Wondfo 2019-nCoV Antigen Test (Lateral Flow Method)
Applicant
Guangzhou Wondfo Biotech Co., Ltd.
Product Code
QYT · Microbiology
Decision Date
Sep 30, 2024
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.3984
Device Class
Class 2
Attributes
Real-World Evidence, Pediatric
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K241317 · Sep 30, 2024
Wondfo 2019-nCoV Antigen Test (Lateral Flow Method)
Guangzhou Wondfo Biotech Co., Ltd.
NIH and University of Massachusetts Chan Medical School prospective cohort study data (Test Us at Home)
The FDA-referenced external cohort studies support the clinical utility and performance of the serial testing protocol required for the device's intended use, specifically to mitigate the risk of false negatives.
Serial testing; COVID-19 antigen test; Prospective cohort study; Clinical mitigation
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Test Us at Home prospective cohort study; Prospective cohort study
Individuals undergoing serial rapid antigen testing for SARS-CoV-2
Not applicable for this study
Performance of serial rapid antigen testing to detect symptomatic and asymptomatic SARS-CoV-2 infection
Indications for Use
The Wondfo 2019-nCoV Antigen Test (Lateral Flow Method) is a visually read lateral flow immunoassay test intended for the qualitative detection of SARS-CoV-2 virus nucleocapsid protein antigen directly in anterior nasal swab specimens from individuals with signs and symptoms of COVID-19. This test is for non-prescription home use by individuals aged 14 years or older testing themselves, or adults testing individuals aged 2 years or older. All negative results are presumptive. Symptomatic individuals with an initial negative test result must be re-tested once between 48 and 72 hours after the first test using either an antigen test or a molecular test for SARS-CoV-2. Negative results do not rule out SARS-CoV-2 infections or other pathogens and should not be used as the sole basis for treatment. Positive results do not rule out co-infection with other respiratory pathogens. This test is not a substitute for visits to a healthcare provider or appropriate follow-up and should not be used to determine any treatments without provider supervision. Individuals who test negative and experience continued or worsening COVID-19 like symptoms, such as fever, cough and/or shortness of breath, should seek follow up care from their healthcare provider. The performance characteristics for SARS-CoV-2 were established from April, 2023 to February, 2024 when SARS-CoV-2 Omicron was dominant. Test accuracy may change as new SARS-CoV-2 viruses emerge. Additional testing with a lab-based molecular test (e.g., PCR) should be considered in situations where a new virus or variant is suspected.
Device Story
Lateral flow immunoassay for qualitative detection of SARS-CoV-2 nucleocapsid protein antigen; utilizes anterior nasal swab samples. User collects sample; inserts into pre-filled extraction buffer tube to disrupt virus; adds extracted specimen to test cassette sample well. Specimen migrates via capillary action across nitrocellulose membrane; SARS-CoV-2 antigens bind to dye-conjugated antibodies; sandwich complexes captured at test line (T) by immobilized antibodies; control line (C) indicates valid flow. Visually read by user 10-20 minutes post-application. Home-use device; intended for symptomatic individuals. Negative results are presumptive; requires serial testing (re-test 48-72 hours later) to mitigate false negatives. Provides rapid identification of SARS-CoV-2; supports clinical decision-making regarding isolation and follow-up care.
Clinical Evidence
Prospective lay-person clinical study (n=1,032 evaluable subjects) conducted April 2023–February 2024. Compared candidate test to 510(k)-cleared RT-PCR assay. Results: PPA 84.38% (95% CI: 77.10%–89.65%); NPA 99.67% (95% CI: 99.03%–99.89%). Usability study (n=30) confirmed lay-user ability to perform critical tasks. Readability/comprehension study (n=50) showed high accuracy in interpreting mock test results.
Technological Characteristics
Lateral flow immunoassay; nitrocellulose membrane with test (T) and control (C) lines; dye-conjugated antibody technology. Components: test cassette, extraction buffer tube, swab, tube holder. Storage: 2°C to 30°C. Visual readout. No electronic components or software.
Indications for Use
Indicated for qualitative detection of SARS-CoV-2 nucleocapsid protein antigen in anterior nasal swab specimens from symptomatic individuals. For non-prescription home use by individuals aged 14+ testing themselves, or adults testing individuals aged 2+.
Regulatory Classification
Identification
For the rapid, qualitative detection of SARS-CoV-2 virus nucleocapsid protein antigen in individuals 2 years and older.
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K241317
B Applicant
Guangzhou Wondfo Biotech Co., Ltd.
C Proprietary and Established Names
Wondfo 2019-nCoV Antigen Test (Lateral Flow Method)
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QYT | Class II | 21 CFR 866.3984 - Over-The-Counter Test To Detect SARS-Cov-2 From Clinical Specimens | MI - Microbiology |
## II Submission/Device Overview:
A Purpose for Submission:
The purpose of this submission is to request premarket notification 510(k) clearance for the Wondfo 2019-nCoV Antigen Test (Lateral Flow Method).
B Measurand:
Nucleocapsid protein antigen from SARS-Coronavirus 2 (SARS-CoV-2)
C Type of Test:
Qualitative lateral flow immunoassay
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The Wondfo 2019-nCoV Antigen Test (Lateral Flow Method) is a visually read lateral flow immunoassay test intended for the qualitative detection of SARS-CoV-2 virus nucleocapsid protein antigen directly in anterior nasal swab specimens from individuals with signs and symptoms of COVID-19.
This test is for non-prescription home use by individuals aged 14 years or older testing themselves, or adults testing individuals aged 2 years or older.
All negative results are presumptive. Symptomatic individuals with an initial negative test result must be re-tested once between 48 and 72 hours after the first test using either an antigen test or a molecular test for SARS-CoV-2. Negative results do not rule out SARS-CoV-2 infections or other pathogens and should not be used as the sole basis for treatment.
