K092355 · Bio-Rad Laboratories, Inc. · LOL · Oct 29, 2009 · Microbiology
Device Facts
Record ID
K092355
Device Name
MONOLISA ANTI-HAV EIA
Applicant
Bio-Rad Laboratories, Inc.
Product Code
LOL · Microbiology
Decision Date
Oct 29, 2009
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.3310
Device Class
Class 2
Attributes
Real-World Evidence, Pediatric
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K092355 · Oct 29, 2009
MONOLISA ANTI-HAV EIA
Bio-Rad Laboratories, Inc.
Retrospective clinical samples
Retrospective clinical samples were used to compare the performance of the MONOLISA Anti-HAV assay on the EVOLIS Automated Microplate System against the manual reference method.
Clinical serum/plasma samples; Sample Size: 688; Number of Sites: 3
Manual MONOLISA Anti-HAV assay
Positive and negative percent agreement
Indications for Use
The MONOLISA™ Anti-HAV EIA is an in vitro enzyme immunoassay kit intended for use in the qualitative detection of total antibodies (IgG and IgM) to hepatitis A virus (anti-HAV) in human (adult and pediatric) serum or plasma (EDTA, Heparin, Citrate, ACD). This kit can be used as an aid in the diagnosis of acute or past hepatitis A virus (HAV) infection or as an aid in the identification of HAV-susceptible individuals for vaccination. However, any diagnosis should take into consideration the patient's clinical history and symptoms, as well as serological data. The MONOLISA™ Anti-HAV EIA is intended for manual use and with the Evolis™ Automated Microplate System in the detection of total antibodies to hepatitis A virus. Assay performance characteristics have not been established for immunocompromised or immunosuppressed patients, and cord blood or neonatal specimens. Warning: This assay is not intended for screening blood or solid or soft tissue donors.
Device Story
MONOLISA™ Anti-HAV EIA is a competitive enzyme immunoassay for detecting total anti-HAV antibodies. Input: human serum/plasma samples. Process: samples incubated with HAV antigen in microwells coated with mouse monoclonal anti-HAV; conjugate (HRP-labeled mouse monoclonal anti-HAV) added; TMB chromogen/substrate solution added. If anti-HAV is absent, HRP binds, turning solution blue (yellow after stop solution). If anti-HAV is present, solution remains colorless. Output: spectrophotometric absorbance intensity compared to cutoff value. Used in clinical laboratories; operated by technicians. EVOLIS™ Automated Microplate System automates sample/reagent dispensing, barcode scanning, incubation, washing, and photometric measurement. Results assist clinicians in diagnosing HAV infection or assessing vaccination needs.
Clinical Evidence
Clinical performance evaluated via method comparison study of 688 retrospective samples tested on both manual and EVOLIS platforms. Positive percent agreement: 98.8% (95% CI: 97.0–99.5%); negative percent agreement: 97.4% (95% CI: 95.2–98.6%). A secondary study of 315 samples using combination plate formats showed 100% agreement (95% CI: 97.7–100% positive; 97.6–100% negative). Precision/reproducibility validated across 3 sites using 21-member and 6-member panels per CLSI EP5-A2; total %CVs ranged from 5.9% to 18.1%.
Technological Characteristics
Enzyme immunoassay (competitive format). Photometric measurement (450 nm filter, 620 nm reference). Automated system (EVOLIS™) performs barcode scanning, sample/reagent dispensing, incubation (60 min at 37°C), and washing (5 cycles, 370 µL/well). Connectivity: standalone analyzer with dedicated PC. Software-controlled.
Indications for Use
Indicated for qualitative detection of total anti-HAV (IgG and IgM) in human adult and pediatric serum or plasma. Used as aid in diagnosis of acute/past HAV infection or identification of HAV-susceptible individuals for vaccination. Not for screening blood/tissue donors. Performance not established for immunocompromised/immunosuppressed patients, cord blood, or neonates.
