AuraTek FDP is a rapid one-step gold dye particle lateral flow immunoassay indicated for the in vitro qualitative measurement of fibrinogen and fibrin/fibrinogen degradation products (FDP) in human urine, to be used with standard cystoscopic examination to aid in the management of patients with a history of bladder cancer.
Device Story
AuraTek FDP is a point-of-care, lateral flow immunoassay for qualitative detection of fibrinogen and fibrin/fibrinogen degradation products (FDP) in human urine. It utilizes monoclonal antibodies specific to FDP and fibrinogen. The device consists of a porous carrier with discrete zones: mobile purple-red dye particles labeled with anti-FDP/fibrinogen antibodies, immobile capture anti-FDP/fibrinogen antibodies, and a control zone (anti-murine IgG). When urine is applied, FDP/fibrinogen binds to the labeled particles and is captured in the test window, forming a purple-red dot via a sandwich reaction. The test is performed in a physician's office to support cystoscopic examination. Results provide clinicians with rapid, non-invasive information to aid in managing bladder cancer recurrence. The device includes internal validity checks (Reaction Control windows).
Clinical Evidence
Multi-center study of 192 patients with a history of bladder cancer (mean age 69.1). Bladder tumors confirmed in 79 patients via cystoscopy and biopsy. AuraTek FDP demonstrated 68% overall sensitivity (95% CI: 56.9-78.4%) compared to 34% for cytology and 41% for hemoglobin dipstick. Sensitivity was 63% for superficial and 100% for invasive disease. Specificity was 96% in healthy subjects and 80% in cystoscopy-negative patients with a history of bladder cancer. Analytical sensitivity is 30 ng FE/ml. No high-dose hook effect up to 2000 ng FE/ml.
Technological Characteristics
One-step lateral flow immunoassay on a porous carrier. Uses gold dye particle labeling. Sensing principle: sandwich-type immunoassay using monoclonal antibodies. Connectivity: standalone. Sterilization: not specified. Software: none.
Indications for Use
Indicated for patients with a history of bladder cancer undergoing follow-up monitoring. Used as an adjunct to cystoscopic examination for the qualitative detection of FDP in urine.
Regulatory Classification
Identification
A tumor-associated antigen immunological test system is a device that consists of reagents used to qualitatively or quantitatively measure, by immunochemical techniques, tumor-associated antigens in serum, plasma, urine, or other body fluids. This device is intended as an aid in monitoring patients for disease progress or response to therapy or for the detection of recurrent or residual disease.
Special Controls
*Classification.* Class II (special controls). Tumor markers must comply with the following special controls: (1) A guidance document entitled “Guidance Document for the Submission of Tumor Associated Antigen Premarket Notifications (510(k)s) to FDA,” and (2) voluntary assay performance standards issued by the National Committee on Clinical Laboratory Standards.
Predicate Devices
BARD BTA Rapid Urine Test
Submission Summary (Full Text)
{0}
K970353
000009
APR 30 1997
AuraTek FDP
510(k) #K970353
510(k) SUMMARY
{1}
1.0 510(k) SUMMARY
000010
## 1.1 General Information
Date Prepared: April 28, 1997
Device Generic Name: AuraTek FDP
Device Trade Name: AuraTek FDP
Applicant’s Name and Address: Organon Teknika, B.V.
Veedijk 58
2300 Turnhout, Belgium
Authorized representative in the U.S.: PerImmune, Inc.
1330 Piccard Drive
Rockville, MD 20850-4396
Tel: (301) 258-5200
Contact: Fedora Daye Contreras
Establishment Registration Number: 1119752
510(k) Premarket Notification Number: K970353
## 1.2 Indications for Use
AuraTek FDP is a rapid one-step gold dye particle lateral flow immunoassay indicated for the *in vitro* qualitative measurement of fibrinogen and fibrin/fibrinogen degradation products (FDP) in human urine, to be used with standard cystoscopic examination to aid in the management of patients with a history of bladder cancer.
## 1.3 Device Classification
AuraTek FDP is a bladder tumor marker test system-monitoring which has been reclassified as a Class II (Performance standards) device, product code 82 MMW.