Positive results do not rule out co-infection with other respiratory pathogens.
This test is not a substitute for visits to a healthcare provider or appropriate follow-up and should not be used to determine any treatments without provider supervision. Individuals who test negative and experience continued or worsening COVID-19 like symptoms, such as fever, cough and/or shortness of breath, should seek follow up care from their healthcare provider.
The performance characteristics for SARS-CoV-2 were established from April 2023 to February 2024 when SARS-CoV-2 Omicron was dominant. Test accuracy may change as new SARS-CoV-2 viruses emerge. Additional testing with a lab-based molecular test (e.g., PCR) should be considered in situations where a new virus or variant is suspected.
C Special Conditions for Use Statement(s):
OTC - Over The Counter
D Special Instrument Requirements:
Not applicable.
IV Device/System Characteristics:
A Device Description:
The Wondfo 2019-nCoV Antigen Test (Lateral Flow Method) is a lateral flow immunoassay intended for non-prescription home use for the qualitative detection of nucleocapsid protein antigen directly in anterior nasal swab specimens from individuals with signs and symptoms of COVID-19 within the first five (5) days of symptom onset. Results are for the identification of SARS-CoV-2 nucleocapsid protein antigen.
K241317 - Page 2 of 18
{2}
The Wondfo 2019-nCoV Antigen Test (Lateral Flow Method) is consisted of components below:
- Tube Holder (located in kit box)
- Test Cassette
- Tube (pre-filled extraction buffer)
- Swab
- Instruction for Use
The test cassette is assembled with a test strip in a plastic housing that contains a nitrocellulose membrane with two lines: a test line (T line) and a control line (C line).
## B Principle of Operation:
The Wondfo 2019-nCoV Antigen Test is a sandwich immunochromatographic assay that uses antibodies to detect SARS-CoV-2 nucleocapsid antigen in anterior nasal swab specimen. A nasal swab sample is collected by the lay user and then inserted into the extraction buffer that disrupts the virus particles in the specimen to expose internal viral nucleocapsid antigens. The extracted specimen is then added into the sample well of the test cassette. When an adequate volume of the specimen is added to the sample well (S) of the test cassette, the specimen migrates by capillary action from the sample well over the conjugated pad and across the nitrocellulose membrane test strip. During the migration, the reagents contained in the conjugated pad are solubilized. If SARS-CoV-2 nucleocapsid antigens are present in the sample, the antigens bind to the specific annti-SARS-CoV-2 antibody that is conjugated with dye particles. These antigen-antibody complexes are captured by the anti-SARS-CoV-2 antibody immobilized at the test line region (T) to form sandwich complexes that generate a visible colored test line. Unbound conjugate molecules continue to migrate across the nitrocellulose membrane and are captured at the control line region (C) to result in a visible colored control line that indicates adequate operations and sample flow during the test. If no SARS-CoV-2 nucleocapsid antigens are present in the sample, the conjugate will only be captured at the control line of the test.
Results are interpreted between 10 and 20 minutes after adding the extracted sample into the sample well. A false negative or false positive result may occur if the test result before 10 minutes or after 20 minutes.
## V Substantial Equivalence Information:
### A Predicate Device Name(s):
Flowflex COVID-19 Antigen Home Test
### B Predicate 510(k) Number(s):
K230828
K241317 - Page 3 of 18
{3}
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K241317 | K230828 |
| --- | --- | --- |
| Device Trade Name | Wondfo 2019-nCoV Antigen Test (Lateral) | Flowflex COVID-19 Antigen Home Test |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | The Wondfo 2019-nCoV Antigen Test (Lateral Flow Method) is a visually read lateral flow immunoassay test intended for the qualitative detection of SARS-CoV-2 virus nucleocapsid protein antigen directly in anterior nasal swab specimens from individuals with signs and symptoms of COVID-19. | The Flowflex COVID-19 Antigen Home Test is a visually read lateral flow immunoassay device intended for the rapid, qualitative detection of SARS-CoV-2 virus nucleocapsid protein antigen directly in anterior nasal swab specimens from individuals with signs and symptoms of COVID-19 within the first 6 days of symptom onset. |
| | This test is for non-prescription home use by individuals aged 14 years or older testing themselves, or adults testing individuals aged 2 years or older. Wondfo 2019-nCoV Antigen Test (Lateral Flow Method) does not differentiate between SARS-CoV and SARS-CoV-2. | This test is for non-prescription home use by individuals aged 14 years or older testing themselves, or adults testing individuals aged 2 years or older. The Flowflex COVID-19 Antigen Home Test does not differentiate between SARS-CoV and SARS-CoV-2. |
| | All negative results are presumptive. Symptomatic individuals with an initial negative test result must be re-tested once between 48 and 72 hours after the first test using either an antigen test or a molecular test for SARS-CoV-2. Negative results do not rule out SARS-CoV-2 infections or other pathogens and should not be used as the sole basis for treatment. | All negative results are presumptive. Symptomatic individuals with an initial negative test result must be re-tested once between 48 and 72 hours after the first test using an antigen test or a molecular test for SARS-CoV-2. Negative results do not preclude SARS-CoV-2 infections or other pathogens and should not be used as the sole basis for treatment. |