Regulatory Classification
Identification
HAV serological assays are devices that consist of antigens and antisera for the detection of hepatitis A virus-specific IgM, IgG, or total antibodies (IgM and IgG), in human serum or plasma. These devices are used for testing specimens from individuals who have signs and symptoms consistent with acute hepatitis to determine if an individual has been previously infected with HAV, or as an aid to identify HAV-susceptible individuals. The detection of these antibodies aids in the clinical laboratory diagnosis of an acute or past infection by HAV in conjunction with other clinical laboratory findings. These devices are not intended for screening blood or solid or soft tissue donors.
Special Controls
*Classification.* Class II (special controls). The special control is “Guidance for Industry and FDA Staff: Class II Special Controls Guidance Document: Hepatitis A Virus Serological Assays.” See § 866.1(e) for the availability of this guidance document.
{0}
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K092355
B. Purpose for Submission:
This is a new 510k application for a new indication for the MONOLISA™ Anti-HAV EIA with the EVOLIST™ Automated Microplate System. The MONOLISA™ Anti-HAV EIA was previously cleared with a manual assay procedure.
C. Measurand:
Antibody to Hepatitis A (Total)
D. Type of Test:
Enzyme immunoassay (competitive assay format)
E. Applicant:
Bio-Rad Laboratories
F. Proprietary and Established Names:
MONOLISA Anti-HAV EIA/Hepatitis A test (Total Antibody)
EVOLIS Automated Microplate System/Automated Laboratory Analyzer
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| LOL | Class II | 21 CFR 866.3310 | Microbiology (83) |
| JJE | Class I | 21 CFR 862.2160 | Chemistry (75) |
H. Intended Use:
1. Intended use:
The MONOLISA Anti-HAV EIA is an in vitro enzyme immunoassay kit intended for use in the qualitative detection of total antibodies (IgG and IgM) to hepatitis A virus (anti-HAV) in human (adult and pediatric) serum or plasma (EDTA, Heparin, Citrate, ACD). This kit can be used as an aid in the diagnosis of acute or past hepatitis A virus (HAV) infection or as an aid in the identification of HAV-susceptible individuals for vaccination. However, any diagnosis should take into consideration the patient's clinical history and
{1}
K092355
symptoms, as well as serological data. The MONOLISA Anti-HAV EIA is intended for manual use and with the Evolis™ Automated Microplate System in the detection of total antibodies to hepatitis A virus.
Assay performance characteristics have not been established for immunocompromised or immunosuppressed patients, and cord blood or neonatal specimens.
WARNING: This assay is not intended for screening blood or solid or soft tissue donors.
2. Indication(s) for use:
Same as Intended Use
3. Special conditions for use statement(s):
For prescription use only.
4. Special instrument requirements:
The assay may be run using a manual method or with the EVOLIS Automated Microplate System.
I. Device Description:
The MONOLISA Anti-HAV EIA 192 test kit contains the following components:
- 2 Microwell strip plates. Wells are coated with monoclonal anti-HAV
- Wash Solution Concentrate – Tris NaCl buffer, ProClin, Tween 20
- Negative Control – Human serum negative for total anti-HAV antibodies
- Positive Control – Human serum positive for anti-HAV antibodies
- Calibrator – Human serum positive for anti-HAV antibodies
- HAV Viral antigen – inactivated HAV virus in Tris buffer and ProClin
- Conjugate – Peroxidase labeled mouse monoclonal antibody to HAV in Tris buffer
- Substrate buffer – H₂O₂, buffer, DMSO
- Chromogen - TMB
- Stopping solution – 1N H₂SO₄
The EVOLIS Automated Microplate System is an automated microplate analyzer that performs all functions necessary for processing microplate assays. Functions include: barcode scanning, sample pre-dilutions, sample and reagent dispensing, plate incubations, plate wash cycles, photometric measurement of completed assay plates and results evaluation. The analyzer instrument is controlled via the EVOLIS software, a Windows 2000 application running on a separate dedicated PC. An operator loads the appropriate microplates, assay reagents, and patient and control samples, then selects assay parameters, loads sample information, initiates instrument processing, and generates results reports.
