CDC HUMAN INFLUENZA VIRUS REAL-TIME RT-PCR DIAGNOSTIC PANEL
K123905 · Centers for Disease Control and Prevention · OQW · Jan 14, 2013 · Microbiology
Device Facts
Record ID
K123905
Device Name
CDC HUMAN INFLUENZA VIRUS REAL-TIME RT-PCR DIAGNOSTIC PANEL
Applicant
Centers for Disease Control and Prevention
Product Code
OQW · Microbiology
Decision Date
Jan 14, 2013
Decision
SESE
Submission Type
Special
Regulation
21 CFR 866.3332
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K123905 · Jan 14, 2013
CDC HUMAN INFLUENZA VIRUS REAL-TIME RT-PCR DIAGNOSTIC PANEL
Centers for Disease Control and Prevention
Human respiratory specimens from U.S. public health laboratories
Clinical specimens collected during routine public health surveillance were used to evaluate the positive percent agreement of the device for the detection of influenza A (H3N2)v virus.
Public health surveillance; Clinical specimen testing; Confirmatory testing
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Retrospective analysis of clinical specimens; Follow-up/Duration: July 2012 to August 2012; Study Period: July 2012 - August 2012
Human patients with respiratory infections; Sample Size: 165; Number of Sites: Multiple U.S. public health laboratories
Genetic sequence analysis
Positive percent agreement for detection of influenza A (H3N2)v
Indications for Use
The CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panel is intended for use in real-time RT-PCR (rRT-PCR) assays on an Applied Biosystems (ABI) 7500 Fast Dx Real-Time PCR Instrument in conjunction with clinical and epidemiological information: - For qualitative detection of influenza virus type A or B from viral RNA in upper respiratory tract clinical specimens (including nasopharyngeal swabs [NPS], nasal swabs [NS], throat swabs [TS], nasal aspirates [NA], nasal washes [NW] and dual nasopharyngeal/throat swabs [NPS/TS], and lower respiratory tract specimens (including bronchoalveolar lavage [BAL], bronchial wash [BW], tracheal aspirate [TA], sputum, and lung tissue) from human patients with signs and symptoms of respiratory infection and/or from viral culture; - For determination of the subtype of seasonal human influenza A virus as seasonal A/H1, A/H3, and/or A/H1pdm09 from viral RNA in upper respiratory tract clinical specimens (including NPS, NS, TS, NA, NW and NPS/TS) and lower respiratory tract specimens (including BAL, BW, TA, sputum and lung tissue) from human patients with signs and symptoms of respiratory infection and/or from viral culture; - For the presumptive identification of virus in patients who may be infected with influenza A subtype A/H5 (Asian lineage) from viral RNA in human respiratory specimens and viral culture in conjunction with clinical and epidemiological risk factors; - To provide epidemiologic information for surveillance of circulating influenza viruses. Performance characteristics for influenza were established during a season when influenza viruses A/H1 and A/H3 were the predominant influenza A viruses in circulation and during a season when the A/H1pdm09 influenza virus was the predominant influenza A virus in circulation. Performance characteristics may vary with other emerging influenza A viruses. Testing with the influenza H5a and H5b primer and probe sets should not be performed unless the patient meets the most current U.S. Department of Health and Human Services (DHHS) clinical and epidemiologic criteria for testing suspect A/H5 specimens. The definitive identification of influenza A/H5 (Asian lineage) either directly from patient specimens or from virus cultures requires additional laboratory testing, along with clinical and epidemiological assessment in consultation with national influenza surveillance experts. Negative results do not preclude influenza virus infection and should not be used as the sole basis for treatment or other patient management decisions. Conversely, positive results do not rule out bacterial infection or co-infection with other viruses. The agent detected may not be the definite cause of disease. If infection with a novel influenza A virus is suspected based on current clinical and epidemiological screening criteria recommended by public health authorities, specimens should be collected with appropriate infection control precautions for novel virulent influenza viruses and sent to state or local health department for testing. Viral culture should not be attempted in these cases unless a BSL 3+ facility is available to receive and culture specimens. All users, analysts, and any person reporting results from use of this device should be trained to perform and interpret the results from this procedure by a competent instructor prior to use. CDC Influenza Division will limit the distribution of this device to only those users who have successfully completed a training course provided by CDC instructors or designees.
