CYAN DXD, MULTITEST CD8/CD4/CD3, CD3-FITC, CD3-RPE, CD3-APC AND FLUOROSPHERES
K060423 · Dakocytomation California, Inc. · GKZ · Aug 15, 2006 · Hematology
Device Facts
Record ID
K060423
Device Name
CYAN DXD, MULTITEST CD8/CD4/CD3, CD3-FITC, CD3-RPE, CD3-APC AND FLUOROSPHERES
Applicant
Dakocytomation California, Inc.
Product Code
GKZ · Hematology
Decision Date
Aug 15, 2006
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 864.5220
Device Class
Class 2
Indications for Use
The CyAn™ DXD Flow Cytometer with Summit™ software and user manual is intended for use as an In-Vitro Diagnostic device for identification and enumeration of the relative fraction of lymphocyte subsets in human peripheral whole blood using flow cytometry, i.e., identifies the relative percentage of CD4 and CD8 T-cells as demonstrated by gating on CD3 positive cells. TC-660, the three color combination, CD3, CD4 and CD8 intended for use to identify the relative percentages of CD4 and CD8 positive T cells. Calibrators, FluoroSpheres (Dako K0110) are intended for in vitro use on the Dako CyAn™ DXD flow cytometer with Summit™ software to adjust detector voltages and monitor daily instrument performance. CD3 FITC (Dako F0818), CD3 RPE (R0810), and CD3 APC (C7225) single antibody- fluorochrome conjugates are intended to be used for setting fluorescence compensation parameters using automated compensation.
Device Story
Bench-top flow cytometer; uses multi-laser stimulation (up to 3 lasers) to analyze fluorescence-tagged lymphocytes in peripheral whole blood. Input: whole blood samples stained with MultiMix™ triple-color reagents (CD3/CD4/CD8). Operation: cells flow single-file past lasers; fluorescence, forward scatter (FSC), and side scatter (SSC) detected. Summit™ software processes signals to identify T-cell subsets via gating on CD3+ cells. Daily calibration uses FluoroSpheres; automated compensation uses single-antibody conjugates. Used in clinical labs by trained personnel. Output: relative percentages of CD4 and CD8 T-cell subsets. Assists clinicians in immunophenotyping; provides quantitative data for lymphocyte subset analysis.
Clinical Evidence
Bench testing only. Precision studies (n=30 aliquots) showed SDs 0.17-1.02. Linearity (0-100% range) showed R2 ≥ 0.99. Method comparison (n=92 specimens) against predicate reagents showed R2 > 0.95 for all CD4/CD8 populations. Specificity verified in 5 healthy donors. Reference ranges established in 161 healthy adults.
Technological Characteristics
Bench-top flow cytometer; multi-laser (up to 3) excitation (365-650 nm). Uses fluorescence-tagged antibodies (FITC, RPE, APC). Includes automated compensation and quality control algorithms. Software-driven (Summit).
Indications for Use
Indicated for clinical immunophenotyping of human peripheral whole blood to identify and enumerate CD3, CD4, and CD8 lymphocyte subsets.
Regulatory Classification
Identification
An automated differential cell counter is a device used to identify one or more of the formed elements of the blood. The device may also have the capability to flag, count, or classify immature or abnormal hematopoietic cells of the blood, bone marrow, or other body fluids. These devices may combine an electronic particle counting method, optical method, or a flow cytometric method utilizing monoclonal CD (cluster designation) markers. The device includes accessory CD markers.
Special Controls
*Classification.* Class II (special controls). The special control for this device is the FDA document entitled “Class II Special Controls Guidance Document: Premarket Notifications for Automated Differential Cell Counters for Immature or Abnormal Blood Cells; Final Guidance for Industry and FDA.”
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
K060423
B. Purpose for Submission:
New Device
C. Measurand:
CD3, CD4, CD8 Lymphocytes
D. Type of Test:
Flow Cytometry, Quantitative and Semi-quantitative
E. Applicant:
DAKOCYTOMATION CALIFORNIA, INC.