J. Substantial Equivalence Information:
{2}
K092355
1. Predicate device names:
MONOLISA Anti-HAV EIA
2. Predicate 510(k) number(s):
K063318
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended Use/Indications for Use | An in vitro enzyme immunoassay kit intended for use in the qualitative detection of total antibodies (IgG and IgM) to hepatitis A virus (anti-HAV) in human (adult and pediatric) serum or plasma (EDTA, Heparin, Citrate, ACD) | An in vitro enzyme immunoassay kit intended for use in the qualitative detection of total antibodies (IgG and IgM) to hepatitis A virus (anti-HAV) in human (adult and pediatric) serum or plasma (EDTA, Heparin, Citrate, ACD) |
| Assay procedure | Per the instructions in the package insert | Per the instructions in the package insert |
| Plate incubation | 60 ± 5 minutes at 37°C + 2°C | 60 ± 5 minutes at 37°C + 2°C |
| Plate washing | Wash with ≥ 370 μL of Working Wash Solution per well, and 30 - 60 second soak between each wash cycle for a total of 5 cycles. | Wash with ≥ 370 μL of Working Wash Solution per well, and 30 - 60 second soak between each wash cycle for a total of 5 cycles. |
| Result interpretation | Result interpretations, based on sample O.D.s, are determined according to package insert criteria. | Result interpretations, based on sample O.D.s, are determined according to package insert criteria. |
| Photometric measurement of completed assay plates | Read absorbance using 450 nm filter with 620 nm as the reference | Read absorbance using 450 nm filter with 615 to 630 nm as the reference |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Sample and reagent dispensing | Samples and reagents are dispensed by the automated system | Samples and reagents are dispensed manually |
| Barcode reading | Sample and reagent ID are verified automatically | NA or can be performed manually with barcode |
{3}
K092355
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | | wand |
| Plate incubation | Plates are automatically moved to the incubation chamber | Plates are moved manually to an incubation chamber |
| Plate wash cycles | Plates are automatically washed | Plates are moved manually to an automated plate washer |
| Data management | Archives and retrieves data and sample information | NA |
| Spectrophotometric verification of sample and reagent pipeting | Performed automatically | Optional verification visually or with microplate reader |
## K. Standard/Guidance Documents Referenced:
- Guidance on Informed Consent for In Vitro Diagnostic Device Studies Leftover Human Specimens that are Not Individually Identifiable (April 2006)
- Statistical Guidance on Reporting Results from Studies Evaluating Diagnostic Tests; Guidance for Industry and FDA Reviewers (March 2007)
- Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (May 2005)
- Evaluation of Precision Performance of Qualitative Measurement Methods, CLSI EP5-A2
- User Protocol for Evaluation of Qualitative Test Performance, CLSI EP15-A2
## L. Test Principle:
Patient specimens, a Calibrator and controls are incubated with HAV antigen in microwells that have been coated with mouse monoclonal anti-hepatitis A antibodies. Antibodies to HAV present in a specimen or control will complex with the HAV antigen reagent and with antibodies coated on the microwells. Excess sample and HAV Viral Antigen reagent are removed by a wash step. The Conjugate (containing horseradish peroxidase-labeled mouse monoclonal antibody to HAV) is subsequently added to the microwells and incubated. The Conjugate binds to the HAV antigen bound to the microwell, in the absence of antibodies to HAV from the specimen. Excess Conjugate is removed by a wash step, and a TMB Chromogen/Substrate solution is added to the microwells and allowed to incubate. If a sample does not contain anti-HAV antibodies, the bound enzyme (HRP) causes the colorless tetramethylbenzidine (TMB) in the Chromogen solution to change to blue. The blue color turns yellow after the addition of a Stopping Solution. If a sample contains anti-HAV antibodies, the Chromogen/Substrate solution in the well remains colorless during the substrate incubation, and after the addition of the Stopping Solution. The color intensity is measured spectrophotometrically. Absorbance value readings for patient specimens are compared to the Cutoff value determined by the mean of the Calibrator absorbance values.