## 1.4 Background Information
Cancer of the bladder is a disease with high prevalence among men and women in the U.S. (4th and ninth respectively among malignant diseases) and a high rate of recurrence (estimated to be 80%). Consequently, close follow-up of bladder cancer patients on a regularly scheduled basis is essential. The standard practice for follow-up of patients with a history of bladder cancer involves the use of an invasive diagnostic procedure, transurethral cystoscopy, in which the urothelium is visually inspected with a flexible or rigid endoscope.
{2}
000011
Although there have been many attempts to develop efficient and reliable non-invasive diagnostic tests for bladder cancer, the urinary cytological examination remains the current clinical standard. However, cytology suffers from a limited sensitivity¹ (approximately 35%), particularly in low grade and low stage disease. In addition, cytology is costly, requires a specialized clinical laboratory and the results are not available to the urologist during the office visit by the bladder cancer patient.
Hemoglobin dipstick may be used as a diagnostic aid, but lacks both sensitivity and specificity for bladder tumors. In addition, a single instance of microhematuria may be attributable to a variety of causes². A wide range of alternative markers and procedures have been proposed, including flow cytometry, QFIA³, M344 antigen⁴, nuclear matrix protein⁵, bladder tumor associated antigen (BTA)⁶, and autocrine motility factor⁷. The acceptance of alternative markers has been limited due to lack of efficacy, high expense, and test complexity. It would be useful, therefore, for the urologist to have available a rapid, point-of-care, diagnostic test that could offer high sensitivity, convenience, and rapid results to support the cystoscopic examination of bladder cancer patients.
Previously published studies have shown that elevated urinary fibrin(ogen) degradation products (FDP) are associated with the presence of bladder cancer. In particular, McCabe, et al.⁸ found elevated urinary fibrinogen and FDP levels in 83% of all bladder cancer patients tested using an ELISA method. Based upon this initial study, a rapid, self-contained immunoassay device was developed (AuraTek FDP) that is similar in principle to several over the counter urinary hCG pregnancy tests. This test employs monoclonal antibodies specific for fibrinogen and fibrin(ogen) degradation products and is designed for point-of-care use in the physician's office.
{3}
000012
## 1.5 Device Description
### 1.5.1 Description of Test Analyte
Fibrinogen is a protein found in blood plasma that is converted into fibrin in the process of blood clotting. Fibrin/fibrinogen degradation products (FDP) are protein fragments generated by the action of the fibrinolytic system (plasmin) on fibrin and fibrinogen.
### 1.5.2 FDPs in Bladder Cancer
Studies have shown that increased urinary fibrin/fibrinogen degradation products (FDP) levels are associated with the presence of bladder malignancy. Wajsman et al. reported findings of significantly elevated FDP levels in patients with active bladder carcinoma⁹. Using an ELISA procedure, McCabe et al. found elevated urinary fibrinogen and FDP levels in 83% of all bladder cancer patients tested⁸. The same paper also reported a 98% specificity for patients with nonmalignant urological disease. Other studies have confirmed the utility of urinary fibrinogen and FDP measurement in patients with bladder carcinoma¹⁰,¹¹,¹².
Tumor cells produce vascular endothelial growth factor (VEGF), which is an angiogenic factor¹³. Increased expression of VEGF has been associated with bladder tumors¹⁴,¹⁵. One effect of VEGF is to increase the permeability of the surrounding microvasculature. The increased permeability may lead to leakage of plasma proteins including plasminogen, fibrinogen, and various clotting factors. The clotting factors along with other factors released by the tumor cells rapidly convert the fibrinogen into an extravascular fibrin clot. This fibrin clot will act as a provisional stroma for the tumor until being replaced by mature stroma. Plasminogen may be converted to plasmin by urokinase, the plasminogen activator in the urine produced by the kidney, as well as the tumor cells. The plasmin can then break down the fibrin deposit into fibrin degradation products or FDP’s.
### 1.5.3 Device Design
AuraTek FDP is a one-step gold dye particle immunoassay on a porous carrier. Mobile purple-red dye particles labeled with anti-FDP and fibrinogen antibody and immobile capture anti-FDP and fibrinogen antibodies are coated as discrete zones on the porous carrier. In addition a test control zone with anti-murine IgG (Reaction Control 2) is coated on the carrier. A sample placed on the device is absorbed by
{4}
000013
the porous carrier. The rehydrated colored sol particles move through the porous carrier to the capture anti-FDP and then to the anti-murine IgG. If the sample contains FDP and/or fibrinogen, the antibody-labeled sol particles will bind in a sandwich-type reaction to the capture anti-FDP and fibrinogen antibody producing a purple-red dot in the test result window. With a negative sample, the white test result window remains unchanged at the time of reading. AuraTek FDP has the unique feature that the test run validity is double-checked with the appearance and disappearance of color in the Reaction Control 1 window and development of a purple-red dot in the Reaction Control 2 window.

