ADVIA CENTAUR SHBG READYPACK, LOW AND HIGH CALIBRATORS AND MASTER CURVE MATERIAL, MODELS 06520781, 04819274 AND 06520773
Applicant
Siemens Healthcare Diagnostics
Product Code
CDZ · Clinical Chemistry
Decision Date
Jan 14, 2010
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1680
Device Class
Class 1
Indications for Use
The ADVIA Centaur® SHBG assay is an in vitro diagnostic immunoassay for the quantitative determination of sex hormone-binding globulin (SHBG) in human serum and plasma using the ADVIA Centaur systems. The ADVIA Centaur SHBG assay is intended for use as an aid in the diagnosis of androgen disorders. The ADVIA Centaur SHBG Calibrators are for in vitro diagnostic use in calibrating the ADVIA Centaur sex hormone-binding globulin (SHBG) assays. The ADVIA Centaur SHBG Master Curve Material are for in vitro diagnostic use in the verification of calibration and reportable range in the ADVIA Centaur sex hormonebinding globulin (SHBG) assay.
Device Story
ADVIA Centaur SHBG assay is an in vitro diagnostic immunoassay; performs quantitative determination of SHBG in human serum and plasma. Used on ADVIA Centaur systems; operated by laboratory professionals in clinical settings. Device utilizes calibrators and master curve material for calibration and verification of reportable range. Output provides SHBG concentration levels; assists clinicians in diagnosing androgen disorders. Benefits patient by providing diagnostic information for endocrine conditions.
Clinical Evidence
No clinical data provided; document focuses on 510(k) clearance for an in vitro diagnostic immunoassay.
Technological Characteristics
In vitro diagnostic immunoassay; utilizes ADVIA Centaur system platform. Includes liquid-stable reagents, calibrators, and master curve material. Quantitative measurement of SHBG in serum/plasma.
Indications for Use
Indicated for the quantitative determination of sex hormone-binding globulin (SHBG) in human serum and plasma as an aid in the diagnosis of androgen disorders.
Regulatory Classification
Identification
A testosterone test system is a device intended to measure testosterone (a male sex hormone) in serum, plasma, and urine. Measurement of testosterone are used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in males and, in females hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes.
Submission Summary (Full Text)
{0}
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k091867
B. Purpose for Submission:
New device
C. Measurand:
Sex hormone-binding globulin (SHBG)
D. Type of Test:
Quantitative, chemiluminescent
E. Applicant:
Siemens Healthcare Diagnostics, Inc.
F. Proprietary and Established Names:
ADVIA Centaur SHBG ReadyPack
SHBG Low Calibrator
SHBG High Calibrator
SHBG Master Curve Material
G. Regulatory Information:
| Device Name | Product Code | Device Classification | Regulation Number | Panel |
| --- | --- | --- | --- | --- |
| SHBG Calibrators | JIT | II | 21 CFR 862.1150 | Chemistry (75) |
| ADVIA Centaur SHBG ReadyPack | CDZ | Class I, reserved | 21 CFR 862.1680 | Chemistry (75) |
| SHBG Master Curve Material | JJX | Class I, reserved | 21 CFR 862.1660 | Chemistry (75) |
H. Intended Use:
1. Intended use(s):
{1}
Page 2 of 12
See Indications for Use below.
2. **Indications(s) for use:**
The ADVIA Centaur SHBG assay is an in vitro diagnostic immunoassay for the quantitative determination of sex hormone-binding globulin (SHBG) in human serum and plasma using the ADVIA Centaur systems. The ADVIA Centaur SHBG assay is intended for use as an aid in the diagnosis of androgen disorders.
The ADVIA Centaur SHBG Calibrators are for in vitro diagnostic use in calibrating the ADVIA Centaur sex hormone-binding globulin (SHBG) assay.
The ADVIA Centaur SHBG Master Curve Material (MCM) is for in vitro diagnostic use in the verification of calibration and reportable range in the ADVIA Centaur sex hormone-binding globulin (SHBG) assay.
