicated Trexo tablet connected through the device WI-Fi network to select gait settings, initiate ambulation, and adjust speed. Device operating status is communicated via the tablet interface and device indicators. HAL-ML and Rewalk utilize different control approaches and user interfaces consistent
Confidential
(Page 2 of 5)
{6}
510k Summary
Trexo Robotics
with their cleared configurations; however, all devices include controls to initiate, adjust, and stop assisted ambulation.
Safety-related design features: Trexo incorporates safety features including a communication-loss response (automatic cessation of actuation upon loss of tablet-to-device communications), a safe stop upon battery depletion, and a physical Emergency Stop button that removes power to the actuators. In safe-stop states, joint actuation is disabled while external support is maintained through the walker frame. The predicate device similarly incorporates safety related controls intended to support controlled stopping and system power interruption consistent with their cleared designs.
Sizing and configurable assistance: The Trexo is provided in multiple sizes and includes size-specific hip and knee torque limits, configurable assistance levels, and adjustable joint range-of-motion (ROM) settings appropriate for the indicated user population. Predicate devices are also available in configured sizes and/or adjustable settings consistent with their cleared and labeled use.
Trexo configurable accessories: The configurable accessories such as footplates, shin/thigh cuffs, a chest prompt, saddle, contracture blocks, headrest, arm prompts, and steering guide rod serve positioning, comfort, and patient-specific fitting functions analogous to the strapping and adjustable elements of the predicate devices. The Trexo device can be loaded onto an optional Trexo treadmill (not available from predicate), for stationary walking. The treadmill is entirely passive, containing no motor, electrical components, or battery connections. Performance testing on the treadmill and other configurable accessories have been conducted to confirm safe and effective performance.
To conclude, Trexo conforms to all core performance testing standards used for the predicate device. Bench testing and clinical data demonstrate stable closed-loop behaviour and operating limits. Therefore the technological differences do not raise new questions regarding safety and effectiveness of the device.
### 7. Non-Clinical Performance Testing
The following testing was conducted to evaluate that the device meets its specifications:
- Electrical safety and essential performance (IEC 60601-1 and applicable collateral/particular standards) including:
- Medical robots for Rehabilitation IEC 80601-2-78
- Usability and Human Factors per IEC 60601-1-6, IEC 62366-1/-2 and FDA guidance
- Home Healthcare Testing per IEC 60601-1-11
- Battery safety and transport (IEC 62133-2 / UN 38.3)
- Ingress protection (IEC 60529)
- Electromagnetic compatibility/immunity (EMC/EMI) (IEC 60601-1-2) including:
- Performance Evaluation per IEC 60601-4-2
- Common Emitters (5G, RFID, WPT, EAS/Metal Detectors)
- Software verification and validation under IEC 62304
- Biocompatibility per ISO 10993-1 and FDA guidance
- Packaging validation per ISTA 3A
- Wireless coexistence per ANSI C63.27
- Cybersecurity assessment consistent with FDA guidance
Confidential
(Page 3 of 5)
{7}
510k Summary
Trexo Robotics
• Other Trexo internal performance testing. Most Notably:
o Endurance Testing
o Torque Accuracy Testing
o Performance Testing
o Battery Testing
o Joint Position Accuracy Testing
All planned non-clinical testing were successfully completed and passed against predefined acceptance criteria. These results demonstrate that the Trexo device performs safely and as intended and does not raise new questions of safety or effectiveness compared to the predicate devices.
### 8. Clinical Data Summary
Clinical performance data were relied upon to support substantial equivalence and to address the special controls for powered lower-body exoskeletons.
# Trexo real-world evidence study
The multi-site real world evidence study evaluating Trexo use in the intended population directly assessed functional ambulation performance, device use patterns, and adverse event rates in the indicated population and settings. The device was clinically evaluated to assess safety and functional performance when used by patients aged 12 years and older with cerebral palsy (CP). The evaluation was based on a retrospective analysis of real-world use data collected on the device from 2019 to 2025 from both clinical and home/community settings.
All trexo-assisted walking sessions were conducted by trained operators under defined supervision requirements. The device was used in indoor and outdoor environments, including clinical rehabilitation settings, schools, community locations, and homes. Use occurred on common walking surfaces like the Trexo treadmill, common clinic and household flooring (e.g. tile, hardwood, carpet), and outdoor paved surfaces (e.g. concrete and paving stone). A total of 124 users were included in the study - 70 users used the device in their home/community and the remaining used it in clinical rehabilitation centers or rehabilitation schools. More than 77% were GMFCS Levels III - IV and 24% were unable to walk or initiate steps independently at baseline.
The primary study efficacy endpoint was total steps taken during Trexo walking sessions, used as an objective measure of stepping activity enabled by the device. Results indicated that total cumulative steps taken by all users were 21,669,731 with a median steps per user per session being 710, with GMFCS III and IV users having the highest median step counts of 1,253 and 1,198, respectively. This highlights the device's capacity to support consistent gait practice even among individuals with substantial functional limitations. The primary study safety endpoint was incidence of AEs. There were no (0%) reported device-related serious adverse events in the study. When normalized to exposure, the AE rate was remarkably low, at 0.002 per 1,000 steps overall. 19.4% of users reported that they did experience some adverse event during their device usage period (median usage duration was 126 weeks and 20 weeks for home/community and clinic/rehabilitation school users, respectively), but all were expected of exoskeleton use, including pain, discomfort, redness, bruising, skin abrasions/lesions, blisters, and minor static shock. Notably all reported events were classified as having either negligible or minimal severity of harm. There were no reported AEs related to sprains/strains, fracture, joint dislocation, head/neck injury, or cardiovascular issues. There were no unexpected adverse events reported.
Confidential
(Page 4 of 5)
{8}
510k Summary
Trexo Robotics
# Published literature
Numerous articles were identified reporting outcomes in patients with cerebral palsy using the Trexo device, including a study with validated 6MWT endpoints. The sample size range of the studies are n=1 to n=171. Studies were conducted in both supervised clinical rehabilitation settings and in supervised home settings consistent with the indications for use. No serious or unexpected device-related adverse events were reported. Published literature consistently demonstrated successful Trexo-assisted stepping and improvements or favourable trends in functional ambulation measures. Reported outcomes show that Trexo use enables repeatable overground stepping volumes per session and sustained stepping over longitudinal home/community use, with associated improvements in functional mobility.
# 9. Conclusions
Subject and predicate devices share the same intended use and fundamental scientific technology, including principles of operation and mechanism of action. Differences in design and technological characteristics between the subject and predicate devices do not raise any new types of questions of safety and effectiveness. The results of performance testing support substantial equivalence of the subject device with its predicate devices.
Confidential
(Page 5 of 5)
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:
Guidance alerts
New and changed FDA guidance documents, emailed as a daily digest.
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 ? 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 as a Medical Device, 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 as a Medical Device), 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.