{4}
K092355
# M. Performance Characteristics:
# 1. Analytical performance:
# a. Precision/Reproducibility:
A 21-member panel consisting of the following was tested: three (3) serum samples with six (6) corresponding plasma samples (EDTA K2, EDTA K3, Sodium Citrate, Sodium Heparin, Lithium Heparin, ACD) at three (3) different levels [1 low positive near the cutoff (Panel Set 1), 1 negative near the cutoff (Panel Set 2) and 1 negative (Panel Set 3)]. The kit controls and calibrator were also tested for a total of 24 samples. Two replicates each of the twenty-four (24) samples were assayed twice a day for 20 days. The data were analyzed per CLSI guidance EP5A2. The mean ratio, the Standard Deviation (SD) and percent coefficient of variation (%CV) were calculated for each panel member.
| Panel Member | N | Mea n CO/S | Within run1 | | Between Run2 | | Between Day3 | | Total4 | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | CV (%) | SD | CV (%) | SD | CV (%) | SD | CV (%) |
| Positive Control | 80 | 4.63 | 0.21 | 4.5 | 0.31 | 6.7 | 0.75 | 16.2 | 0.84 | 18.1 |
| High Negative | 765 | 0.36 | 0.01 | 3.4 | 0.02 | 6.4 | 0.01 | 4.1 | 0.03 | 8.3 |
| Cutoff Control | 80 | 0.91 | 0.03 | 3.5 | 0.07 | 7.4 | 0.10 | 10.8 | 0.12 | 13.6 |
| Serum (1) | 80 | 1.13 | 0.05 | 4.6 | 0.06 | 5.3 | 0.11 | 9.5 | 0.13 | 11.8 |
| EDTA K2 (1) | 80 | 1.16 | 0.04 | 3.7 | 0.06 | 5.5 | 0.08 | 6.9 | 0.11 | 9.6 |
| EDTA K3 (1) | 80 | 1.16 | 0.04 | 3.8 | 0.09 | 7.9 | 0.08 | 6.7 | 0.13 | 11 |
| Sodium Citrate (1) | 80 | 1.12 | 0.05 | 4.2 | 0.09 | 8.0 | 0.08 | 7.5 | 0.13 | 11.8 |
| Sodium Heparin (1) | 80 | 1.24 | 0.06 | 4.9 | 0.08 | 6.8 | 0.11 | 9.0 | 0.15 | 12.3 |
| Lithium Heparin (1) | 80 | 1.18 | 0.04 | 3.1 | 0.08 | 6.6 | 0.12 | 10.2 | 0.15 | 12.5 |
| ACD (1) | 80 | 0.4 | 0.01 | 2.7 | 0.03 | 6.4 | 0.04 | 9.4 | 0.05 | 11.7 |
| Serum (2) | 80 | 0.64 | 0.02 | 3.6 | 0.03 | 5.1 | 0.02 | 3.4 | 0.05 | 7.1 |
| EDTA K2 (2) | 80 | 0.63 | 0.02 | 3.4 | 0.04 | 6.0 | 0.03 | 4.8 | 0.05 | 8.4 |
| EDTA K3 (2) | 80 | 0.62 | 0.02 | 3.1 | 0.04 | 7.0 | 0.03 | 4.9 | 0.06 | 9.1 |
| Sodium Citrate (2) | 80 | 0.63 | 0.02 | 3.1 | 0.04 | 7.0 | 0.04 | 5.9 | 0.06 | 9.7 |
| Sodium Heparin (2) | 80 | 0.68 | 0.02 | 3.3 | 0.04 | 6.2 | 0.07 | 10.4 | 0.09 | 12.6 |
| Lithium Heparin (2) | 80 | 0.61 | 0.02 | 3.2 | 0.04 | 6.1 | 0.04 | 7.1 | 0.06 | 9.9 |
| ACD (2) | 80 | 0.59 | 0.01 | 2.4 | 0.04 | 7.0 | 0.06 | 9.8 | 0.07 | 12.3 |
| Serum (3) | 80 | 0.41 | 0.01 | 1.9 | 0.03 | 6.3 | 0.02 | 4.7 | 0.03 | 8.1 |
| EDTA K2 (3) | 80 | 0.41 | 0.02 | 4.6 | 0.03 | 7.7 | 0.02 | 4.1 | 0.04 | 9.9 |
| EDTA K3 (3) | 80 | 0.41 | 0.01 | 3 | 0.03 | 7.1 | 0.02 | 4.6 | 0.04 | 8.9 |
| Sodium Citrate (3) | 80 | 0.43 | 0.01 | 2.7 | 0.03 | 6.5 | 0.02 | 4.9 | 0.04 | 8.6 |
| Sodium Heparin (3) | 80 | 0.43 | 0.01 | 2 | 0.03 | 5.9 | 0.04 | 9.1 | 0.05 | 11 |
| Lithium Heparin (3) | 80 | 0.4 | 0.01 | 3.5 | 0.03 | 6.8 | 0.04 | 9.2 | 0.05 | 12 |
| ACD (3) | 80 | 1.07 | 0.04 | 3.4 | 0.08 | 7.6 | 0.14 | 13.2 | 0.17 | 15.6 |
1 Within Run: variability of the assay performance from replicate to replicate
2 Between Run: variability of the assay performance from Run to Run