3. **Special conditions for use statement(s):**
For prescription use only
Not for newborn testing
SHBG Calibrators barcode labels are lot-number specific and should not be used with other calibrator lots.
SHBG Master Curve Material is not intended for use as routine quality control material or as calibration material.
4. **Special instrument requirements:**
ADVIA Centaur
I. **Device Description:**
Each SHBG Ready Pack contains: 1) Solid Phase (11.0 mL) streptavidin coupled magnetic latex particles (~150 µg/mL), 2) Lite Reagent (3.0 mL) containing mouse monoclonal anti-SHBG antibody (~130 µg/mL) labeled with acridinium ester, and 3) Ancillary Well Reagent (3.0 mL) containing a biotinylated monoclonal mouse anti-SHBG antibody (~6 µg/mL). Each Ready Pack contains reagents for 50 tests.
SHBG Calibrators are listed in the SHBG Ready Pack labeling as required by not provided. They contain 2 vials (2 mL/vial after reconstitution) each of lyophilized Low (~10 nmol/L) and High (~160 nmol/L) calibrators, a calibrator assigned value card, and lot specific barcode labels. Calibrators contain low or high levels of SHBG in equine serum, detergents and preservatives.
{2}
Page 3 of 12
The ADVIA SHBG Master Curve Materials (MCM) are listed in the SHBG kit labeling as an optional reagent. It contains 5 levels of human SHBG in equine serum provided as 5 vials of lyophilized material (1 mL/ vial after reconstitution). MCM Levels 1-4 are expected to be in the acceptable range, while Level 5 is manufactured to meet or exceed the reportable range of the assay.
The product inserts for the SHBG Calibrators and SHBG Master Curve Material include the following statement: Human source material used in the manufacture of this product has been tested using FDA approved methods and found to be non-reactive for hepatitis B surface antigen (HBsAg), antibody to hepatitis C (HCV), and antibody to HIV-1/2.
## J. Substantial Equivalence Information:
1. Predicate device name(s):
Roche Elecsys SHBG Immunoassay System
Roche Elecsys SHBG CalCheck
2. Predicate 510(k) number(s):
k031717, k031698
3. Comparison with predicate:
| Reagent Similarities and Differences | | |
| --- | --- | --- |
| | Device
ADVIA Centaur SHBG assay | Predicate
(Elecsys SHBG Immunoassay, k031717) |
| Intended Use | The ADVIA Centaur SHBG assay is an in vitro diagnostic immunoassay for the quantitative determination of sex hormone-binding globulin (SHBG) in human serum and plasma using the ADVIA Centaur Systems. The ADVIA Centaur SHBG assay is intended for use as an aid in the diagnosis of androgen disorders. | Same |
| Assay Protocol | Sandwich Immunoassay | Same |
| Sample type | Serum and Lithium Heparin Plasma | Same |
| Test Methodology | Chemiluminescent Magnetic Latex Particle Immunoassay | Chemiluminescent solid phase enzyme Immunoassay |
{3}
Page 4 of 12
| Reagent Similarities and Differences | | |
| --- | --- | --- |
| | Device
ADVIA Centaur SHBG assay | Predicate
(Elecsys SHBG Immunoassay, k031717) |
| Measuring Range | 0.35 to 180 nmol/L | 0.35 to 200 nmol/L |
| Calibrator Similarities and Differences | | |
| --- | --- | --- |
| | Device
ADVIA SHBG Calibrators | Predicate
(k031717) |
| Intended Use | The ADVIA Centaur SHBG Calibrators are for in vitro diagnostic use in calibrating the ADVIA Centaur sex hormone-binding globulin (SHBG) assays. | The Elecsys SHBG CalSet is used for calibrating the quantitative Elecsys SHBG assay on the Elecsys immunoassay systems. |
| Calibrator composition | Calibrator 1 contains approximately 10 nmol/L SHBG; Calibrator 2 contains approximately 160 nmol/L SHBG | Calibrator 1 contains approximately 0 nmol/L SHBG; Calibrator 2 contains approximately 40 nmol/L SHBG |
| Matrix | Equine serum | Calibrator 1 is in equine serum; Calibrator 2 is in human serum |
| Master Curve Material Similarities and Differences | | |
| --- | --- | --- |
| | Device
ADVIA SHBG Master Curve Material | Predicate
(k031698) |
| Intended Use | The ADVIA Centaur SHBG Master Curve Material are for in vitro diagnostic use in the verification of calibration and reportable range in the ADVIA Centaur sex hormone-binding globulin (SHBG) assay | The Elecsys SHBG CalCheck is intended for use in the verification of the calibration established by the Elecsys SHBG reagent |
| Levels | 5 levels at approximately 0, 10, 50, 100, 200 nmol/L SHBG in equine serum | 3 levels at approximately 20, 81 and 163 nmol/L SHBG in equine/human serum |
K. Standard/ Guidance Document Referenced (if applicable):
- Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline – Second Edition (CLSI EP5-A2).