Device Story
The CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panel is a molecular diagnostic assay used on the ABI 7500 Fast Dx Real-Time PCR Instrument. It processes viral RNA extracted from respiratory specimens (swabs, aspirates, washes, sputum, tissue) or viral culture. The device uses oligonucleotide primers and TaqMan hydrolysis probes to perform one-tube rRT-PCR. During thermocycling, 5' nuclease activity of Taq polymerase cleaves hybridized probes, releasing reporter dye and generating a fluorescent signal proportional to target amplification. The system monitors fluorescence intensity at each cycle. The device is operated by trained personnel in clinical or public health laboratories. The output is a qualitative detection of influenza A/B, subtyping of seasonal A/H1, A/H3, A/H1pdm09, and presumptive identification of A/H5. Results assist healthcare providers in patient management and public health surveillance. The modification allows reporting of specific marker patterns as 'presumptive positive for influenza A (H3N2) variant virus' instead of 'inconclusive'.
Clinical Evidence
Clinical performance evaluated using 165 human respiratory specimens. Specimens testing positive for InfA, H3, and pdmInfA (and negative for H1/pdmH1) were compared against genetic sequence analysis (comparator). Results showed 97.6% positive percent agreement (95% CI: 93.9-99.1%).
Technological Characteristics
Real-time RT-PCR assay; utilizes ABI 7500 Fast Dx instrument. Nucleic acid extraction via QIAamp Viral RNA Mini, MagNA Pure, or NucliSENS easyMAG. Enzyme master mix: Invitrogen SuperScript III Platinum One-Step Quantitative RT-PCR. Detects universal influenza A, B, and subtypes A/H1, A/H3, A/H1pdm09, A/H5. Standalone diagnostic panel.
Indications for Use
Indicated for qualitative detection and subtyping of influenza A and B viruses in human respiratory specimens (upper and lower tract) and viral culture from patients with signs/symptoms of respiratory infection. Used for presumptive identification of A/H5 (Asian lineage) and surveillance of circulating influenza viruses. Contraindicated for H5 testing unless patient meets DHHS clinical/epidemiologic criteria.
Regulatory Classification
Identification
Reagents for detection of specific novel influenza A viruses are devices that are intended for use in a nucleic acid amplification test to directly detect specific virus RNA in human respiratory specimens or viral cultures. Detection of specific virus RNA aids in the diagnosis of influenza caused by specific novel influenza A viruses in patients with clinical risk of infection with these viruses, and also aids in the presumptive laboratory identification of specific novel influenza A viruses to provide epidemiological information on influenza. These reagents include primers, probes, and specific influenza A virus controls.
Special Controls
The device is classified as Class II under regulation 21 CFR 866.3332 with special controls. The special control guidance document "Reagents for Detection of Specific Novel Influenza A viruses" will be available shortly.
*Classification.* Class II (special controls). The special controls are:(1) FDA's guidance document entitled “Class II Special Controls Guidance Document: Reagents for Detection of Specific Novel Influenza A Viruses.” See § 866.1(e) for information on obtaining this document.
(2) The distribution of these devices is limited to laboratories with experienced personnel who have training in standardized molecular testing procedures and expertise in viral diagnosis, and appropriate biosafety equipment and containment.
Predicate Devices
CDC Human Influenza Virus Real-time RT-PCR Diagnostic Panel (k111507)
Submission Summary (Full Text)
{0}
SPECIAL 510(k): Device Modification Decision Summary
To: Center for Disease Control and Prevention (CDC)
RE: k123905
This 510(k) submission contains information/data on modifications made to the SUBMITTER'S own Class II or Class I device requiring 510(k). The following items are present and acceptable
1. The name and 510(k) number of the SUBMITTER'S previously cleared device:
Trade Name: CDC Human Influenza Virus Real-time RT-PCR Diagnostic Panel
510(k) number: k111507 (also k080570 and k101564)
2. Submitter's statement that the INDICATION/INTENDED USE of the modified device as described in its labeling HAS NOT CHANGED along with the proposed labeling which includes instructions for use.
3. A description of the device MODIFICATION(S). The modification presented in this 510(k) is the modification of the package insert of the device so that the results for a specimen that tests positive for InfA, H3, and pdmInfA markers and negative for H1 and pdmH1 markers will be interpreted as a presumptive positive for H3N2v influenza A virus detection.