## 1.6 Substantial Equivalence
The AuraTek® FDP in vitro diagnostic device described in this application is substantially equivalent to a currently marketed test. The BARD BTA Rapid Urine Test, manufactured by Bard Diagnostic Sciences, Bard Urological Division is designed for the qualitative measurement of an analyte associated with the presence of bladder cancer in human urine. (See Table 1.0)
{5}
000014
| Table 1.0 Substantial Equivalence of AuraTek FDP with the Bard BTA Test | | |
| --- | --- | --- |
| Test Name | AuraTek FDP | Bard BTA |
| Intended Use | AuraTek FDP is a rapid one-step gold dye particle lateral flow immunoassay indicated for the [in vitro qualitative measurement] of fibrinogen and fibrin/fibrinogen degradation products (FDP) in human urine to be used with standard cystoscopic examination [to aid in the management of patients with a history of bladder cancer.] | The Bard BTA rapid latex agglutination test is an [in vitro] device intended for the [qualitative] measurement of Bladder Tumor Associated Analytes in human urine [to aid in the management of bladder cancer patients.] |
| Sample Matrix | Urine | Urine |
| Format | Rapid lateral flow immunoassay | Rapid latex agglutination test |
| Analyte | Fibrinogen and Fibrin/Fibronogen Degradation Products (FDP) | Bladder Tumor Associated Analytes |
| Limit of Detection | 30 ng Fibrinogen Equivalents (FE) / ml | 9.8 μg/ml Bladder Tumor Associated Analytes |
| Sensitivity | 68% | 40% (from package insert) |
| Specificity | 80% | 80% (from package insert) |
## 1.7 Summary of Studies
### 1.7.1 Analytical Sensitivity / Limits of Detection
The sensitivity of AuraTek FDP is approximately 30 ng FE/ml as defined by the amount of FDP (ng FE/ml) present in urine which consistently produces a positive test result. The unit, "ng FE/ml" refers to "fibrinogen equivalents". This represents the relative immunoreactivity of fibrin(ogen) degradation products derived from a predetermined quantity of fibrinogen in plasma.
{6}
000015
## 1.7.2 Reproducibility
Qualitative reproducibility studies were conducted to determine within-day, between-day, between laboratory and between-lot variability. The within-day reproducibility study was run using a negative control sample (0 ng FE/mL), a low level control (25 ng FE/ml), and a high level control (250 ng FE/mL). All controls were tested using twenty replicates at each level. The other studies were conducted using a negative control sample (0 ng FE/mL), a low level control (65 ng FE/ml), and an intermediate level control (200 ng FE/mL). All three controls were tested in duplicate using two separate lots of devices on four separate days at four different clinical sites. All reproducibility studies demonstrated total qualitative agreement at each control level
## 1.7.3 High Dose Hook (Prozone) Effect
AuraTek FDP was tested using high concentration FDP specimens to assess high dose hook effects in patient samples with high concentrations of analyte. No hook effects were seen at concentrations up to 2000 ng FE/ml.
## 1.7.4 Interfering Substances
AuraTek FDP was performed with urine specimens containing a variety of potentially interfering substances. The tests included specimens with no detectable levels of FDP, 15 ng FE (fibrinogen equivalents)/ml and 100 ng FE/ml. Whole blood and plasma may cause positive interference with AuraTek FDP at levels greater than 0.0156% volume/volume.