F. Proprietary and Established Names:
CyAn™ DXD with Summit™ Software
(Code CY204-30, CY205-30)
MultiMix™ Triple-Colour Reagent (Code TC660)
Anti-Human CD8/FITC
Anti-Human CD4/RPE
Anti-Human CD3/APC
FluoroSpheres (Code K0110)
Anti-human CD3 FITC (Code F0818)
Anti-human CD3 RPE (Code F0810)
Anti-human CD3 APC (Code C7225)
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| GKZ | Class II | 864.5220 | Hematology (81) |
{1}
H. Intended Use:
1. Intended use(s):
The CyAn™ DXD Flow Cytometer with Summit™ software and user manual is intended for use as an In-Vitro Diagnostic device for identification and enumeration of the relative fraction of lymphocyte subsets in human peripheral whole blood using flow cytometry, i.e., identifies the relative percentage of CD4 and CD8 T-cells as demonstrated by gating on CD3 positive cells. TC-660, the three color combination, CD3, CD4 and CD8 intended for use to identify the relative percentages of CD4 and CD8 positive T cells. Calibrators, FluoroSpheres (Dako K0110) are intended for in vitro use on the Dako CyAn™ DXD flow cytometer with Summit™ software to adjust detector voltages and monitor daily instrument performance. CD3 FITC (Dako F0818), CD3 RPE (R0810), and CD3 APC (C7225) single antibody- fluorochrome conjugates are intended to be used for setting fluorescence compensation parameters using automated compensation.
2. Indication(s) for use:
Clinical immunophenotyping using the CyAn™ DXD flow cytometer, a lyse wash sample preparation method, for identification and enumeration of CD3, CD4 and CD8 lymphocyte subsets using TC-660.
For In-Vitro Diagnostic Use
3. Special conditions for use statement(s):
Not applicable.
4. Special instrument requirements:
Not applicable.
I. Device Description:
The Dako CyAn™ DXD device is a bench-top flow cytometer system relying on multiple (up to three) laser stimulation of fluorescence tagged lymphocytes. It is used with the Dako MultiMix, a triple color reagent; one each to CD3, CD4 and CD8, conjugated to fluorochromes APC(allophycocyanin), r-phycoerythrin, and fluorescein isothiocyanate, which are balanced to identify the dual positive T-cell populations (CD3+CD4+ and CD3+CD8+) in peripheral blood lymphocytes. The instrument requires daily set-up with Dako FluoroSpheres consisting of a set of 5 bead populations having different fluorescent intensities and one nonfluorescent bead population. The combination of fluorochromes enables excitation by light of any wavelength from 365-650 nm. The CyAn DXD utilizes anti-human CD3 conjugated with FITC, RPE and APC to perform autocompensation.
{2}
# J. Substantial Equivalence Information:
| Predicate | Item | Similarities | Differences |
| --- | --- | --- | --- |
| K974360BD-FACSCaliburBectonDickenson | IntendedUse | The BD FACSCalibur IVD Flow Cytometer with CellQuest Software is intended for use as an In-Vitro Diagnostic device for identification and enumeration of the relative fraction of lymphocyte subsets in human cells in suspension using flow cytometry.I.e., identifies the relative percentages of CD4 and CD8 T-cells as demonstrated by gating on CD3 positive cells | The DakoCytomation CyAn IVD Flow Cytometer with Summit software is intended for use as an In-Vitro Diagnostic device for identification and enumeration of the relative fraction of lymphocyte subsets in human cells in suspension using flow cytometryI.e., identifies the relative percentages of CD4 and CD8 T-cells |