| | Positive results do not rule out co-infection with other respiratory pathogens. | Positive results do not rule out co-infection with other respiratory pathogens. |
| | This test is not a substitute for visits to a healthcare provider or appropriate follow-up and should not be used to determine any treatments without provider | Performance characteristics for SARS-CoV-2 were established from December 2022 to March 2023 of the SARS-CoV-2 pandemic when SARS-CoV-2 Omicron was the |
K241317 - Page 4 of 18
{4}
VI Standards/Guidance Documents Referenced:
| Document Title | Issued by | Applicable study |
| --- | --- | --- |
| Special controls for Over- the-counter test to detect SARS-CoV-2 from clinical specimens (Reclassification order for DEN220028 and special controls under 21 CFR 866.3984) | FDA/CDRH | All Studies |
| Guidance: Submission and review of sterility information in premarket notification (510(k)) submissions for devices labeled as sterile. | FDA/CDRH | Sterility |
| Guidance: Use of International Standard ISO 10993-1, "Biological evaluation of medical devices - Part 1: | FDA/CDRH | Biocompatibility |
K241317 - Page 5 of 18
{5}
| Document Title | Issued by | Applicable study |
| --- | --- | --- |
| Evaluation and testing within a risk management process" | | |
| Standard: ISO 11135:2014, Sterilization of health care products - Ethylene oxide - Requirements for development, validation and routine control of a sterilization process for medical devices | ISO | Sterility |
| Standard: ISO 10993-7, Biological Evaluation of Medical Devices – Part 7: Ethylene Oxide Sterilization Residuals | | |
| Standard: ISO 10993-1, Biological Evaluation of Medical Devices – Part 1: Evaluation and testing within a risk management process | ISO | Biocompatibility |
| Standard: ISO 10993-5, Third edition, Biological evaluation of medical devices – Part 5: Tests for in vitro cytotoxicity | | |
| Standard: ISO 10993-10, Third Edition, Biological evaluation of medical devices – Part 10: Tests for irritation and skin sensitization | | |
## VII Performance Characteristics (if/when applicable):
## A Analytical Performance:
### 1. Precision:
A precision study was conducted to assess variability with respect to days, operators, and device lots. The study included three device lots, each tested every day by three operators for 20 days; testing was conducted in duplicates for each sample concentration (i.e., 3 operators x 20 days x 3 lots x 2 runs per day x 2 replicates per sample per run = 720 results per sample panel member). Three levels of heat inactivated SARS-CoV-2 Omicron Variant lineage BA.5 (Isolate USA/COR-22-063113/2022) were spiked into negative clinical nasal swab matrix (NCM) as follows:
1. Negative Sample
2. Below LoD (0.9xLoD)
3. Low Positive Sample at 1.5xLoD
4. Positive Sample at 3xLoD
50μL of each sample was applied to dry nasal swabs. After blinding and randomizing, samples were processed per the IFU of the candidate device.
Precision was observed to be 100% for all replicates prepared at 1.5xLoD and 3xLoD, demonstrating no variability in the performance of the candidate assay across the conditions, operators, lots, and days tested.
Precision study samples were therefore prepared at 0.9xLoD using the same materials for sample preparation as for the original study. These samples were then tested as follows: 2 operators x 3 lots x 3 days x 2 runs per day x 2 replicates per sample per run and resulted in a total of 72 replicates. The precision for the 0.9xLoD sample was less than 100%, which is expected based on the random error for a sample below the LoD. However, the performance was consistent across all three lots tested.
K241317 - Page 6 of 18
{6}
Table 1. Precision Study Summary Results.
| | Negative (n/N) | | | Below LoD (0.9xLoD) (n/N) | | Low Positive (1.5xLoD) (n/N) | | | Positive (3xLoD) (n/N) | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Operator | 1 | 2 | 3 | 1 | 2 | 1 | 2 | 3 | 1 | 2 | 3 |
| Lot 1 | 0/80 | 0/80 | 0/80 | 11/12 | 9/12 | 80/80 | 80/80 | 80/80 | 80/80 | 80/80 | 80/80 |
| Lot 2 | 0/80 | 0/80 | 0/80 | 10/12 | 10/12 | 80/80 | 80/80 | 80/80 | 80/80 | 80/80 | 80/80 |
| Lot 3 | 0/80 | 0/80 | 0/80 | 12/12 | 12/12 | 80/80 | 80/80 | 80/80 | 80/80 | 80/80 | 80/80 |
| Agreement | NPA = 100% (720/720) | | | PPA = 88.89% (64/72) | | PPA = 100% (720/720) | | | PPA = 100% (720/720) | | |
| 95%CI | 99.47%, 100% | | | 79.58%, 94.26% | | 99.47%, 100% | | | 99.47%, 100% | | |
# 2. Linearity:
Not applicable as the device is a qualitative assay with binary visually read results.
# 3. Analytical Specificity/Interference:
# a. Cross-Reactivity and Microbial Interference
A panel of microorganisms commonly found as either pathogens or normal flora in respiratory samples were individually spiked into NCM. In the cross-reactivity study, the organisms were evaluated for their ability to cross-react with the test by adding $50\mu \mathrm{l}$ of each sample directly to the test swab and then processing the sample swabs per the IFU. The microbial interference testing was conducted in the same manner but in the presence of SARS-CoV-2 Omicron Variant lineage BA.5 co-spiked into the samples at 3xLoD. The testing was performed in triplicates for each microorganism. Neither cross-reactivity nor microbial interference was observed for any of the tested microorganisms at the concentration used in the study.