The submitter provided the following LoD, Analytical Reactivity, and Clinical Specimen Testing data:
## Limit of Detection (LoD)
The LoD of the CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panel for influenza A(H3N2) variant ((H3N2)v) virus was evaluated with two recent isolates by determining the lowest concentration of virus as measured by 50% egg infectious dose (EID50/ml) where the InfA, pdmInfA, and H3 primer and probe sets demonstrated a uniform detection rate of ≥ 95%. The results are summarized in the table below.
(H3N2)v LoD Summary
| Influenza A(H3N2)v virus | Limit of Detection (EID50/mL) | | | |
| --- | --- | --- | --- | --- |
| | InfA | pdm InfA | H3 | Final LoD |
| A/West Virginia/06/2011 | 10^{0.7} | 10^{1.4} | 10^{2.1} | 10^{2.1} |
| A/Indiana/12/2012 | 10^{0.6} | 10^{1.3} | 10^{2.0} | 10^{2.0} |
## Analytical Reactivity/Inclusivity
Recent isolates of influenza A (H3N2)v virus from 2009 - 2012 were evaluated with the CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panel at virus concentrations of approximately 10<sup>2.0</sup> EID<sub>50</sub>/ml. The inclusivity testing verifies that the device can detect contemporary influenza A (H3N2)v viruses near the LoD. The results are summarized in the following table.
{1}
2
# Inclusivity Testing
| Strain designation | EID_{50}/mL | Average InfA Ct Value (n=3) | Average pdm InfA Ct Value (n=3) | Average H3 Ct Value (n=3) |
| --- | --- | --- | --- | --- |
| A/Kansas/13/2009 | 10^{2.0} | 33.4 | 32.6 | 33.9 |
| A/Indiana/08/2011 | 10^{2.3} | 33.0 | 33.5 | 35.6 |
| A/Wisconsin/12/2011 | 10^{2.1} | 28.9 | 26.9 | 28.9 |
| A/West Virginia/06/2011 | 10^{2.9} | 28.1 | 28.3 | 30.1 |
| A/Indiana/12/2012 | 10^{2.1} | 31.7 | 32.8 | 36.0 |
# Clinical Specimen Testing
From July 2012 to August 2012, a total of 165 human respiratory specimens that tested positive for InfA, H3, and pdmInfA markers and negative for H1 and pdmH1 markers with the CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panel were transferred from U.S. public health laboratories to the CDC for confirmatory testing.
The specimens were retested upon arrival with the CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panel following the instructions for use provided in the package insert. Results were confirmed through genetic sequence analysis. Comparison of the results obtained with the CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panel to the results of the genetic sequencing analysis demonstrated a positive percent agreement of 97.6% with a 95% confidence interval of 93.9-99.1% for the detection of influenza A (H3N2)v virus.
# Clinical Performance Comparison
| | Comparator^{1} | | Performance |
| --- | --- | --- | --- |
| | Positive^{2} | Negative | |
| CDC Flu rRT-PCR Dx Panel (+) | 161 | NA | 97.6% Positive Percent Agreement (93.9 – 99.1) 95% CI |
| CDC Flu rRT-PCR Dx Panel (-) | 4 | NA | NA |
| Total | 165 | NA | NA |
1. The comparator is genetic sequence analysis.
2. A positive result for InfA, H3, and pdmInfA markers (negative for H1 and pdmH1 markers) was investigated. Any result that was not positive for all three markers InfA, pdm InfA, and H3 was considered as negative.
NA = not applicable.