| K974360BD-FACSCaliburBectonDickenson | Number of lasers | 2 | 3 |
| K974360BD-FACSCaliburBectonDickenson | Type of lasers | 488nm air cooled635nm solid state diode | Solid state diode lasers488nm OPSL405nm diode635nm semiconductor |
| K974360BD-FACSCaliburBectonDickenson | Number and type of parameters | 488 laser pathsFITCPEPE-TR/PerCP/PE-Cy5/PE-Cy7635 laser pathAPC/APC-Cy7 | 488nm laser path- 5 channelsFITCPEPE-Cy5PE-Cy7635nm laser pathAPCAPC-Cy7405nm laser pathPacific Blue |
| K974360BD-FACSCaliburBectonDickenson | Calibrators | BD CaliBRITE beads | FluoroSpheres (K0110) for instrument setup.CD3 FITC (DakoCytomation F0818), CD3 RPE (R0810), and CD3 APC (C7225) to set fluorescence compensation parameters |
| K974360BD-FACSCaliburBectonDickenson | Reagents | DC-FR875 (CD3 FITC/ CD4 PE)DC-FR881 (CD3 FITC/ CD8 PE)DC-FR700 (CD45 FITC/ CD14 RPE)DC-XO932 (IgG1 FITC/ IgG1 PE) | DC-TC660 (CD8 FITC/CD4 PE/CD3 APC)DC-CD3 Pacific BlueBD CD4 APC-Cy7BD CD8 PE-Cy7DC CD8 PE-Cy5 |
{3}
4
| K974360
BD-FACS
Calibur
Becton
Dickenson | Software | CellQuest/FACSComp/Multiset | Summit v.4 |
| --- | --- | --- | --- |
| K974360
BD-FACS
Calibur
Becton
Dickenson | Detectors | 1- Forward Scatter Photodiode
1-Side Scatter photomultiplier tube (PMT)
4- Fluorescence Detector PMTs | Forward Scatter Photodiode
Side Scatter photomultiplier tube (PMT)
9 - Same 4 plus additional 5
Fluorescence Detector PMTs |
| K974360
BD-FACS
Calibur
Becton
Dickenson | Optics | FACSCalibur Flow Cell
Laser light delivered by mirrors, prisms, and lenses
Emitted light delivered by mirrors | DakoCytomation Flow Cell
Laser light delivered by mirrors, prisms, and lenses
Emitted light delivered by mirrors |
| K974360
BD-FACS
Calibur
Becton
Dickenson | Electronics | Analog | Analog/digital |
| K974360
BD-FACS
Calibur
Becton
Dickenson | Sample
Introduction | Manual sample loading | Same |
| K974360
BD-FACS
Calibur
Becton
Dickenson | Computer
platform | Macintosh | PC |
K. Standard/Guidance Document Referenced (if applicable):
| STANDARDS |
| --- |
| Title and Reference Number |
| Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline (EP09-A2) |
{4}
| GUIDANCE | | | |
| --- | --- | --- | --- |
| Document Title | Office | Division | Web Page |
| Draft Guidance for 510(k) Submission of Lymphocyte Immunophenotyping IVDs using Monoclonal Antibodies | OIVD | DIHD | http://www.fda.gov/cdrh/ode/475.pdf |
# L. Test Principle:
TC660 consists of three monoclonal antibodies, each labeled with a unique fluorochrome. The CD8, CD4, and CD3 specific antibodies have been conjugated with FITC, RPE and APC, respectively. Lymphocyte subpopulations in peripheral blood samples may be stained with fluorochrome-conjugated antibody and evaluated after interfering red blood cells (RBCs) have been lysed.
An aliquot of a stained and lysed sample is applied to a flow cytometer and the cells flow in a single file past a laser beam. Stained cells will fluoresce depending on the nature of the fluorochrome label, FITC with an emission maximum at $520\mathrm{nm}$ , RPE at $575\mathrm{nm}$ and APC at $660\mathrm{nm}$ . This fluorescence as well as forward scatter (FSC) and side scatter (SSC) light is detected by the flow cytometer. The combination of fluorescence, FSC and SSC characteristics allows identification of T-cell subsets.