- Protocols for Determination of Limits of Detection and Limits of Quantitation; Approved Guideline (CLSI EP17-A).
- Interference Testing in Clinical Chemistry; Approved Guideline – Second Edition (CLSI EP7-A2).
- Guidance for Industry and FDA Staff: Bundling Multiple Devices or Multiple Indications in a Single Submission
4
{4}
Page 5 of 12
- Guidance for Industry – Abbreviated 510(k) Submissions for In Vitro Diagnostic Calibrators
L. Test Principle:
The ADVIA Centaur SHBG assay is a quantitative antibody sandwich immunoassay intended for use as an aid in the differential diagnosis of hirsutism and other adrenal abnormalities. The SHBG assay consists of streptavidin magnetic latex particles as the solid phase, biotin labeled anti-SHBG antibody as the capture conjugate, and an acridinium labeled anti-SHBG conjugate as the Lite reagent. An antibody sandwich is formed when SHBG in the patient sample or calibrator is captured by the anti-SHBG on the solid phase which then binds the anti-SHBG antibody acridinium ester (AE) conjugate.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
The sponsor performed Within Run and Total precision studies according to the CLSI EP5-A2 guideline. Seven samples at various levels of SHBG were evaluated: five samples were pooled human serum samples at levels 9.04, 37.89, 72.84, 116.92 and 142.87 nmol/L, and two samples were human serum based control material at levels 21.42 and 39.87 nmol/L.
Five of the samples (1-5 below) were assayed 2 times, in 2 runs, on 1 ADVIA Centaur analyzer, (n = 80 for each sample), over a period of 20 days (n=80). Two additional serum samples (samples 6 and 7) were assayed 2 times, in 2 runs, on 1 ADVIA Centaur analyzer (n=40), over a period of 10 days. One trained operator performed the study.
| | | | Within Run | | Total | |
| --- | --- | --- | --- | --- | --- | --- |
| Sample | Mean (nmol/L) | N | SD | %CV | SD | %CV |
| Level 1 | 9.04 | 80 | 0.28 | 3.1 | 1.59 | 6.5 |
| Level 2 | 21.42 | 80 | 0.82 | 3.8 | 0.93 | 4.3 |
| Level 3 | 37.39 | 80 | 1.12 | 3.0 | 1.96 | 5.2 |
| Level 4 | 39.87 | 80 | 1.03 | 2.6 | 1.53 | 3.8 |
| Level 5 | 72.84 | 80 | 2.61 | 3.6 | 4.20 | 5.8 |
| Level 6 | 116.92 | 40 | 3.02 | 2.6 | 3.57 | 3.1 |
| Level 7 | 142.87 | 40 | 3.57 | 2.5 | 5.49 | 3.8 |
{5}
Page 6 of 12
b. Linearity/assay reportable range:
A linearity study was performed using a high pool and a low pool samples. Intermediate 10 levels were prepared from these two pool samples. A total of 12 samples ranging from 0.16 to 189.89 nmol/L which encompasses the claimed reportable range of 0.35 to 180 nmol/L were tested in triplicate. The measured values were plotted against the expected values and an appropriate line fitted by standard linear regression resulting in: y=1.011x+0.3897. The recovery results are presented below:
| Sample | Dilution | Expected (nmol/L) | Measured (nmol/L) | Recovery (%) |
| --- | --- | --- | --- | --- |
| 1 | High Sample | 189.89 | 189.89 | 100.0 |
| 2 | 1:2 | 95.15 | 100.94 | 106.1 |
| 3 | 1:4 | 48.03 | 50.37 | 104.9 |
| 4 | 1:8 | 24.28 | 24.97 | 102.8 |
| 5 | 1:16 | 12.73 | 12.18 | 95.7 |
| 6 | 1:32 | 6.45 | 6.54 | 101.4 |
| 7 | 1:64 | 3.32 | 3.54 | 106.7 |
| 8 | 1:128 | 1.75 | 1.82 | 104.2 |
| 9 | 1:256 | 0.96 | 1.10 | 114.8 |
| 10 | 1:518 | 0.56 | 0.61 | 108.9 |