4. The FUNDAMENTAL SCIENTIFIC TECHNOLOGY of the modified device has not changed.
5. Comparison Information (similarities and differences) to applicant's legally marketed predicate device including, labeling, intended use, and physical characteristics:
{2}
Similarities
| | CDC Human Influenza Virus Real-time PCR Diagnostic Panel (k111507) | Modified CDC Human Influenza Virus Real-time PCR Diagnostic Panel (k123905) |
| --- | --- | --- |
| Intended Use | The CDC Human Influenza Virus Real-Time PCR Diagnostic Panel is intended for use in Real-time RT-PCR assays on an Applied Biosystems (ABI) 7500 Fast Dx Real-Time PCR Instrument in conjunction with clinical and epidemiological information:· For qualitative detection of influenza virus type A or B from viral RNA in upper respiratory tract clinical specimens (including nasopharyngeal swabs, nasal swabs, throat swabs, nasal aspirates, nasal washes and dual nasopharyngeal/throat swabs), and lower respiratory tract specimens (including bronchioalveolar lavages, bronchial washes, tracheal aspirates, sputum, and lung tissue) from human patients with signs and symptoms of respiratory infection and/or from viral culture· For determination of the subtype of seasonal human influenza A virus as seasonal A/H1, A/H3, and/or A/H1pdm09 from viral RNA in upper respiratory tract clinical specimens (including nasopharyngeal swabs, nasal swabs, throat swabs, nasal aspirates, nasal washes and dual nasopharyngeal/throat swabs), and lower respiratory tract specimens (including bronchioalveolar lavages, bronchial washes, tracheal aspirates, sputum, and lung tissue) from human patients with signs and symptoms of respiratory infection and/or from viral culture· For the presumptive identification of virus in patients who may be infected with influenza A subtype A/H5(Asian Lineage) from viral RNA in human respiratory specimens and viral culture in conjunction with clinical and epidemiological risk factors· To provide epidemiologic information for surveillance of the circulating influenza viruses.Performance characteristics for influenza were established during a season when influenza viruses A/H1 and A/H3 were the predominant influenza A viruses in circulation and during a season when the A/H1pdm09 influenza virus was the predominant influenza A virus in circulation. Performance characteristics may vary with other emerging influenza A viruses.Testing with the influenza H5a and H5b primer and | Same |
{3}
4
| | probe sets should not be performed unless the patient meets the most current U.S. Department of Health and Human Services (DHHS) clinical and epidemiologic criteria for testing suspect A/H5 specimens. The definitive identification of influenza A/H5 (Asian lineage) either directly from patient specimens or from virus cultures requires additional laboratory testing, along with clinical and epidemiological assessment in consultation with national influenza surveillance experts.
Negative results do not preclude influenza virus infection and should not be used as the sole basis for treatment or other patient management decisions. Conversely, positive results do not rule out bacterial infection or co-infection with other viruses. The agent detected may not be the definite cause of disease.
If infection with a novel influenza A virus is suspected based on current clinical and epidemiological screening criteria recommended by public health authorities, specimens should be collected with appropriate infection control precautions for novel virulent influenza viruses and sent to state or local health department for testing. Viral culture should not be attempted in these cases unless a BSL 3+ facility is available to receive and culture specimens.
**All users, analysts, and any person reporting results from use of this device should be trained to perform and interpret the results from this procedure by a competent instructor prior to use. CDC Influenza Division will limit the distribution of this device to only those users who have successfully completed a training course provided by CDC instructors or designees.** | |
| --- | --- | --- |
| Technology | Real-time RT-PCR | Same |
| Organism Detected | Universal influenza A viruses (animal and human), Swine-origin influenza A viruses, Influenza B viruses, and Influenza A subtypes: seasonal A/H1, A/H3, A/H1pdm09 , and A/H5 | Same |
| Required Instrumentation | Applied Biosystems 7500 Fast Dx Real- Time PCR Instrument | Same |
| Nucleic Acid Extraction | Yes | Same |
| Extraction Method | - QIAamp® Viral RNA Mini Kit, Qiagen Inc.
- MagNA Pure Compact -Total Nucleic Acid Kit, Roche Applied Science
- MagNA Pure Compact – RNA Isolation Kit, Roche Applied Science
- MagNA Pure LC - RNA Isolation Kit II, Roche Applied Science
- Qiagen QIAcube with QIAamp® Viral RNA Mini Kit, Qiagen Inc.
- NucliSENS® easyMAG®, bioMerieux | Same |
| Enzyme Master Mix | Invitrogen SuperScript™ III Platinum® One-Step Quantitative RT-PCR Kits (with or without ROX) | Same |
{4}
5
## Differences
| | CDC Human Influenza Virus Real-time PCR Diagnostic Panel (k111507) | Modified CDC Human Influenza Virus Real-time PCR Diagnostic Panel (k123905) |
| --- | --- | --- |
| Non Standard Results Interpretation Guidance in the Package Insert | Results positive for InfA, H3, and pdmInfA markers and negative for H1 and pdmH1 markers are reported as inconclusive and referred to CDC for further testing. | Results positive for InfA, H3, and pdmInfA markers and negative for H1 and pdmH1 markers are interpreted as a presumptive positive for influenza A (H3N2) variant virus and referred to CDC for further testing. |
## 6. Design Control Activities Summary:
a) Risk Analysis:
A risk analysis for the CDC Human Influenza Virus Real-Time RT-PCR Diagnostic Panel was conducted and the results reviewed to verify that the change did not present increased or new risks to the user. No new risks were identified as a result of the proposed modification. As an additional mitigation, (H3N2)v influenza strains will continue to be referred to CDC for further confirmation.
