The Mint ACE Pump (Mint pump) is intended for the subcutaneous delivery of insulin for the management of diabetes mellitus in persons requiring insulin. The Mint pump is able to reliably and securely communicate with compatible, digitally connected devices, including automated insulin dosing software, to receive, execute, and confirm commands from these devices. The Mint ACE Pump is intended for the management of diabetes mellitus in people 6 years of age or older. The Mint pump is intended for single-person, home use and requires a prescription.
Device Story
Tubeless alternate controller enabled (ACE) insulin pump; adheres to body (arm, back, abdomen, thigh) via adhesive pad. Inputs: glucose readings from integrated third-party CGM; dosing commands from interoperable automated glycemic controller (iAGC) software. Operation: receives/executes commands via BLE; delivers U-100 rapid-acting insulin subcutaneously. Components: reusable controller (2-year life) and disposable sterile cartridge (3-day + 12-hour wear). Used in home environment by patients or caregivers. Output: automated insulin delivery; alerts/status via mobile app. Benefits: automated glycemic management; reduced manual dosing burden. Safety: includes occlusion detection; requires removal for imaging (MRI/CT/X-ray) and laser surgery.
Clinical Evidence
No clinical trial data provided. Evidence consists of bench testing: basal/bolus delivery accuracy (n=29 pumps, including aged units), occlusion detection, wireless coexistence (ANSI/IEEE C63.27), biocompatibility (ISO 10993-1), and human factors validation (n=diverse user groups including pediatric, seniors, and AID-naïve/experienced users).
Technological Characteristics
Tubeless ACE pump; non-rechargeable battery. Materials: adhesive patch, disposable cartridge. Connectivity: BLE for CGM/iAGC/mobile app integration. Sterilization: Ethylene oxide. Software: IEC 62304 compliant. Standards: IEC 60601-1 (safety), IEC 60601-1-2 (EMC), ISO 10993 (biocompatibility), ISO 14971 (risk management).
Indications for Use
Indicated for management of diabetes mellitus in persons 6 years of age or older requiring subcutaneous insulin delivery. Intended for single-person, home use by prescription.
Regulatory Classification
Identification
An alternate controller enabled infusion pump (ACE pump) is a device intended for the infusion of drugs into a patient. The ACE pump may include basal and bolus drug delivery at set or variable rates. ACE pumps are designed to reliably and securely communicate with external devices, such as automated drug dosing systems, to allow drug delivery commands to be received, executed, and confirmed. ACE pumps are intended to be used both alone and in conjunction with digitally connected medical devices for the purpose of drug delivery.
Special Controls
Alternate controller enabled infusion pumps must comply with the following special controls:
*Classification.* Class II (special controls). The special controls for this device are:(1) Design verification and validation must include the following:
(i) Evidence demonstrating that device infusion delivery accuracy conforms to defined user needs and intended uses and is validated to support safe use under actual use conditions.
(A) Design input requirements must include delivery accuracy specifications under reasonably foreseeable use conditions, including ambient temperature changes, pressure changes (
*e.g.,* head-height, backpressure, atmospheric), and, as appropriate, different drug fluidic properties.(B) Test results must demonstrate that the device meets the design input requirements for delivery accuracy under use conditions for the programmable range of delivery rates and volumes. Testing shall be conducted with a statistically valid number of devices to account for variation between devices.
(ii) Validation testing results demonstrating the ability of the pump to detect relevant hazards associated with drug delivery and the route of administration (
*e.g.,* occlusions, air in line, etc.) within a clinically relevant timeframe across the range of programmable drug delivery rates and volumes. Hazard detection must be appropriate for the intended use of the device and testing must validate appropriate performance under the conditions of use for the device.(iii) Validation testing results demonstrating compatibility with drugs that may be used with the pump based on its labeling. Testing must include assessment of drug stability under reasonably foreseeable use conditions that may affect drug stability (
*e.g.,* temperature, light exposure, or other factors as needed).(iv) The device parts that directly or indirectly contact the patient must be demonstrated to be biocompatible. This shall include chemical and particulate characterization on the final, finished, fluid contacting device components demonstrating that risk of harm from device-related residues is reasonably low.