| 11 | 1:1036 | 0.36 | 0.38 | 106.5 |
| 12 | Low Sample | 0.16 | 0.16 | 100.0 |
In addition, the sponsor performed a dilution study to demonstrate the ability of the ADVIA Centaur analyzer to recovery accurately from a diluted sample using a 1:2 dilution. Thirteen human patient samples with high SHBG concentrations (140.3 to 306.8 nmol/L) near or above the assay upper limit of 180 nmol/L were diluted both manually and onboard the ADVIA Centaur analyzer and assayed using the ADVIA Centaur SHBG assay. One trained operator performed the study and the percent recovery calculated by comparing the observed onboard diluted results to the manually diluted results. The mean recovery results are within 98.86 and 118.72 %.
High-dose hook effect: The potential for a high-dose hook effect was evaluated for this assay. SHBG was spiked into negative pool (equine serum) and into 2 different serum samples to achieve SHBG concentrations ranging from 888 to 11,100 nmol/L. The samples were analyzed in triplicate on one ADVIA Centaur analyzer using 2 reagent lots. Based on the results, the sponsor concluded that SHBG levels < 1000 nmol/L did not exhibit any high dose effect.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
6
{6}
Page 7 of 12
## Traceability:
The ADVIA Centaur SHBG assay is traceable to World Health Organization (WHO) standard (95/560). Assigned values of calibrators and ranges of controls are traceable to this standardization.
The ADVIA Centaur SHBG Calibrators, low and high: A set of internal SHBG standards were manufactured and value assigned using a SHBG WHO standard (NIBSC Code: 95/960). SHBG master lot calibrators are then value assigned against these standards by pooling the results using multiple ADVIA Centaur analyzers, multiple reagent lots and multiple runs. Productions lots are value assigned against Master lots by assaying replicate samples alternating between the “master lot” calibrator and the production lot (test lot) calibrator.
The SHBG Calibrator insert refers to the Calibrator Assigned Value card to facilitate entering the calibrator values on the system. Values for the Low (~10 nmol/L) and High (~160 nmol/L) calibrators are provided on the SHBG calibrator card.
The ADVIA SHBG Master Curve Material (MCM) is value assigned against an existing MCM reference lot that is traceable to a WHO SHBG standard (NIBSC Code: 95/960). Assigned values were established using the ADVIA Centaur SHBG assay and ADVIA Centaur analyzer. The target values for the 5 MCM solutions, MCM1 to MCM5 are 0, 10, 50, 100, and 200 nmol/L. Test lots are value assigned against the reference lot by assaying replicate samples alternating between the “reference lot” and the test lot. SHBG Master Curve Material product insert refers to the SHBG MCM lot specific target value sheet for the actual ranges.
## Stability:
Real time shelf life and open vial stability testing protocols and acceptance criteria for the ADVIA Centaur SHBG Calibrators were reviewed and found to be acceptable. The product insert recommends storing the lyophilized calibrators at 2 to 8°C until expiration date on the vial label. The sponsor recommends a 39 week stability. It is recommended by the sponsor that the reconstituted calibrators be stored at -20°C for 60 days and to freeze-thaw once.