The following table is a summary of the risk analysis:
{5}
| Device Modification | Cause of Risk | Hazardous Situation | Consequence | Risk Control Measure | Risk Acceptability Criteria | Verification Method | Summary Conclusion |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Change in results interpretation will allow public health labs to report presumptive positives for the (H3N2)v virus. | Current device results interpretation guidance does not allow for the conclusive identification and reporting of H3N2v virus | (H3N2)v may be present in human respiratory specimens but not conclusively identified by the device. | Patient or community with (H3N2)v infections may not be identified in a timely fashion, leading to a delay in implementation of public health mitigation measures | A combination of measures are used to control risk:
-Characterization of the performance of the device with (H3N2)v viruses.
-Provide users with additional guidance on the results interpretation of the device
-Provide users with instructions on reporting results and referral of specimens with presumptive positive results for (H3N2)v to CDC for confirmation
-Non-standard results are reported to CDC and referred for further analysis | Only trained laboratories are allowed to order the device.
Analytical and clinical sensitivity of the device for (H3N2)v must be comparable with the detection of human seasonal influenza A viruses.
Device labeling must be updated to include results interpretation guidance and instructions on referral of specimens with presumptive positive results for(H3N2)v to CDC for confirmation | Internal controls allow only trained public health laboratories to order the device.
LoD, inclusivity, and clinical testing done in accordance with the test methods cleared in the predicate. (k111507)
Updated device instructions for use. | Test results demonstrate that the risk of a delay in the identification of (H3N2)v viruses is mitigated to as low as reasonably possible (ALARP).
Based on the results of the analytical and clinical testing, the device is capable of sensitive detection of (H3N2)v viruses. |
{6}
7
| | Incorrect Diagnosis | Specimen is negative for (H3N2)v but device reports positive | Incorrect reporting of patient results; unnecessary public health investigation and expenditure of resources. | A combination of measures are used to control risk:
-Only trained users are allowed to receive the device
-Specificity of the device is demonstrated.
-Specimens with presumptive positive results for(H3N2)v or other non-standard results are referred to CDC for further analysis | Only trained public health laboratories are allowed to order the device
The device must have high level of analytical and clinical specificity. | Internal controls allow only trained public health laboratories to order the device.
High levels of specificity were previously demonstrated in the cleared predicate. | Test results demonstrate that the risk of an incorrect diagnosis of a specimen as presumptively positive for (H3N2)v have been mitigated to as low as reasonably possibly (ALARP). |
| --- | --- | --- | --- | --- | --- | --- | --- |
{7}
b) LoD, Analytical Reactivity/Inclusivity testing, and testing of clinical specimens were conducted as described in section 3, Device Modifications.
c) Declaration of Conformity
A "Declaration of Conformity" statement was submitted for the manufacturing facility and verification activities and signed by the Deputy Branch Chief, Division of the Scientific Resources, CDC, and the Acting Branch Chief, Virus Surveillance and Diagnostic Branch, CDC, respectively. The statements indicate that:
1. The manufacturing facility is in conformance with design control procedure requirements as specified in 21 CFR 820.30 and the records are available for review.
2. The verification activities, as required by the risk analysis, for the modification were performed by the designated individuals and the results demonstrated that the predetermined acceptance criteria were met.
In conclusion, based on both the results of the analytical testing, clinical specimens testing, and the risk management report, the modified labeling is truthful and accurate. The changes do not affect the performance of the test and it is therefore substantially equivalent to the current cleared test.
7. A Truthful and Accurate Statement, a 510(k) Summary, and the Indications for Use Enclosure.
The labeling for this modified subject device has been reviewed to verify that the indication/intended use for the device is unaffected by the modification. In addition, the submitter's description of the particular modification and the comparative information between the modified and unmodified devices demonstrate that the fundamental scientific technology has not changed. The submitter has provided the design control information as specified in The New 510(k) Paradigm. On this basis, I recommend the device be determined substantially equivalent to the previously cleared device.
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.