3 Between Day: variability of the assay performance from Day to Day
4 Total: Total variability of the assay performance includes within run, between run and between days
5 4 replicates did not meet volume verification requirements
A 6-member panel consisting of diluted plasma specimens (negative and different levels of positive) was tested in triplicate, once a day for 5 days with the MONOLISA™ Anti-HAV EIA
{5}
K092355
at 3 separate clinical trial sites. Each panel was coded with a different number on each day tested in order to blind the operator to the expected value of the sample. One (1) lot was used at each of 3 sites.
| Panel Member | N | Mean CO/S | Within Run1 | | Between Day2 | | Between Site3 | | Total4 | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| P1 | 90 | 0.41 | 0.02 | 5.7 | 0.01 | 1.2 | 0.00 | 1.1 | 0.02 | 5.9 |
| P2 | 90 | 0.8 | 0.05 | 5.6 | 0.03 | 4.1 | 0.01 | 1.7 | 0.06 | 7.2 |
| P3 | 90 | 1.3 | 0.06 | 4.9 | 0.05 | 4.2 | 0.005 | 0 | 0.08 | 6.4 |
| P4 | 90 | 2.13 | 0.14 | 6.6 | 0.09 | 4.3 | 0.005 | 0 | 0.17 | 7.9 |
| P5 | 90 | 2.82 | 0.13 | 4.5 | 0.16 | 5.6 | 0.005 | 0 | 0.20 | 7.1 |
| P6 | 90 | 4.04 | 0.16 | 3.9 | 0.27 | 6.8 | 0.005 | 0 | 0.32 | 7.8 |
| P7 | 90 | 3.69 | 0.17 | 4.6 | 0.28 | 7.5 | 0.005 | 0 | 0.32 | 8.8 |
| P8 | 87 | 0.38 | 0.02 | 5.1 | 0.01 | 3.1 | 0.005 | 0 | 0.02 | 6.0 |
| P9 | 87 | 0.95 | 0.06 | 5.9 | 0.04 | 4.0 | 0.005 | 0 | 0.07 | 7.1 |
Within run: Variability of the assay performance from replicate to replicate
2 Between day: Variability of the assay performance from day to day
3 Between site: Variability of the assay performance from site to site
4 Total: Total variability of the assay performance includes within run, between days and between sites
5 Negative variances were rounded to zero, per statistical convention
b. Linearity/assay reportable range:
See K063318
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
See K063318
d. Detection limit:
See K063318
e. Analytical specificity:
See K063318
f. Assay cut-off:
See K063318
2. Comparison studies:
a. Method comparison with predicate device:
{6}
K092355
Six-hundred eighty-eight retrospective samples were tested on the MONOLISA Anti-HAV assay, using a total of four (4) EVOLIS instruments at three sites. The same samples were tested manually (reference method) on the MONOLISA Anti-HAV assay. Specimens that were borderline with the reference assay and negative with EVOLIS were considered as false negative for the EVOLIS; specimens that were borderline with the reference assay and reactive with EVOLIS were considered as false positive for the EVOLIS.
| Manual Anti-HAV Results | EVOLIS Anti-HAV Results | | | |
| --- | --- | --- | --- | --- |
| | Reactive | Borderline | Nonreactive | Total |
| Reactive | 336 | 2 | 1 | 339 |
| Borderline | 2 | 0 | 1 | 3 |
| Nonreactive | 2 | 5 | 339 | 346 |
| Total | 340 | 7 | 341 | 688 |
The positive percent agreement with the reference method, manual testing, is 98.8% (336/340) with a 95% confidence interval of 97.0 – 99.5%. The negative percent agreement with the reference method is 97.4% (339/348) with a 95% confidence interval of 95.2 – 98.6%.