{7}
000016
| Substance | Highest Concentration Tested | Highest Concentration with no Interference (1) |
| --- | --- | --- |
| Hemoglobin | 225 mg/dl | 225 mg/dl |
| Albumin | 10 g/l | 10 g/l |
| Bilirubin unconjugated | 206 mg/dl | 206 mg/dl |
| Uric Acid | 250 mg/dl | 250 mg/dl |
| Disodium cromoglycate | 10 mg/l | 10 mg/l |
| Cetirizine HCl | 10 mg/l | 10 mg/l |
| Caffeine | 100 mg/l | 100 mg/l |
| Paracetamol | 500 mg/l | 500 mg/l |
| Ibuprofen | 400 mg/l | 400 mg/l |
| Acetylsalicylic Acid | 500 mg/l | 500 mg/l |
| Amoxicillin | 200 mg/l | 200 mg/l |
| Oxazepam | 25 mg/l | 25 mg/l |
| Diazepam | 20 mg/l | 20 mg/l |
| Ethanol | 2000 mg/l | 2000 mg/l |
| Desogestrel | 5 mg/l | 5 mg/l |
| Prednisone | 10 mg/l | 10 mg/l |
| Clomiphene Citrate | 50 mg/l | 50 mg/l |
| Ethinylestradiol | 5 mg/l | 5 mg/l |
| Heroin | 6 mg/l | 6 mg/l |
| Morphine | 6 mg/l | 6 mg/l |
| Tetrahydrcannabinol | 6 mg/l | 6 mg/l |
| Sodium Chloride | 100 mg/l | 100 mg/l |
| Amphetamine Sulfate | 10 mg/l | 10 mg/l |
| Chlorpromazine | 50 mg/l | 50 mg/l |
| Ascorbic Acid | 30 mg/l | 30 mg/l |
| Nicotine | 20 mg/l | 20 mg/l |
| Domperidone | 20 mg/l | 20 mg/l |
| Doxycycline | 200 mg/l | 200 mg/l |
| Methadone | 6 mg/l | 6 mg/l |
| Glucose | 10 g/l | 10 g/l |
| Red blood cells | 1 X 10^{6} / ml | 1 X 10^{6} / ml |
| White blood cells | 5 X 10^{4} / ml | 5 X 10^{4} / ml |
| Whole blood | 1% vol/vol | 0.0156% vol/vol (2) |
| Plasma | 1% vol/vol | 0.0156% vol/vol (2) |
| Serum | 1% vol/vol | 1% vol/vol |
| IgG Antibody | 6.25 mg/dl | 6.25 mg/dl |
Notes: (1) Refers to absence of both positive and negative interference.
(2) Positive interference was found at a level of 0.125% vol/vol.
{8}
000017
# Expected Results
## Clinical Sensitivity
Positive urinary FDP test results may be indicative of bladder cancer in patients with a confirmed prior history of bladder cancer. A multi-center study was performed on 192 patients with a history of bladder cancer undergoing cystoscopic examination in a general urology practice. The mean age of the group was $69.1 \pm 10.3$ years. Seventy-three percent of the subjects were male. Subject racial distribution was 181 Caucasian subjects, 1 Asian subject, 2 African American subjects, 1 Hispanic subject, 1 Pacific Islander, 1 Indian Subcontinent subject and 5 subjects of unknown racial origin. Bladder tumors were confirmed in 79 patients by positive cystoscopy results with confirmatory biopsy. The sensitivity results for the AuraTek test and urine cytology are listed in the following tables.
| Sensitivity of AuraTek FDP by Stage | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Disease Stage | Number of Subjects | AuraTek FDP Positive | AuraTek FDP 95% Confidence Interval | Cytology Positive | Cytology 95% Confidence Interval | Hemoglobin Dipstick | Hemoglobin Dipstick 95% Confidence Interval |
| All Stages | n = 79 | 68% (54/79) | 56.9-78.4% | 34% (27/79) | 23.9-45.7% | 41% (32/79) | 33.6-54.8% |
| Superficial (Tis, Ta, T1) | n = 67 | 63% (42/67) | 50.0-74.2% | 27% (18/67) | 16.8-39.1% | 36% (28/77) | 25.7-48.1% |
| Invasive (T2,T3,T4) | n = 12 | 100% (12/12) | 73.5-100% | 75% (9/12) | 42.8-94.5% | 86% (12/14) | 57.1-98.3% |
| Tis | n = 6 | 67% (4/6) | 22.3-95.7% | 50% (3/6) | 11.8-88.2% | 33% (2/6) | 4.3-77.7% |
| Ta | n = 45 | 62% (28/45) | 46.5-76.2% | 20% (9/45) | 9.6-34.6% | 24% (11/45) | 12.9-39.5% |
| T1 | n = 16 | 63% (10/16) | 35.4-84.8% | 38% (6/16) | 15.2-64.6% | 50% (8/16) | 24.7-75.4% |
{9}
000018
# Sensitivity of AuraTek FDP by Stage
Compared to Cytology and Hemoglobin Dipstick