(v) Evidence verifying and validating that the device is reliable over the ACE pump use life, as specified in the design file, in terms of all device functions and in terms of pump performance.
(vi) The device must be designed and tested for electrical safety, electromagnetic compatibility, and radio frequency wireless safety and availability consistent with patient safety requirements in the intended use environment.
(vii) For any device that is capable of delivering more than one drug, the risk of cross-channeling drugs must be adequately mitigated.
(viii) For any devices intended for multiple patient use, testing must demonstrate validation of reprocessing procedures and include verification that the device meets all functional and performance requirements after reprocessing.
(2) Design verification and validation activities must include appropriate design inputs and design outputs that are essential for the proper functioning of the device that have been documented and include the following:
(i) Risk control measures shall be implemented to address device system hazards and the design decisions related to how the risk control measures impact essential performance shall be documented.
(ii) A traceability analysis demonstrating that all hazards are adequately controlled and that all controls have been validated in the final device design.
(3) The device shall include validated interface specifications for digitally connected devices. These interface specifications shall, at a minimum, provide for the following:
(i) Secure authentication (pairing) to external devices.
(ii) Secure, accurate, and reliable means of data transmission between the pump and connected devices.
(iii) Sharing of necessary state information between the pump and any digitally connected alternate controllers (
*e.g.,* battery level, reservoir level, pump status, error conditions).(iv) Ensuring that the pump continues to operate safely when data is received in a manner outside the bounds of the parameters specified.
(v) A detailed process and procedure for sharing the pump interface specification with digitally connected devices and for validating the correct implementation of that protocol.
(4) The device must include appropriate measures to ensure that safe therapy is maintained when communications with digitally connected alternate controller devices is interrupted, lost, or re-established after an interruption (
*e.g.,* reverting to a pre-programmed, safe drug delivery rate). Validation testing results must demonstrate that critical events that occur during a loss of communications (*e.g.,* commands, device malfunctions, occlusions, etc.) are handled appropriately during and after the interruption.(5) The device design must ensure that a record of critical events is stored and accessible for an adequate period to allow for auditing of communications between digitally connected devices and to facilitate the sharing of pertinent information with the responsible parties for those connected devices. Critical events to be stored by the system must, at a minimum, include:
(i) A record of all drug delivery
(ii) Commands issued to the pump and pump confirmations
(iii) Device malfunctions
(iv) Alarms and alerts and associated acknowledgements
(v) Connectivity events (
*e.g.,* establishment or loss of communications)(6) Design verification and validation must include results obtained through a human factors study that demonstrates that an intended user can safely use the device for its intended use.
(7) Device labeling must include the following:
(i) A prominent statement identifying the drugs that are compatible with the device, including the identity and concentration of those drugs as appropriate.
(ii) A description of the minimum and maximum basal rates, minimum and maximum bolus volumes, and the increment size for basal and bolus delivery, or other similarly applicable information about drug delivery parameters.
(iii) A description of the pump accuracy at minimum, intermediate, and maximum bolus delivery volumes and the method(s) used to establish bolus delivery accuracy. For each bolus volume, pump accuracy shall be described in terms of the number of bolus doses measured to be within a given range as compared to the commanded volume. An acceptable accuracy description (depending on the drug delivered and bolus volume) may be provided as follows for each bolus volume tested, as applicable: Number of bolus doses with volume that is <25 percent, 25 percent to <75 percent, 75 percent to <95 percent, 95 percent to <105 percent, 105 percent to <125 percent, 125 percent to <175 percent, 175 to 250 percent, and >250 percent of the commanded amount.