Real time shelf life stability protocols and acceptance criteria for the ADVIA SHBG Master Curve Material were reviewed and found to be acceptable. The sponsor recommends in the insert to store unopened MCM material at 2 to 8°C until the expiration date on the vial. The sponsor is recommends a 39 week stability. Once reconstituted the material should be used immediately and any remaining material discarded.
7
{7}
Page 8 of 12
d. Detection limit:
The sponsor performed Limit of Blank (LoB) and the Limit of Detection (LoD) studies in accordance with the CLSI EP17-A guideline. For the LoB studies 5 negative SHBG base pools (horse serum) were used as blanks and were analyzed on two ADVIA Centaur analyzers over three days, with two replicates each, using two reagent lots. A total of 120 results were generated. A nonparametric analysis was employed and the LoB is reported as 0.0033 nmol/L.
For the LoD studies 5 spiked low SHBG pools with mean values ranging from 0.119 to 0.216 nmol/L were used. The pools were analyzed with 2 different reagent lots, on 2 ADVIA Centaur analyzers, over 3 days with 2 replicates/sample/run for a total of 24 replicates per sample. A total of 120 replicates were analyzed.
The mean, median and 5th percentiles were calculated for each sample by reagent lot by system. The LoD, the lowest level material in which the 5th percentile exceeds the Limit of Blank, was determined nonparametrically since the requirement of normality was not met for these pools for all combinations of reagent lot and system. The LoD was estimated to be 0.164 nmol/L.
The SHBG assay has a linearity range of 0.35 to 180 nmol/L.
c. Analytical specificity:
The sponsor performed interference studies according to the CLSI EP7-A guideline. Potential cross-reactive compounds (see table below) were added to steroid-free diluent and were evaluated in triplicate on ADVIA Centaur instrument using 2 reagent lots. Each test sample was compared to a matched unspiked control and the % change calculated. The sponsor defines no significant cross-reactivity as <5% difference from sample and control results and states that all the following tested cross reactants are within these specifications:
| Potential Cross-Reactive Agent | Spiking Concentration |
| --- | --- |
| Alpha-Fetoprotein (AFP) | 48.4 μg/dL |
| Cortisol | 100 μg/mL |
| 11-Deoxycortisol | 4 μg/mL |
| 5α-Dihydroxytestosterone | 20 μg/mL |
| Estradiol | 3600 pg/mL |
| Testosterone | 20 μg/mL |
| Thyroglobulin | 300 μg/mL |
| Thyroxin-Binding Globulin | 193 μg/mL |
| Transferrin | 4 mg/mL |
| Fibrinogen | 4.5 g/L |
{8}
Page 9 of 12
| Plasminogen | 250 mg/L |
| --- | --- |
| IgA | 367 mg/dL |
| IgG | 335 mg/dL |
| CBG | 35 mg/dL |
| TSH | 180 mIU/L |
Potential interfering substances were added to three sample pools containing 10, 50, and 80 nmol/L SHBG. The following interfering substances were added to these sample pools and assayed on an ADVIA Centaur in replicates of six: 5 mg/dL conjugated bilirubin and unconjugated bilirubin, 10, 30, 60 and 100 ng/dL biotin, 250 and 500 mg/dL of hemoglobin, 50 mg/mL of BSA, 50 ul/mL intralipid (equivalent to 1000 mg/dL triglyceride), and 1, 10, 100 ul/mL Silwet. The same samples pools containing the appropriate solvent of diluent used to dissolve the interferents were used as controls and the percent recovery between the samples and controls were calculated. The sponsor defines no significant interference as <10% change in results, and states that no significant interference was observed with any of the potential interferents tested. The labeling includes the following limitation: Samples that contain bilirubin concentrations greater than 5 mg/dL may be inaccurate due to potential interference and should not be used.
d. Assay cut-off:
Not Applicable
2. Comparison studies:
a. Method comparison with predicate device:
Method comparisons to the predicate device were performed in accordance with the CLSI EP9-A2 guideline.