When excluding granulocytes and monocytes from the analysis gate on the basis of their FSC and SSC characteristics percent positive, lymphocytes can be determined. The T-cell counts are typically expressed as percentages of lymphocytes. Since each type of flow cytometer has different operating characteristics, each laboratory must determine its optimal operating procedure.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
Precision of the instrument was measured in two separate studies. In the first study, 5 whole blood specimens that had different ranges of CD3, CD4 and CD8 expression levels were used to measure precision for the FITC, RPE and APC parameters. Each specimen was separated in aliquots of 6, mixed with the test reagent and then acquired 10 times on the CyAn. The TC660 reagent (combined CD8 FITC/ CD4 RPE/ CD3 APC) was used as the detecting reagent. For the FITC parameter, standard deviations of 30 aliquots ranged from 0.18 to 0.88. For the RPE and APC parameters, standard deviations of 30 aliquots ranged from 0.17 to 1.02 and 0.25 to 0.93 respectively.
In the second study, cells obtained from JM and Raji cell lines were the test matrix. Cell line concentrations were $10\%$ , $50\%$ and $90\%$ to test the middle and outer limits of
{5}
the instrument. Combination reagents consisting of CD3, CD4 or CD8 antibodies conjugated to different fluorochromes (APC-Cy7, RPE-Cy5, RPE-Cy7 and Pacific Blue) were used as the test reagents. Cells were mixed, separated in aliquots, and mixed with the antibody reagents. Each aliquot was acquired on the CyAn 10 times. Means, standard deviations and $\% \mathrm{CV}$ 's were determined. Means and standard deviations were determined as listed in table below:
Range of means and standard deviations for each parameter and cell line concentration:
| | Reagent Pair 1 | | Reagent Pair 2 | |
| --- | --- | --- | --- | --- |
| % JM Cells | APC-Cy7 Means (standard deviations) | RPE-Cy7 Means (standard deviations) | RPE-Cy5 Means (standard deviations) | Pacific Blue Means (standard deviations) |
| 90% | 84.23 - 85.67% (0.38 - 0.94) | 86.97 - 87.86% (0.94 - 1.18) | 89.78 - 91.21% (0.46 - 0.90) | 88.67 - 90.20% (0.60 - 0.75) |
| 50% | 46.00 - 47.93% (1.15 - 1.95) | 46.75 - 49.93% (2.15 - 3.28) | 50.76 - 52.54% (1.21 - 2.39) | 48.46 - 50.95% (1.64 - 2.91) |
| 10% | 10.04 - 11.82%. (0.39 - 0.67) | 10.06 - 12.33% (0.63 - 1.13) | 11.14 - 11.84%. (0.37 - 0.69) | 10.37 - 11.39% (0.46 - 0.99) |
# b. Linearity/assay reportable range:
For linearity, duplicate tubes of 5 different cell line concentrations ranging from 0 to $100\%$ of positive cells were prepared. Each of 7 parameters was assessed for linear conformity to the theoretical 1:1 line. Linear equations for each parameter had a slope close to 1 and intercept close to 0, with an $\mathbb{R}^2$ of at least 0.99.
Linearity results using cell line concentrations
| | Intercept | Slope | R2 |
| --- | --- | --- | --- |
| FITC | -1.79 | 1.04 | 0.9977 |
| R-PE | -3.27 | 1.05 | 0.9942 |
| APC | -2.74 | 1.04 | 0.9934 |
| APC-Cy7 | -1.38 | 1.05 | 0.9980 |
| Pacific Blue | -1.01 | 1.04 | 0.9991 |
| RPE-Cy5 | -1.74 | 1.02 | 0.9993 |
| RPE-Cy7 | -2.95 | 1.02 | 0.997 |
Linear Range: 0-100%
Reportable Range: 0-100%0
{6}
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Reference material used for daily QC includes the three anit-CD3 reagents (CD3FITC, CD3RPE, CD3APC). Shelf-life studies for these reagents support three years for CD3FITC and two years for CD3RPE and CD3APC.
Based on manufacturer's supplied information on stability, the fluorospheres have a shelf life of two years. To verify this, a reference letter from Spherotech was included.
d. Detection limit:
Analytical limits are currently 0 and 100%.
e. Analytical specificity:
Not applicable
f. Assay cut-off:
Not applicable
2. Comparison studies:
a. Method comparison with predicate device:
Comparison testing was performed on a total of ninety-two (92) normal and abnormal specimens at three study sites. Regression analysis was performed comparing data obtained from the predicate and DakoCytomation FDA-cleared dual antibody reagents (CD45/CD14, CD3/CD4 and CD3/CD8) combination products to three different triple antibody-fluorochrome combination products run on the CyAn™ DXD instrument. Linear regression statistical analysis of the predicate device to test device comparison gave R2 values above 0.95 for all comparisons.