Table 2. Cross-Reactivity and Microbial Interference Testing Results
| Microorganism | Concentration Tested | Cross Reactivity Result | Interference Result |
| --- | --- | --- | --- |
| Human coronavirus 229E | 2x105TCID50/mL | 0/3 | 3/3 |
| Human coronavirus OC43 | 2x105TCID50/mL | 0/3 | 3/3 |
| Human coronavirus NL63 | 2x105TCID50/mL | 0/3 | 3/3 |
| MERS-coronavirus | 2x105TCID50/mL | 0/3 | 3/3 |
| Human coronavirus HKU1 (n=2)* | Ct = 20.5 – 22* | 0/6 | 6/6 |
| SARS-CoV Nucleocapsid Protein (His Tag)# | 0.25 ng/mL | 0/3 | 3/3 |
| Human Adenovirus 1 | 2x105TCID50/mL | 0/3 | 3/3 |
| Human Metapneumovirus 3 (hMPV-3) Type B1 | 2x105TCID50/mL | 0/3 | 3/3 |
| Parainfluenza virus – Type 1 | 2x105TCID50/mL | 0/3 | 3/3 |
| Parainfluenza virus – Type 2 | 2x105TCID50/mL | 0/3 | 3/3 |
| Parainfluenza virus – Type 3 | 2x105TCID50/mL | 0/3 | 3/3 |
| Parainfluenza virus – Type 4A | 2x105TCID50/mL | 0/3 | 3/3 |
| Influenza A/Darwin/6/21 | 2x105TCID50/mL | 0/3 | 3/3 |
| Influenza A/Victoria/4897/22 | 2x105TCID50/mL | 0/3 | 3/3 |
| Influenza B/Washington/02/19 | 2x105TCID50/mL | 0/3 | 3/3 |
K241317 - Page 7 of 18
{7}
K241317 - Page 8 of 18
| Microorganism | Concentration Tested | Cross Reactivity Result | Interference Result |
| --- | --- | --- | --- |
| Influenza B/Florida/04/06 | 2x10^{5} TCID_{50}/mL | 0/3 | 3/3 |
| Enterovirus Type 68 | 2x10^{5} TCID_{50}/mL | 0/3 | 3/3 |
| Respiratory syncytial virus | 2x10^{5} TCID_{50}/mL | 0/3 | 3/3 |
| Rhinovirus (Isolate: 10/2014 Isolate #1) | 5.62x10^{4} TCID_{50}/mL | 0/3 | 3/3 |
| Haemophilus influenzae type b (Eagan) | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Streptococcus pneumoniae Z022 | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Streptococcus pyogenes Z018 | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Candida albicans Z006 | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Bordetella pertussis A639 | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Mycoplasma pneumoniae M129 | 2x10^{6} CCU/mL | 0/3 | 3/3 |
| Mycoplasma tuberculosis H37Ra-1 | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Chlamydia pneumoniae | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Legionella pneumophila Philadelphia | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Staphylococcus aureus (strain: COL) | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Staphylococcus epidermidis MRSE; PR62A | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Pneumocystis jirovecii (PJP) - S. cerevisiae^{b} | 2x10^{6} CFU/mL | 0/3 | 3/3 |
| Pooled human nasal wash | NA | 0/3 | 3/3 |
| *Clinical specimens were evaluated
bRecombinant protein/strains were tested as the live or inactivated strains were hard to obtain | | | |
## b. Endogenous/Exogenous Interfering Substances Study
A panel of common endogenous and exogenous substances were evaluated for their potential to interfere with the performance of the test device. Samples were contrived by individually adding the substances listed in Table 3 below and testing them in NCM with or without SARS-CoV-2 virus at 2xLoD. 50 µL of each contrived sample was applied to the head of a swab and processed per the proposed IFU of the test. One device lot was used to test the potential interferents in triplicate measurements. No erroneous results were observed.
Table 3. Endogenous / Exogenous Interfering Substances Summary Data
| Interfering Substances | Concentration | Cross-reactivity (no analyte) (# positive/total) | Interference (2xLoD) (# positive/total) |
| --- | --- | --- | --- |
| Whole Blood | 2.5% | 0/3 | 3/3 |
| Mucin | 2.5 mg/mL | 0/3 | 3/3 |
| Chloraseptic sore throat lozenges (Benzocaine) | 3 mg/mL | 0/3 | 3/3 |
| Chloraseptic sore throat lozenges (Menthol) | 3 mg/mL | 0/3 | 3/3 |
| NeilMed (Sodium chloride with preservatives) | 15% v/v | 0/3 | 3/3 |
| CVS Nasal Drops (Phenylephrine) | 15% v/v | 0/3 | 3/3 |
| Afrin (Oxymetazoline) | 15% v/v | 0/3 | 3/3 |
{8}
| Interfering Substances | Concentration | Cross-reactivity (no analyte) (# positive/total) | Interference (2xLoD) (# positive/total) |
| --- | --- | --- | --- |
| CVS Nasal Spray (Cromolyn) | 15% v/v | 0/3 | 3/3 |
| Zicam | 15% v/v | 0/3 | 3/3 |
| Homeopathic (Alkalol) | 15% v/v | 0/3 | 3/3 |
| Sore Throat Phenol Spray | 5% w/v | 0/3 | 3/3 |
| Tobramycin | 4 μg/mL | 0/3 | 3/3 |
| Mupirocin | 10 mg/mL | 0/3 | 3/3 |
| Fluticasone Propionate | 15% v/v | 0/3 | 3/3 |
| Tamiflu (Oseltamivir Phosphate) | 5 mg/mL | 0/3 | 3/3 |
| Biotin | 3.5 μg/mL | 0/3 | 3/3 |
| Menthol | 0.015% w/v | 0/3 | 3/3 |
| Bleach | 0.01% v/v | 0/3 | 3/3 |
| Dish Soap | 1% v/v | 0/3 | 3/3 |
| Laundry Detergent | 1% v/v | 0/3 | 3/3 |
| Multi-Surface Cleaner | 1% v/v | 0/3 | 3/3 |
| Hand Soap | 1% v/v | 0/3 | 3/3 |
| Laundry Detergent | 1% w/v | 0/3 | 3/3 |
| Bar Soap | 1% w/v | 0/3 | 3/3 |
| Multipurpose Cleaner | 1% v/v | 0/3 | 3/3 |
| Hand Sanitizer | 1% v/v | 0/3 | 3/3 |
| Aspirin | 15 mg/mL | 0/3 | 3/3 |
| Motrin (Ibuprofen) | 50 mg/mL | 0/3 | 3/3 |
| Naproxen | 20 mg/mL | 0/3 | 3/3 |
| Budesonide | 15% v/v | 0/3 | 3/3 |
| Flunisolide | 15% v/v | 0/3 | 3/3 |
| Triamcinolone | 15% v/v | 0/3 | 3/3 |
| Dexamethasone | 5 mg/mL | 0/3 | 3/3 |
| Beclomethasone | 15% v/v | 0/3 | 3/3 |
| Remdesivir | 5 mg/mL | 0/3 | 3/3 |
| Molnupiravir | 5 mg/mL | 0/3 | 3/3 |
| Leukocytes | ≥1 x10^6 cells/mL | 0/3 | 3/3 |
| Zinc | 15% v/v | 0/3 | 3/3 |
| Luffa opperculata | 1.25% | 0/3 | 3/3 |
| Galphimia glauca | 15% v/v | 0/3 | 3/3 |
| Histaminum hydrochloricum | 15% v/v | 0/3 | 3/3 |
| Zanamivir | 10 mg/mL | 0/3 | 3/3 |
4. **Assay Reportable Range:**
Not applicable as the device is a qualitative assay that is visually read without numeric output.