{10}
000019
# Sensitivity of AuraTek FDP by Grade
Compared to Cytology and Hemoglobin Dipstick

{11}
000020
| Sensitivity of AuraTek FDP by Grade | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Disease Grade | Number of Subjects | AuraTek FDP Positive | AuraTek FDP 95% Confidence Interval | Cytology Positive | Cytology 95% Confidence Interval | Hemoglobin Dipstick | Hemoglobin Dipstick 95% Confidence Interval |
| All Grades | n=79 | 68% (54/79) | 56.9-78.4% | 34% (27/79) | 23.9-45.7% | 41% (32/79) | 29.6-52.2% |
| G1 | n=13 | 62% (8/13) | 31.6-86.1% | 8% (1/13) | 0.2-36.0% | 15% (2/13) | 1.9-45.5% |
| G2 | n=36 | 64% (23/36) | 46.2-79.2% | 28% (10/36) | 14.2-45.2% | 39% (14/36) | 23.1-56.5% |
| G3, G4 | n=22 | 86% (19/22) | 65.1-97.1% | 50% (11/22) | 28.2-71.8% | 73% (16/22) | 49.8-89.3% |
| Not Assigned | n=8 | 50% (4/8) | 15.7-84.3% | 63% (5/8) | 24.5-91.5% | 0% (0/8) | 0.0-36.9% |
## Specificity
Specificity was tested on a panel of normal, healthy subjects, on urology clinic patients being cystoscopically examined for recurrence of bladder cancer or suspicion of bladder cancer, and on general urology patients with a variety of non-bladder cancer urological disease.
Specificity of AuraTek FDP Healthy Subjects and Cystoscopy Negative Bladder Cancer Patients
| Subject Type | Number of Subjects | AuraTek FDP Negative | AuraTek FDP 95% Confidence Interval |
| --- | --- | --- | --- |
| Healthy subjects | n=73 | 96% (70/73) | 88.5-99.1% |
| Cystoscopy negative patients with a history of bladder cancer | n=113 | 80% (90/113) | 72.2-87.1% |
{12}
000021
| Specificity Results of AuraTek FDP on Patients with Non-Bladder Cancer Urological Disease | | | | | |
| --- | --- | --- | --- | --- | --- |
| Disease Category | Disease | Total Evaluable Subjects | AuraTek FDP Negative | Specificity | 95% Confidence Interval |
| Total | All Urological Disease | 232 | 200 | 86.2 | (81.1-90.4) |
| Prostate | Benign prostatic hypertrophy | 48 | 44 | 91.7 | (80.0-97.7) |
| | Prostatitis | 12 | 11 | 91.7 | (61.5-99.8) |
| | Prostate cancer | 40 | 34 | 85.0 | (70.2-94.3) |
| | Misc. prostate | 1 | 1 | 100 | (2.5-100.0) |
| | Total Prostate Disease | 101 | 90 | 89.1 | (81.4-94.4) |
| Renal | Renal stones | 12 | 10 | 83.3 | (51.6-97.9) |
| | Renal cell carcinoma | 10 | 9 | 90.0 | (55.8-99.7) |
| | Transitional cell carcinoma | 1 | 0 | 0 | NA |
| | Misc. renal | 3 | 1 | 33.3 | (0.8-90.6) |
| | Total Renal Disease | 26 | 20 | 76.9 | (56.4-91.0) |
| Urinary Tract Infections | Urinary tract infections | 13 | 10 | 76.9 | (46.2-95.0) |
| Bladder | Interstitial cystitis | 27 | 24 | 88.9 | (70.8-97.7) |
| | Misc. bladder disease | 5 | 3 | 60.0 | (14.7-94.3) |
| | Total Bladder Disease | 32 | 27 | 84.4 | (67.2-94.7) |
| Urodynamic | Incontinence | 25 | 23 | 92.0 | (74.0-99.0) |
| | Misc. urodynamic | 3 | 3 | 100 | (29.2-100.0) |
| | Total Urodynamic Disease | 28 | 26 | 92.9 | (76.5-99.1) |
| Testes | Testicular cancer | 5 | 5 | 100 | (47.8-100.0) |
| | Misc. testicular | 5 | 5 | 100 | (47.8-100.0) |
| | Total Testicular Disease | 10 | 10 | 100 | (63.1-100.0) |
| Miscellaneous | Misc. categories | 22 | 17 | 77.3 | (54.6-92.2) |
| Cancer* | Total Urological Cancers | 56 | 48 | 85.7 | (73.8-93.6) |
* Includes subjects from all disease categories
{13}
000022
# REFERENCES
1. Giella, J.G., Ring, K., Olsson, C.A., Karp, F.S., Benson, M.C.: The predictive value of flow cytometry and urinary cytology in the followup of patients with transitional cell carcinoma of the bladder. J. Urol., 148: 293, 1992.