Correlation of CD4 Positive Population
| Linear regression equations and correlation statistic (R2) CD3+CD4+ | | | |
| --- | --- | --- | --- |
| Reagent Combination (CD3+CD4+) | CD8 FITC/CD4 RPE/ CD3 APC (TC660) | CD3 Pacific Blue/ CD4 APC-Cy7/ CD8 RPE-Cy5 | CD3 Pacific Blue/ CD4 APC-Cy7/ CD8 RPE-Cy7 |
| Linear equation | y = 0.37 +0.96b | y = -0.21+0.97b | y = 0.16+0.97b |
| R2 | 0.9735 | 0.9744 | 0.9734 |
| n | 92 | 92 | 92 |
{7}
Correlation of CD4 Negative Population
| Linear regression equations and correlation statistic (R2) CD3+CD4- | | | |
| --- | --- | --- | --- |
| Reagent Combination (CD3+CD4-) | CD8 FITC/CD4 RPE/ CD3 APC (TC660) | CD3 Pacific Blue/ CD4 APC-Cy7/ CD8 RPE-Cy5 | CD3 Pacific Blue/ CD4 APC-Cy7/ CD8 RPE-Cy7 |
| Linear equation | y = 0.03+0.98b | y = 0.37+0.98b | y = 0.06+0.98b |
| R2 | 0.9919 | 0.9914 | 0.9871 |
| n | 92 | 92 | 92 |
Correlation of CD8 Positive Population
| Linear regression equations and correlation statistic (R2) CD3+CD8+ | | | |
| --- | --- | --- | --- |
| Reagent Combination (CD3+CD8+) | CD8 FITC/CD4 RPE/ CD3 APC (TC660) | CD3 Pacific Blue/ CD4 APC-Cy7/ CD8 RPE-Cy5 | CD3 Pacific Blue/ CD4 APC-Cy7/ CD8 RPE-Cy7 |
| Linear equation | y = -0.44+0.96b | y = 0.16+0.97b | y = -0.07+0.97b |
| R2 | 0.9903 | 0.9916 | 0.9913 |
| n | 92 | 92 | 92 |
Correlation of CD8 Negative Population
| Linear regression equations and correlation statistic (R2) CD3+CD8- | | | |
| --- | --- | --- | --- |
| Reagent Combination (CD3+CD8-) | CD8 FITC/CD4 RPE/ CD3 APC (TC660) | CD3 Pacific Blue/ CD4 APC-Cy7/ CD8 RPE-Cy5 | CD3 Pacific Blue/ CD4 APC-Cy7/ CD8 RPE-Cy7 |
| Linear equation | y = 1.16+0.96b | y = 0.18+ 0.96b | y = 0.68+0.96b |
| R2 | 0.9683 | 0.9735 | 0.9793 |
| n | 92 | 92 | 92 |
b. Matrix comparison:
Not applicable.
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable.
b. Clinical specificity:
Specificity of MultiMix™ Triple-Colour Antibody Reagent Anti-CD8/FITC+Anti-CD4/RPE+Anti-CD3/APC were verified by tests performed on five apparently healthy adult donors of various races. Cell populations tested were lymphocytes, monocytes, granulocytes and debris (RBC, platelets). The results indicate antibody binding of MultiMix™ Triple-Colour Reagent Anti-CD8/FITC+Anti-CD4/RPE+Anti-CD3/APC is specific for T-lymphocytes.