K241317 - Page 9 of 18
{9}
K241317 - Page 10 of 18
# 5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
## a. Controls
### i. Internal Control:
The Wondfo 2019-nCOV Antigen test has a built-in internal procedural control. A red line should always appear in the control line region (C) indicating that proper volume of sample has been added and that membrane wicking has occurred. The anti-SARS-CoV-2 antibodies are conjugated with colloid gold nanoparticles leading to the coloration of the C line.
### ii. External Controls:
This test is for OTC distribution. As such the test kits will not contain external controls as lay users are not required to perform external control testing.
## b. Device Stability:
### i. Real Time Stability (Shelf life):
The stability of the Wondfo 2019-nCOV Antigen test was determined for the intended storage conditions, 2-30°C (36-86°F), and an intended shelf life of 11 months. Within one month of manufacture three device lots were transferred to three different temperatures (2 - 8°C, 30±2°C and 30±2°C & 95±5% relative humidity), where they were stored for 12 months. Testing of the kit lots was performed every 3 months with 20 replicates/timepoint and lot. Two test samples, corresponding to negative sample and positive sample at 3xLoD, were tested at each time point. All study data were 100% concordant with expected results and thereby supportive of the 11 months shelf life at 2-30°C (36-86°F).
### ii. Shipping Stability:
The effects of shipping on the integrity of the test device were evaluated with three device lots that were manufactured within one month of study start. These were exposed to either cycles of temperature and humidity fluctuations or mechanical stress. Temperature cycles included temperatures from -20 to 60°C with relative humidities between 85%, depending on the cycle. All results were concordant with expected results supporting stability during the anticipated shipping conditions for the test.
## c. Expected Values:
Patient samples are expected to be negative for SARS-CoV-2.
# 6. Detection Limit:
## a. Limit of Detection:
The limit of detection of the Wondfo 2019-nCOV Antigen test was determined with UV-inactivated SARS-CoV-2 USA-WA1/2020 and BA.5 Omicron isolates. Inactivated SAR-CoV-2 virus was diluted into NCM in 10-fold dilutions. Fifty (50) µl of each dilution was added directly to the test swab and the sample was then processed per the instructions for use. The LoD was assessed with three independent device lots. For the preliminary LoD
{10}
study, testing was performed with three replicates and the lowest concentration with $>95\%$ detection was then tested with 20 replicates to confirm the LoD.
- For SARS-CoV-2 (USA-WA-1/2020), the LoD was confirmed at $1 \times 10^{4}$ TCID $_{50}$ /mL.
- For SARS-CoV-2 (Lineage BA.5 (Omicron Variant)) the LoD was confirmed at $3.33 \times 10^{3} \mathrm{TCID}_{50} / \mathrm{mL}$ .
Table 4. LoD Study Summary with UV Inactivated SARS-CoV-2 (USA-WA1/2020)
| Concentration | | Lot 1 | | Lot 2 | | Lot 3 | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| TCID50/mL | TCID50/Swab | P | C | P | C | P | C |
| 3.39x107 | 1.7x106 | 100% (3/3) | N | 100% (3/3) | N | 100% (3/3) | N |
| 1x106 | 5x104 | 100% (3/3) | N | 100% (3/3) | N | 100% (3/3) | N |
| 1x105 | 5x103 | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) |
| 1x104 | 5x102 | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) |
| 3.33x103 | 1.67x102 | N | 95% (19/20) | N | 85% (17/20) | N | N |
| 1x103 | 5x101 | 0% (0/3) | N | 0% (0/3) | N | 0% (0/3) | N |
P: Preliminary Study. C: Confirmatory LoD Study. N: Not tested
Table 5. LoD Study Summary with UV Inactivated SARS-CoV-2 BA.5 (Omicron)
| Concentration | | Lot 1 | | Lot 2 | | Lot 3 | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| TCID50/mL | TCID50/Swab | P | C | P | C | P | C |
| 1.98x106 | 9.9x104 | 100% (3/3) | N | 100% (3/3) | N | 100% (3/3) | N |
| 1x105 | 5x103 | 100% (3/3) | N | 100% (3/3) | N | 100% (3/3) | N |
| 1x104 | 5x102 | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) |
| 3.33x103 | 1.67x102 | N | 100% (20/20) | N | 100% (20/20) | N | 100% (20/20) |
| 1.11x103 | 5.55x101 | N | 65% (13/20) | N | 15% (3/20) | N | 85% (17/20) |
| 1x103 | 5x101 | 0% (0/3) | N | 0% (0/3) | N | 0% (0/3) | N |
P: Preliminary Study. C: Confirmatory LoD Study. N: Not tested
# b. Limit of Detection with the 1st WHO International Standard (NIBSC 21/368):
Wondfo tested the sensitivity of the test against the $1^{\mathrm{st}}$ WHO International Standard for SARS-CoV-2 antigen (NIBSC code: 21/368) spiked into pooled nasal swab sample in saline. The unitage of this material has an assigned value of 5,000 International Units (IU) of SARS-CoV-2 antigen per ampoule when reconstituted per instructions. A 10-fold dilution series was made to determine the preliminary LoD, which was measured using three (3) device lots and in triplicate measurements $(n = 3)$ . The LoD was confirmed using
K241317 - Page 11 of 18
{11}
20 replicates $(n = 20)$ per dilution. The measurements were done by adding $50\mu l$ of each dilution directly to the test swab and processing the sample per the test's instructions for use. The lowest concentration of the SARS-CoV-2 antigen at which a minimum of $95\%$ of results were positive was confirmed to be $200~\mathrm{IU / mL}$ or $10~\mathrm{IU / Swab}$ .