(iv) A description of the pump accuracy at minimum, intermediate, and maximum basal delivery rates and the method(s) used to establish basal delivery accuracy. For each basal rate, pump accuracy shall be described in terms of the amount of drug delivered after the basal delivery was first commanded, without a warmup period, up to various time points. The information provided must include typical pump performance, as well as worst-case pump performance observed during testing in terms of both over-delivery and under-delivery. An acceptable accuracy description (depending on the drug delivered) may be provided as follows, as applicable: The total volume delivered 1 hour, 6 hours, and 12 hours after starting delivery for a typical pump tested, as well as for the pump that delivered the least and the pump that delivered the most at each time point.
(v) A description of delivery hazard alarm performance, as applicable. For occlusion alarms, performance shall be reported at minimum, intermediate, and maximum delivery rates and volumes. This description must include the specification for the longest time period that may elapse before an occlusion alarm is triggered under each delivery condition, as well as the typical results observed during performance testing of the pumps.
(vi) For wireless connection enabled devices, a description of the wireless quality of service required for proper use of the device.
(vii) For any infusion pumps intended for multiple patient reuse, instructions for safely reprocessing the device between uses.
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
# I Background Information:
A 510(k) Number
K260001
B Applicant
Beta Bionics, Inc.
C Proprietary and Established Names
Mint ACE Pump
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QFG | 880.5730 | Alternate controller enabled infusion pump | CH – Clinical Chemistry |
# E Purpose for Submission:
- New device
- Establish a Predetermined Change Control Plan (PCCP)
# II Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The Mint ACE Pump (Mint pump) is intended for the subcutaneous delivery of insulin for the management of diabetes mellitus in persons requiring insulin. The Mint pump is able to reliably and securely communicate with compatible, digitally connected devices, including automated insulin dosing software, to receive, execute, and confirm commands from these devices. The Mint ACE Pump is intended for the management of diabetes mellitus in people 6 years of age or older. The Mint pump is intended for single-person, home use and requires a prescription.
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
### **C Special Conditions for Use Statement(s):**
- • Rx – For Prescription Use Only
- • Always check your glucose frequently during amusement park rides and flying or other situations where sudden changes or extremes of air pressure, altitude, or gravity may be occurring. Though the Mint System is safe to use at atmospheric pressures typically found in airplane cabins during flight, the atmospheric pressure in an airplane cabin can change during flight, which may affect the Mint pump's insulin delivery. Rapid changes in altitude and gravity, such as those typically found on amusement park rides or flight take-off and landing, can affect insulin delivery, leading to possible hypoglycemia or injury. If needed, follow your healthcare provider's treatment instructions.
- • Do not expose your Mint System to X-ray (screening at airports or other facilities and procedures), Computed Tomography (CT) scan, Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET) scan, diathermy treatment procedures, or to equipment used in procedures for Pacemaker / Automatic Implantable Cardioverter Defibrillator (AICD) placement or reprogramming, Cardiac Catheterization, or Nuclear Stress Test. Exposure of the Mint pump to any of these may damage it. Remove the Mint pump before undergoing these procedures.
- • Do not use a Mint pump if you are sensitive to or have allergies to acrylic adhesives or have fragile or easily damaged skin. Applying a Mint pump under these circumstances could cause skin irritation, damage or infection.
- • Remove your Mint System prior to any laser surgery as some lasers can create interference and cause your system to alert you.
### **III Device Description**
The Mint ACE Pump (Mint pump) is a tubeless alternate controller enabled (ACE) Pump intended to automatically deliver insulin under the skin based on input from an integrated third party continuous glucose monitor (CGM) and an interoperable automated glycemic controller (iAGC) cleared under K262763 in people 6 years of age or older with diabetes mellitus.
The Mint is adhered to the user on the back of the arm, the lower back, the abdomen, the thigh area, or any site that has a layer of fatty tissue available. It is held in place by an adhesive pad and provides 3 days + 12-hour grace period of insulin delivery before insulin delivery is stopped automatically.