A total of 202 remnant, de-identified serum samples, ranging from 0.37 to 172.72 nmol/L SHBG were tested in duplicate at one clinical site on the ADVIA Centaur analyzer (Y) and were compared to results of samples analyzed in duplicate on the Roche Elecsys 2010 (the predicate) (X). Data was analyzed using a singlet set of data from the candidate device. The analysis by least squares linear regression resulted in: y = 0.94x + 2.7; r = 0.990.
b. Matrix comparison:
The sponsor performed a matrix comparison study using a set of matched donor samples types (Serum, Lithium heparin plasma). Fifty nine samples, ranging from 15 to 142 nmol/L of SHBG, were analyzed. Nine of the donor samples were spiked with SHBG. Samples were measured in triplicate using one reagent lot and one ADVIA Centaur analyzer. The results of linear regression analysis: y = 1.0331x - 0.0709; R² = 0.9924.
9
{9}
Page 10 of 12
3. Clinical studies:
a. Clinical Sensitivity: Not Applicable
b. Clinical specificity: Not Applicable
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:
Serum samples of 69 healthy, non-pregnant, pre-menopausal women, 80 post-menopausal women, and 125 health males were used to establish reference ranges for SHBG. Samples were screened for the following and were included in the study only if concentrations fell within these ranges:
| | Females
Pre-menopausal | Females
Post-menopausal | Males |
| --- | --- | --- | --- |
| TSH3UL adults
(uIU/mL) | 0.55-4.78 | 0.55-4.78 | 0.55-4.78 |
| ThCG (non-pregnant)
(mIU/L) | <5 | | |
| E2-6 III (pg/mL) | 18.9-570.8 | <50 | |
| TSTO (ng/dL) | 14-76 | 14-76 | >175 |
| FSH (uIU/mL) | | 23-116.3 | |
| LH (uIU/mL) | | 15.9-54 | |
Samples were tested in duplicate using one lot of the ADVIA Centaur SHBG reagent, one ADVIA Centaur analyzer and one trained operator. Based on a central 95% interval, the following reference ranges were established:
10
{10}
The SHBG package insert states that each laboratory should determine its own reference range(s) for the diagnostic evaluation of patient results.
Additionally, the sponsor performed a validation study using the ADVIA Centaur SHBG and the ADVIA Centaur Testosterone assays (k934562 originally the CIBA Corning Diagnostics Corp) and the same serum samples used to establish the SHBG reference ranges described above in section M5.
Samples were tested using single determinations with one lot of the ADVIA Centaur SHBG reagent and one lot of ADVIA Centaur testosterone reagent. The study was performed by one trained operator using on the ADVIA Centaur analyzer.
| | | | Testosterone | | |
| --- | --- | --- | --- | --- | --- |
| | n | Age | Median (ng/dL) | 5thPercentile (ng/dL) | 95thPercentile (ng/dL) |
| Males | 125 | 21-55 | 487.1 | 231 | 735 |
| Females | 69 | 21-47 | 43 | 13.1 | 85.3 |
| Pre-menopausal | | | | | |
| Females | 80 | 42-89 | 28.6 | 6 | 102.3 |
| Post-menopausal | | | | | |
| | | | FAI | | |
| --- | --- | --- | --- | --- | --- |
| | n | Age | Median | 5th Percentile | 95th Percentile |
| Males | 125 | 21-55 | 48 | 23.3 | 103.2 |
| Females | 69 | 21-47 | 2.7 | 0.64 | 9.4 |
| Pre-menopausal | | | | | |
| Females | 80 | 42-89 | 1.86 | 0.3 | 9.6 |
| Post-menopausal | | | | | |
{11}
Page 12 of 12
The Free Androgen Index (%FAI) was obtained as follows: Testosterone (nmol/L)/SHBG (nmol/L) x 100.
**N. Proposed Labeling:**
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
**O. Conclusion:**
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.