{8}
Specificity of triple-color reagent Anti-CD8/FITC+Anti-CD4/RPE+Anti-CD3/APC
| Range (n=5) | % Positive Lymphocytes | % Positive Monocytes | % Positive Granulocytes | % Positive Debris |
| --- | --- | --- | --- | --- |
| CD3+CD4+ | 34.00-47.22 | 0.58-2.61 | 0.12-0.35 | 0.01-0.03 |
| CD3+CD4- | 20.08-33.46 | .10-1.55 | 0.10-0.22 | 0.00-0.03 |
| CD3+CD8+ | 19.08-37.68 | 0.35-1.56 | 0.15-0.26 | 0.00-0.04 |
| CD3+CD8- | 35.96-48.22 | 0.35-2.71 | 0.10-0.30 | 0.01-0.04 |
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable.
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
Blood samples were collected from 161 apparently healthy males and females at three geographically separate locations. The population included adults from a variety of races ranging in age from 20 to 69 years. Samples were stained with Anti-CD8/FITC, Anti-CD4/RPE and Anti-CD3/APC monoclonal antibodies. Normal CD3+CD4+, CD3+CD4-, CD3+CD8+, and CD3+CD8- T-cell values were measured by flow cytometry using the whole blood method, and are presented in the following table. Values below are expressed as a percentage of the total lymphocyte count due to unacceptable variation in absolute counts and are intended as representative values only. Each laboratory should establish its own expected values from the local population of normal donors.
| | % CD3+/CD4+ | % CD3+/CD8- | % CD3+/CD4- | % CD3+/CD8+ |
| --- | --- | --- | --- | --- |
| n | 161 | 161 | 161 | 161 |
| mean | 44.58 | 25.85 | 23.11 | 47.33 |
| St. Dev | 7.67 | 7.21 | 6.24 | 7.40 |
| %CV | 17.21 | 27.88 | 26.99 | 15.63 |
| 5% Range | 25.26 | 12.62 | 9.96 | 27.38 |
| 95% Range | 62.28 | 42.30 | 37.73 | 63.42 |
N. Instrument Name:
CyAn™ DXD
O. System Descriptions:
1. Modes of Operation:
The modes of operation for the CyAn DXD are defined as Open Tube, Manual.
{9}
10
2. Software:
The CyAn Flow Cytometer requires use of the Summit software program to establish instrument settings, control acquisition, manipulate and save data, and provide other status and control regarding instrument behavior.
FDA has reviewed applicants Hazard Analysis and software development processes for this line of product types:
Yes ☐ X or No ☐
3. Specimen Identification:
Patient data is manually entered.
4. Specimen Sampling and Handling:
Collect blood specimens by venipuncture into evacuated tubes containing EDTA, completely expending the vacuum in the tubes. Mix the blood well with the anticoagulant to prevent clotting. At least 100 μL of whole blood is required for each test. Ideally, blood samples should be processed immediately after collection. When this is not possible, each laboratory should validate that its collection and holding methods maintain specimen integrity comparable to freshly processed material. When using EDTA, blood samples should be held at room temperature (18-22 °C) and processed within 30 hours.
5. Calibration:
DakoCytomation K0110 FluoroSpheres are intended for in vitro use on the DakoCytomation CyAn DXD flow cytometer with Summit™ software to adjust detector voltages and monitor daily instrument performance. CD3 FITC (DakoCytomation F0818), CD3 PE (R0810), and CD3 APC (C7225) single antibody-fluorochrome conjugates are intended to be used for setting fluorescence compensation parameters.
6. Quality Control:
Daily Quality Control of the CyAn DXD is achieved through analysis of FluoroSpheres 6-peak beads (K0110) to ensure consistent resolution and sensitivity. Further, a normal specimen can be for an internal quality control.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The Performance Characteristics Section above:
Carryover testing was performed using 3 replicates of the 100% cell line concentrations followed by 3 replicates of 0% concentration of cell line cells. Parameters that were tested in the carryover study using cell lines included FITC, RPE, APC, Pe-Cy7, PE-Cy5, Pacific Blue, and APC-Cy7. Average carryover ranged from 0.45 to 1.18. The range found for the
{10}
0% cells after 100% cells were tested was 0.35 to 1.72. These levels remain within the known lower limits of detection of the instrument and these effects are considered minimal for the 7 parameters tested.
**Q. Proposed Labeling:**
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
**R. Conclusion:**
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
11
{11}
12
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.