The Mint ACE pump consists of two components a controller and a cartridge: Mint Controller that is supplied non-sterile with a useful life of 2 years and interfaces with the iLet Dosing Decision Software that is pre-installed on the Mint controller. The Mint Controller collects glucose readings from a CGM every 5 minutes. The Mint cartridge is a disposable wearable component that is supplied sterile and can be filled with up to 200 Units of compatible U-100 rapid acting insulin. The Mint cartridge is intended to be used for a 3-day insulin delivery period plus a 12-hour grace period, after which insulin delivery stops automatically. The Mint pump is powered by a non-rechargeable battery in the disposable wearable component.
K260001 - Page 2 of 8
{2}
# IV Substantial Equivalence Information:
# A Predicate Device Name(s):
Omnipod 5 ACE Pump
# B Predicate 510(k) Number(s):
K231826
# C Comparison with Predicate(s):
| Device & Predicate Device(s): | K260001 | K231826 |
| --- | --- | --- |
| Device Trade Name | Mint ACE Pump | Omnipod 5 ACE Pump |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | Intended for the subcutaneous delivery of insulin for the management of diabetes mellitus in persons requiring insulin. | Same |
| General Device Characteristic Differences | | |
| Intended patient population | For the management of diabetes mellitus in persons 6 years and older. | For the management of diabetes mellitus in persons 2 years and older. |
| Compatible insulins | U-100 rapid-acting insulin Novolog® and interchangeable biosimilar KIRSTY | U-100 rapid-acting insulin used for both basal and bolus doses: Novolog®, Humalog® and Admelog® |
| App host device | User's compatible mobile smartphone (Android or iPhone) with iLet App installed. | Omnipod 5 Locked Down Android Controller or user's compatible mobile smartphone (Android or iPhone) with Omnipod 5 App installed. |
K260001 - Page 3 of 8
{3}
| Flow Rates and Profiles | Basal: 0.1 to 15 units/hr Bolus 0.1 to 30 units | Basal: 0.05 - 30 units/hour Bolus: 0.05 - 30 units |
| --- | --- | --- |
| Maximum Bolus Flow Rate | 8 units per minute | 1.5 units per minute |
# **Predetermined Change Control Plan (PCCP):**
In addition to the similarities and differences between the candidate and predicate devices, the candidate device has an authorized Predetermined Change Control Plan (PCCP) to allow for future modifications to the Mint ACE Pump. These modifications include addition of compatibility with U-100 Humalog (insulin lispro) and Fiasp (insulin aspart) insulins; and modification of the adhesive patch material, including the non-woven layer, skin-side adhesive, and device-side attachment method. Each modification is supported by a pre-specified Modification Protocol with defined acceptance criteria, including insulin compatibility testing (in-use stability, compatibility, and preservative efficacy against USP Monograph requirements) and adhesive patch bench testing (peel and bond retention forces) and biocompatibility testing (sensitization, irritation, and cytotoxicity per ISO 10993), with each modification released only after all predefined criteria are met. Upon successful completion, each modification will be implemented per Beta Bionics' QSR, including updates to labeling, risk management documentation, and Design History File (DHF), with ongoing monitoring through post-market surveillance.
# **V Standards/Guidance Documents Referenced:**
- ISO 14971:2019 – Medical devices: Application of risk management to medical devices
- IEC 62304 Ed. 1.1 2015-06 – Medical device software: Software life cycle processes
- IEC 60601-1 Ed. 3.2 2020-08 – Medical electrical equipment: General requirements for basic safety
- ANSI AAMI IEC 60601-1-2:2014 [Including AMD1:2021] – EMC Collateral Standard
- IEC 62366-1 Ed. 1.1 2020-06 – Application of usability engineering to medical devices
- ANSI AAMI ISO 10993-1:2018 – Biological evaluation of medical devices
- ISO 11607-1 and -2 Second Edition 2019-02 – Packaging for terminally sterilized medical devices
- ANSI AAMI ISO 11135:2014/A1:2018 – Sterilization: Ethylene oxide
- IEEE ANSI USEMCSC C63.27-2021 – Evaluation of Wireless Coexistence
- AAMI TIR69:2017/(R2020) – Risk management of RF wireless coexistence for medical devices
- ASTM D4169-22 – Performance Testing of Shipping Containers and Systems
- ASTM F1980-21 – Accelerated Aging of Sterile Barrier Systems
- FDA Guidance: Applying Human Factors and Usability Engineering to Medical Devices (2016)
K260001 - Page 4 of 8
{4}
- FDA Guidance: Cybersecurity in Medical Devices: Quality Management System Considerations and Content of Premarket Submissions (2026)
## VI Performance Characteristics:
### A. Non-Clinical Performance
#### 1. Basal Delivery Accuracy
To assess basal delivery accuracy, 29 Mint Pumps were tested by delivering at minimum, intermediate, and maximum basal rates (0.1, 1.0, and 10.0 units/hr). 14 of the 29 durable components for minimum, intermediate, and maximum basal had been aged to simulate two years of regular use. A combination of aged and unaged disposable cartridges was also used for this study. Water was used as a substitute for insulin.