Table 6. LoD Study Summary with $1^{\text{st}}$ WHO International Standard for SARS-CoV-2 antigen (NIBSC code: 21/368)
| Concentration | | Lot 1 | | Lot 2 | | Lot 3 | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| TCID50/mL | TCID50/Swab | P | C | P | C | P | C |
| 2000 | 100 | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) |
| 200 | 10 | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) | 100% (3/3) | 100% (20/20) |
| 20 | 1 | 0% (0/3) | N | 0% (0/3) | N | 0% (0/3) | N |
| 2 | 0.1 | 0% (0/3) | N | 0% (0/3) | N | 0% (0/3) | N |
| 66.7 | 3.34 | 0% (0/3) | 15% (3/20) | 0% (0/3) | 10% (2/20) | 0% (0/3) | 10% (2/20) |
| 0.2 | 0.01 | 0% (0/3) | N | 0% (0/3) | N | 0% (0/3) | N |
| 0.02 | 0.001 | 0% (0/3) | N | 0% (0/3) | N | 0% (0/3) | N |
P: Preliminary Study. C: Confirmatory LoD Study.
# 7. Inclusivity
An evaluation of the sensitivity of the test for the detection of relevant SARS-CoV-2 variants was done in form of an LoD study with eight different SARS-CoV-2 variant strains. Three lots of the Wondfo 2019-nCoV Antigen Test were used. Samples for inclusivity testing were prepared with the same methodology as detailed above for the Limit of Detection study. Viral samples were tested per the IFU in triplicate to first establish the preliminary LoD and then subsequently in replicates of 20 for the confirmatory LoD. The lowest concentration that detected $\geq 95\%$ of all replicates for each evaluated SARS-CoV-2 strain is shown below.
Beyond the testing described above, Omicron JN.1.1 was independently evaluated with the test showing detection down to $2.28 \times 10^{4} \mathrm{GE/mL}$ (corresponding to an average Ct of 27.9).
Table 7: LoD of SARS-CoV-2 Variants
| Strain/Viral Material | Reactivity (Number positive/ Number tested) | | | LoD (TCID50/mL) |
| --- | --- | --- | --- | --- |
| | Lot 1 | Lot 2 | Lot 3 | |
| SARS-CoV-2 Variant B.1.1.7 (Alpha Variant) | 23/23 | 23/23 | 23/23 | 1 x 103 |
| SARS-CoV-2 Lineage B.1.351 (Beta variant) | 23/23 | 23/23 | 23/23 | 1 x 103 |
| SARS-CoV-2 Variant Brazil Lineage P.1 (Gamma variant) | 23/23 | 23/23 | 23/23 | 1 x 103 |
| SARS-CoV-2 Lineage B.1.617.2 (Delta Variant) | 23/23 | 23/23 | 23/23 | 1 x 102 |
| SARS-CoV-2 Lineage B.1.1.529 (Omicron Variant) | 23/23 | 23/23 | 23/23 | 1 x 102 |
| SARS-CoV-2 Lineage BA 2.3 (Omicron Variant) | 23/23 | 23/23 | 23/23 | 3.33 x 102 |
K241317 - Page 12 of 18
{12}
| Strain/Viral Material | Reactivity (Number positive/ Number tested) | GE/mL* |
| --- | --- | --- |
| | Lot 4 | |
| SARS-CoV-2 JN.1.1 (live) | 5/5 | 2.28 x10^{4} |
* GE: Genome equivalent/mL
## 8. Hook Effect Study
An assessment of whether a high dose hook effect exists for the test was done using a serial dilution of UV-inactivated SARS-CoV-2 virus strains. Multiple virus strains were tested, each spiked into negative NCM. 50μl of sample was added directly to the head of the swabs. Swabs were processed per the test's IFU/QRI. Testing was done across three device lots. Each of the 3 operators performed triplicate measurements for each concentration per lot. No high dose hook effect was observed in the study for any of the strains. Only the data for the most relevant contemporary strain tested in this study (i.e., SARS-CoV-2 Omicron Lineage BA.5) are shown in Table 8 below.