The EVOLIS was also evaluated by performing a combination of 2 assays on the same plate frame. In this study 315 samples were tested with the MONOLISA Anti-HAV assay on a combination plate on the EVOLIS (both the MONOLISA Anti-HAV EIA and MONOLISA Anti-HAV IgM EIA assays were run in a single microplate frame). Results were compared to the same samples tested manually (the reference method, individual plate format) on the MONOLISA Anti-HAV assay. Specimens that were borderline with the reference assay (manual individual plate) and negative with EVOLIS (combination plate) were considered as false negative for the EVOLIS (combination plate).
| Manual Anti-HAV Results - Individual Plate | EVOLIS™ Anti-HAV Results - Combination Plate | | | |
| --- | --- | --- | --- | --- |
| | Reactive | Borderline | Nonreactive | Total |
| Reactive | 161 | 0 | 0 | 161 |
| Borderline | 0 | 0 | 0 | 0 |
| Nonreactive | 0 | 0 | 154 | 154 |
| Total | 161 | 0 | 154 | 315 |
The positive percent agreement with the reference method, manual testing, is 100% (161/161) with a 95% confidence interval of 97.7 – 100%. The negative percent agreement with the reference method is 100% (154/154) with a 95% confidence interval of 97.6 – 100%.
b. Matrix comparison:
See K063318
{7}
K092355
3. Clinical studies:
a. Clinical Sensitivity:
See K063318
b. Clinical specificity:
See K063318
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:
See K063318
N. Instrument Name:
EVOLIS Automated Microplate System
O. System Descriptions:
1. Modes of Operation:
The EVOLIS Automated Microplate System is an open tube, batch mode analyzer with a continuous load option. The reagent bottles used from the test kit are placed on the instrument with the caps removed. The sample tubes can be the primary tubes with stoppers removed or the serum/plasma can be poured off into identified test tubes.
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☐ X ☑ or No ☐
3. Specimen Identification:
Specimen information may be entered either by EVOLIS system barcode reading directly off the specimen tube or entered manually by the user.
{8}
K092355
4. Specimen Sampling and Handling:
The system can store and distribute samples from different types of vessels into dilution vessels and microplates. The samples can be accessed in any order. Sample addition is via a 300 µL disposable tip. The system can load and unload samples and assay reagents while it is operating.
The pipetting system utilizes a liquid syringe pump and system fluid. The system uses disposable tips (300 µL and 1100 µL), and can aspirate and dispense fluids from a variety of different vessels. Key functions of the system are liquid level detection, using capacitive sensing, verification of fluid distribution, and the detection of clots and blocked tips. If the pipettor does not detect a sufficient volume an error is displayed. The pipettor automatically flushes with system fluid between each aspirate/dispense cycle of samples and reagent during a pipetting sequence. Mixing occurs during the transfer of sample, addition of diluents, and other reagents.
Intermediate vessels are used to dilute samples when the level of dilution exceeds the volume available in the final reaction vessel. Mixing is utilized to obtain a homogeneous mixture after preparing the dilution. The instrument has space for at least one microplate to be used as a dilution position.
5. Calibration:
The system performs a self-test each time EVOLIS software is launched. During the self-test the instrument hardware is initialized and the status of all instrument modules is verified. The self-test evaluates the following systems: Pipettor, washer, photometer, plate transport, incubators, system communications, and other user-defined maintenance.
Users are instructed in the Operator's Manual to perform the following Performance Evaluation Procedures monthly: Plate Transport Check, Photometer Verification Check, Fluidics Panel Check.
6. Quality Control:
Assay includes positive and negative controls that are run with each batch.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
N/A
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.
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.