The following tables report the typical basal performance (median) observed, along with the lowest and highest results observed for the low, medium, and high basal rate settings for all pumps tested with no warmup period. For each time period, the tables show the volume of insulin requested in the first row and the volume that was delivered as measured by the scale in the second row.
Table 1: Amount of fluid delivered after 1, 6, and 12 hours with 0.1 U/hr (low) basal rate setting
| 0.1 U/hr Basal Duration | 1 hour | 6 hours | 12 hours |
| --- | --- | --- | --- |
| Total expected delivery volume | 0.1 U | 0.6 U | 1.2 U |
| Median amount delivered | 0.107 U | 0.636 U | 1.287 U |
| [min, max] | [0.000, 0.198] | [0.169, 0.914] | [0.492, 1.727] |
Table 2: Amount of fluid delivered after 1, 6, and 12 hours with 1 U/hr (medium) basal rate setting
| 1 U/hr Basal Duration | 1 hour | 6 hours | 12 hours |
| --- | --- | --- | --- |
| Total expected delivery volume | 1 U | 6 U | 12 U |
| Median amount delivered | 0.996 U | 5.978 U | 11.958 U |
| [min, max] | [0.426, 1.274] | [5.450, 6.378] | [11.323, 12.579] |
Table 3: Amount of fluid delivered after 1, 6 and 12 hours with 10 U/hr (high) basal rate setting
| 10 U/hr Basal Duration | 1 hour | 6 hours | 12 hours |
| --- | --- | --- | --- |
| Total expected delivery volume | 10 U | 60 U | 120 U |
| Median amount delivered | 9.888 U | 59.418 U | 118.841 U |
| [min, max] | [9.178, 10.215] | [58.462, 59.792] | [117.835, 119.173] |
#### 2. Bolus Delivery Accuracy
To assess bolus delivery accuracy, 29 Mint Pumps were tested by delivering consecutive minimum, intermediate, and maximum bolus volumes (0.1, 5.0, and 30 units). 14 of the 29
K260001 - Page 5 of 8
{5}
durable components for minimum, intermediate, and maximum bolus had been aged to simulate two years of regular use. Water was used as a substitute for insulin.