Table 8. High Dose Hook Effect Data Summary
| Virus Concentration (TCID_{50}/mL) | Test Results (Agreement #positive /# Total) | | |
| --- | --- | --- | --- |
| | Lot 1 | Lot 2 | Lot 3 |
| 1.98x10^{6} | 3/3 | 3/3 | 3/3 |
| 1x10^{5} | 3/3 | 3/3 | 3/3 |
| 1x10^{4} | 3/3 | 3/3 | 3/3 |
| 1x10^{3} | 0/3 | 0/3 | 0/3 |
| 1x10^{2} | 0/3 | 0/3 | 0/3 |
| 1x10^{1} | 0/3 | 0/3 | 0/3 |
## 9. Assay Cut-Off:
Not applicable as the device is a qualitative assay that yields visually read binary results.
## B Comparison Studies:
### 1. Method Comparison with Predicate Device:
Not applicable. Please refer to Section VII. C. Clinical Studies for performance comparison with a clinical comparator.
### 2. Matrix Comparison:
This device is only intended for use with direct anterior nasal swab specimens. As no other specimen or sample type is used with this device, a matrix comparison study to support other sample types for clinical testing with this device was not performed.
## C Clinical Studies:
### 1. Clinical Sensitivity and Specificity:
A prospective lay person clinical study was conducted to assess the performance of the candidate test in a simulated at-home setting when compared to a highly sensitive 510(k)-
K241317 - Page 13 of 18
{13}
cleared SARS-CoV-2 RT-PCR assay with an extraction step. The study enrolled symptomatic subjects at nine (9) clinical study sites between April 2023, and February 2024, when Omicron was the most prevalent SARS-CoV-2 strain in the U.S.
Both the comparator and the candidate test used anterior nasal swab samples, and the sample collection order was alternated (randomized) for each study subject. Comparator test samples were collected by health care professionals at the clinical study site and inserted into Universal Transport Media per the IFU of the comparator test. Samples for the candidate antigen test were collected per the test's QRI and were either self-collected by a lay user aged $\geq 14$ years or collected by an adult (parent/guardian) from individuals aged 2 to $< 14$ years.
This study enrolled a total of 1,053 individuals. Of the 1,053 results obtained, 21 were excluded and 1,032 were considered evaluable. The clinical performance estimates are based on these 1,032 study subjects between 0 and 5 DPSO. The 1,032 results consisted of 128 positive and 904 negative study subjects as defined by the comparator result. The Wondfo 2019-nCoV Antigen Test demonstrated the following performance, when compared to the result of the SARS-CoV-2 RT-PCR comparator assay:
Positive Percent Agreement (PPA) of $84.38\%$ (108/128) $(95\% \mathrm{CI}: 77.10\%, 89.65\%)$
- Negative Percent Agreement (NPA) of $99.67\%$ (901/904) $(95\% \mathrm{CI}: 99.03\%, 99.89\%)$ .
Table 9: Demographics - Clinical Study Participants
| Characteristic | Number of Evaluable Subjects | % of Total |
| --- | --- | --- |
| Age | | |
| 2-13 years of age | 117 | 11.34% |
| 14-21 years of age | 86 | 8.33% |
| 22-64 years of age | 698 | 67.64% |
| >64years of age | 131 | 12.69% |
| Total | 1,032 | 100% |
| Gender | | |
| Male | 414 | 40.12% |
| Female | 618 | 59.88% |
| Total | 1,032 | 100% |
| Sample Collector | | |
| Self-collected sample | 900 | 87.21% |
| Sample collected by other | 132 | 12.79% |
| Total | 1,032 | 100% |
K241317 - Page 14 of 18
{14}
Table 10: Clinical Performance Estimates
| Candidate Test | Comparator Test | | |
| --- | --- | --- | --- |
| | Positive | Negative | Total |
| Positive | 108 | 3 | 111 |
| Negative | 20 | 901 | 921 |
| Total | 128 | 904 | 1,032 |
| Positive Percent Agreement (PPA) = 84.38% (108/128) 95% CI: (77.10%, 89.65%) | | | |
| Negative Percent Agreement (NPA) = 99.67% (901/904) (95% CI: 99.03%, 99.89%) | | | |
Table 11. Clinical Performance Stratified by DPSO
| Days Post Symptom Onset | PPA |
| --- | --- |
| 0 | 100% (5/5) |
| 1 | 90.91% (20/22) |
| 2 | 82.35% (28/34) |
| 3 | 83.33% (25/30) |
| 4 | 86.36% (19/22) |
| 5 | 73.33% (11/15) |
| Total | 84.38% (108/128) |
2. Usability Study:
The usability of the test was assessed with a sub cohort of the clinical study. During this study, representative test kit users (self-testers aged 14+, caregiver-child pairs, and caregiver-adult pairs) were observed performing the COVID-19 test while using the IFU/QRI. The observers recorded the proper execution of each task when the enrolled lay user study subject (n=30) conducted the test. The observers did not otherwise interfere with the study subject's sample collection and testing.