2. Greene, L.F., O'Shaughnessy, E.J., Hendricks, E.D.: Study of 500 patients with asymptomatic microhematuria. JAMA, 161: 610, 1956.
3. Parry, W.L., Hemstreet, G.P.: Cancer detection by quantitative fluorescence image analysis. J. Urol., 139(2): 270, 1988
4. Cordon-Cardo, C., Wartinger, D. D., Melamed, M.R., Fair, W. Fradet, Y.: Immunopathologic analysis of human urinary bladder cancer. Characterization of two new antigens associated with low-grade superficial bladder tumors. Am. J. Pathol., 140(2): 375, 1992
5. Briggman, J.V., Merrifield, S.A., Halvorsen, M.J., Stolarek, S., et al.: Measurement of a nuclear matrix protein in the urine of patients with bladder cancer. Proc. Annu. Meet. Am. Assoc. Cancer Res., 35: A89, 1994
6. Sarosdy, M.F., Devere White, R.W., Soloway, M.S., Sheinfeld, J., Hudson, M.A., Schellhammer, P.F., Jarowenko, M.V., Adams, G., and Blumenstein, B.A.: Results of a multicenter trial using the BTA test to monitor for and diagnose recurrent bladder cancer. J. Urol., 154: 379, 1995.
7. Guirguis, R., Schiffmann, E., Liu, B., Birkbeck, D., Engel, J., Liotta, L.: Detection of autocrine motility factor in urine as a marker of bladder cancer. J. Natl. Cancer Inst., 80: 1203, 1988.
8. McCabe, R.P., Lamm, L.D., Haspel, M.V., Pomato, N., Smith, K.O., Thompson, E., Hanna, M.G., Jr.: A diagnostic-prognostic test for bladder cancer using a monoclonal antibody-based enzyme-linked immunoassay for detection of urinary fibrin(ogen) degradation products. Cancer Res., 44: 5886, 1984.
9. Wajsman, Z., Merrin, C.E., Chu, T.M., Moore, R.H., Murphy, G.P.: Evaluation of biological markers in bladder cancer. J. Urol., 114: 879, 1975.
10. Jayachandran, S., Unni Mooppan, M.M., Wax, S.H., Kim, H.: The value of urinary fibrin/fibrinogen degradation products as tumor markers in urothelial carcinoma. J. Urol., 132(1): 21, 1984.
11. Sofras, F., Nikolopoulou, R., Karagiannis, A., Kostakopoulos, A., et al.: Fibrin fibrinogen degradation products in bladder tumors. European Urol., 18(suppl. 1): 31, 1990.
12. Marder, V.J., Budzynski, A.Z.: The structure of the fibrinogen degradation products. In: Progress in Hemostasis and Thrombosis. Edited by T. H. Spaet. New York: Grune & Stratton, vol. 2, pp 141-174, 1974.
{14}
000023
13. Nagy, J.A., Brown, L.F., Senger, D.R., Lanir, N., Van De Water, L., Dvorak, A. M., Dvorak, H.F.: Pathogenesis of tumor stroma generation: a critical role for leaky blood vessels and fibrin deposition. Biochem. Biophys. Acta, 948: 305, 1988.
14. Brown, L.F., Berse, B., Jackman, R.W., Tognazzi, K., Manseau, E.J., Dvorak, H.F., Senger, D.R.: Increased expression of vascular permeability factor (vascular endothelial growth factor) and its receptors in kidney and bladder carcinomas. Am. J. Pathol., 143: 1255, 1993.
15. O'Brien, T., Cranston, D., Fuggle, S., Bicknell, R., Harris, A.L.: Different angiogenic pathways characterize superficial and invasive bladder cancer. Cancer Res., 55: 510, 1995.
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.