The number of total and consecutive boluses delivered in this testing for each delivery volume is described in Table 4 below:
Table 4: Summary of bolus testing protocol
| Bolus size (units) | Number of pumps tested | Consecutive boluses per pump | Total boluses |
| --- | --- | --- | --- |
| 0.1 units | 29 | 100 | 2900 |
| 5 units | 29 | 30 | 870 |
| 30 units | 29 | 5 | 145 |
Table 5: Amount of fluid delivered after a 0.1 U bolus request
| Units delivered after a 0.10 U bolus request (% of commanded units) | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | <25% | 25-75% | 75-95% | 95-105% | 105-125% | 125-175% | 175-250% | >250% |
| Number and percent of boluses | 3/2900 (0.1%) | 50/2900 (1.7%) | 710/2900 (24.5%) | 1435/2900 (49.5%) | 655/2900 (22.6%) | 45/2900 (1.6%) | 2/2900 (0.1%) | 0/2900 - |
Table 6: Amount of fluid delivered after a 5.0 U bolus request
| Units delivered after a 2.5 U bolus request (% of commanded units) | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | <25% | 25-75% | 75-95% | 95-105% | 105-125% | 125-175% | 175-250% | >250% |
| Number and percent of boluses | 0/870 - | 0/870 - | 16/870 (1.8%) | 852/870 (97.9%) | 2/870 (0.2%) | 0/870 - | 0/870 - | 0/870 - |
Table 7: Amount of fluid delivered after a 30.0 U bolus request
| Units delivered after a 30.0 U bolus request (% of commanded units) | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | <25% | 25-75% | 75-95% | 95-105% | 105-125% | 125-175% | 175-250% | >250% |
| Number and percent of boluses | 0/145 - | 0/145 - | 0/145 - | 145/145 (100%) | 0/145 - | 0/145 - | 0/145 - | 0/145 - |
### 3. Occlusion Detection Accuracy
Occlusion detection testing was conducted on 30 Mint ACE Pump Systems. Testing included four conditions: 5 U bolus, minimum basal (0.1 U/hr), and intermediate basal (1 U/hr). Sixteen of the pumps used new disposables/durables, and the remaining combined aged conditions. Both aged and new disposables and durables were tested.
K260001 - Page 6 of 8
{6}
Table 8: Occlusion detection testing
| | Typical time to occlusion detection | Maximum time to occlusion detection |
| --- | --- | --- |
| ≥ 5 U Bolus | 19 seconds | 29 seconds |
| 0.1 U/hr Basal | 35 hours 10 minutes | 48 hours and 32 minutes |
| 1 U/hr Basal | 2 hours and 47 minutes | 4 hours 38 minutes |
### B. Other Supportive Device Performance Characteristics Data
#### 4. Additional Bench Testing
| Reliability |
| --- |
| Rapid pressure changes |
| Transient temperature changes |
| IPX8 submersion, drop, shock, vibration, impact |
| Chemical exposure |
| Shelf-life testing |
#### 5. Software and Cybersecurity
The software and cybersecurity documentation provided was determined to be adequate to support substantial equivalence.
#### 6. Interoperability
A plan and approach for interoperability were provided for integration of CGM, iAGC and Mobile App and determined to be adequate to support and clearly specify expectations, requirements, and interface specifications to potential interoperable devices.
#### 7. Biocompatibility
Biocompatibility testing was performed per FDA Guidance Document: Use of International Standard ISO 10993-1 “Biological evaluation of medical devices – Part 1: Evaluation and testing within a risk management process,” and FDA special controls for alternate controller enabled infusion pump. Results support a determination of substantial equivalence.
#### 8. Sterility
The sponsor has performed adequate sterilization validation to demonstrate substantial equivalence.
#### 9. Human Factors
Human Factors validation testing assessed users 6 years of age and older diagnosed with type 1 diabetes across multiple distinct user groups: adults with type 1 diabetes who independently manage their diabetes (including both pump users and MDI users); seniors (65 years and older) with dexterity or vision limitations; and pediatric patients (6–17 years), including both self-managing and caregiver-managed dyads, as well as newly diagnosed patients. The study included participants with varied experience levels, encompassing both AID-naïve and AID-experienced users. Training was standardized and consisted of either in-person or virtual sessions conducted by a certified in-person trainer.
K260001 - Page 7 of 8
{7}
10. Electronic Compatibility and Electrical Safety
Electromagnetic compatibility and electromagnetic immunity and wireless coexistence testing was performed for the pump. The sponsor provided verification evidence for compliance with the IEC 60601-1 and applicable collateral standards. All tests demonstrated that the device would perform as expected in the home healthcare environment.
11. Wireless Coexistence
Wireless coexistence was evaluated per ANSI/IEEE C63.27, as well as range and household coexistence protocols. Reports demonstrated robust BLE communication in coexistence, range, and household environments with no loss of safety or performance.
VII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
VIII Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K260001 - Page 8 of 8
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.