Table 12. Usability Study Results
| Tasks | Critical (C) or Non-critical (NC) | Task Performed Correctly | Acceptability |
| --- | --- | --- | --- |
| Wash hands | NC | 86.7% (26/30) | Yes |
| Check expiration date | NC | 73.3% (22/30) | Yes |
| Unpack kit | NC | 100% (26/30) | Yes |
| Open Tube Cap | NC | 100% (30/30) | Yes |
| Place Tube in tube holder | NC | 100% (30/30) | Yes |
| Remove swab from pouch without contamination/touching tip | C | 100% (30/30) | Yes |
| Swab first nostril 5x/15sec | C | 100% (30/30) | Yes |
| Swab second nostril 5x/15 sec | C | 96.7% (29/30) | Yes |
| Insert swab into tube/touch bottom | C | 100% (30/30) | Yes |
| Stir swab (15x or more) | C | 100% (30/30) | Yes |
| Place tube in holder/Keep swab in tube for 1 minute | C | 93.3% (28/30) | Yes |
| Remove swab while squeezing sides of tube | C | 90% (27/30) | Yes |
K241317 - Page 15 of 18
{15}
| Tasks | Critical (C) or Non-critical (NC) | Task Performed Correctly | Acceptability |
| --- | --- | --- | --- |
| Cap tube | NC | 100% (30/30) | Yes |
| Remove cassette from pouch & use within 1 hour | NC | 100% (30/30) | Yes |
| Open Tube Cap | NC | 96.7% (29/30) | Yes |
| Add 4 drops of sample to sample well | C | 96.7% (29/30) | Yes |
| Set timer to wait 10 minutes (no more than 20 minutes) to read results | C | 96.7% (29/30) | Yes |
## 3. Readability and Comprehension:
A readability and comprehension study with lay persons was conducted to evaluate the ability of the intended lay user to correctly read and interpret their test results. Fifty (50) participants were enrolled in the readability and comprehension study. Each study subject was provided with eight randomized mock tests (2 panels with 4 mock devices each) of different concentrations, which they were asked to interpret per the IFU. After interpreting the mock tests, the study subjects were provided with a questionnaire to assess their comprehension of the test results. Each lay user was asked to interpret two panels of 5 test devices with three different concentrations that were arranged in a randomized and blinded manner, with the following sample results:
- Panel 1: Negative, 1.5xLoD, 1.5xLoD, 5xLoD, Invalid
- Panel 2: Negative, Negative, 1.5xLoD, 5xLoD, Invalid
Table 13. Mock Test Interpretation Summary Results
| Sample Level | Number of Test Results Across all Participants | Number of Correct Interpretation | Observed Performance (%) |
| --- | --- | --- | --- |
| Negative | 150 | 146 | 97.33% |
| 1.5xLoD | 150 | 140 | 93.33% |
| 5xLoD | 100 | 100 | 100% |
| Invalid | 100 | 100 | 100% |
## D Clinical Cut-Off:
The test is a qualitative test with a binary positive/negative signal and has no clinical cut-off.
## E Expected Values/Reference Range:
When the test is valid, it produces binary values, positive or negative for SARS-CoV-2 antigens.
## F Other Supportive Performance Characteristics Data:
### 1. Flex Studies:
To assess the robustness and risk for false results of the test when deviating from the IFU/QRI test steps, flex studies were conducted that assessed all major aspects of the test procedure (sample volume, reading time, swab extraction time, swab rotation, and tube squeezing) and variability of environmental test conditions that the test may be subjected to when in use (lighting, disturbance during use, temperature, and humidity stress conditions). Testing was performed with contrived positive nasal swabs generated by diluting SARS-
K241317 - Page 16 of 18
{16}
CoV-2 virus into negative NCM at 2xLoD. False results are observed with too little sample volume and insufficient incubation time, specifically with less than two drops of sample and with less than eight minutes incubation. However, these failures are mitigated in the labeling with warning statements in the procedural steps. The studies support that the test is robust in the intended use condition with an insignificant risk of erroneous result.
## Lead Reviewer Comment for Internal Discussion Only
A detailed description of the flex studies is available in the internal section of the memo below in section X.7.
## 2. Serial Testing:
As a mitigation for the low performance of antigen tests very early and at the tail end of infection, the Intended Use for this test device (and associated Instructions for Use) states that negative results are presumptive, and it includes the need for repeat testing (i.e., test at least twice over three days with at least 48 hours between tests). These mitigations are supported by data generated by the National Institutes for Health (NIH) and the University of Massachusetts Chan Medical School (in collaboration with the FDA) demonstrating that repeat testing over multiple days improves test performance and increases the likelihood that a COVID-19 antigen test will accurately detect an infection. These results have informed the FDA's general understanding that repeat testing after a negative result from a COVID-19 antigen test reduces the risk of a false negative result. Please refer to the following studies for additional details:
- Finding a Needle in the Haystack: Design and Implementation of a Digital Site-less Clinical Study of Serial Rapid Antigen Testing to Identify Asymptomatic SARS-CoV-2 Infection - https://www.medrxiv.org/content/10.1101/2022.08.04.22278274v1
- Performance of Screening for SARS-CoV-2 using Rapid Antigen Tests to Detect Incidence of Symptomatic and Asymptomatic SARS-CoV-2 Infection: findings from the Test Us at Home prospective cohort study - https://www.medrxiv.org/content/10.1101/2022.08.05.22278466v1
## 3. Variant Monitoring Plan:
The sponsor established a variant monitoring plan for K241317 device to confirm the continued performance of the test device with future SARS-CoV-2 variants. Specifically, Wondfo plans a monthly surveillance of emerging SARS-CoV-2 variants by monitoring CDC and WHO websites along with their post-market surveillance reports and other regulatory sources of information. According to the available information, when a new emerging variant of SARS-CoV-2 is found to have high prevalence and causes public health concern (VOC or VOHC), one or more of the following actions will be taken for evaluating the impact of the variant:
i. In-silico analysis evaluation shall be performed for the impact of certain mutations on the target proteins.
ii. Wet-testing evaluation shall be conducted to verify the clinical performance and LoD of the device once the culture of the variant is available.
An evaluation report shall be prepared. The review date and the result of analysis will be maintained in a variant monitoring log. If the aggregate impact of the mutation reduces the
K241317 - Page 17 of 18
{17}
clinical performance of the test by 5% or more or decreases the clinical performance estimates for the test below 80% PPA or the established LoD decreases, these changes will be reported to FDA within 7 days of completing evaluation. In addition, the corrective and preventative action shall be implemented according to the company’s standard operating procedures.
## VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
## IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K241317 - Page 18 of 18
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.