TIGRIS DTS AUTOMATED ANALYZER FOR AUTOMATING AMPLIFIED NUCLEIC ACID TEST ASSAYS
K032194 · Gen-Probe, Inc. · LSL · Dec 24, 2003 · Microbiology
Device Facts
Record ID
K032194
Device Name
TIGRIS DTS AUTOMATED ANALYZER FOR AUTOMATING AMPLIFIED NUCLEIC ACID TEST ASSAYS
Applicant
Gen-Probe, Inc.
Product Code
LSL · Microbiology
Decision Date
Dec 24, 2003
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.3390
Device Class
Class 2
Indications for Use
The APTIMA Combo 2 Assay is a target amplification nucleic acid probe test that utilizes target capture for the in vitro qualitative detection and differentiation of ribosomal RNA (rRNA) from Chlamydia trachomatis and/or Neisseria gonorrhoeae in endocervical and male urethral swab specimens, and in female and male urine specimens. The assay may be used to test specimens from symptomatic and asymptomatic individuals to aid in the diagnosis of gonococcal and/or chlamydial urogenital disease using the TIGRIS DTS Automated Analyzer or semi-automated instrumentation as specified.
Device Story
Tigris DTS is an automated analyzer for the Aptima Combo 2 Assay; replaces semi-manual processing. System inputs: patient swab or urine specimens in transport tubes. Operation: computer workstation directs analyzer modules to perform sample processing, target capture, amplification, detection, and data reduction. Mechanical components: fluid delivery module, magnetic wash station, incubators, and luminometer. Output: qualitative detection/differentiation of C. trachomatis and N. gonorrhoeae rRNA. Used in clinical laboratories; operated by trained personnel. System software monitors status, inventories, and test results. Output used by clinicians to diagnose urogenital infections. Benefits: full automation of assay steps, reducing manual labor and potential for human error.
Clinical Evidence
No clinical trials; evidence based on parallel testing of clinical specimens (swabs/urine) and contrived panels comparing Tigris automated results to semi-manual DTS results. Overall percent agreement for urine specimens was 99.2% (95% CI: 98.1% - 99.5%). Some reduced agreement observed in asymptomatic female populations for C. trachomatis. Carry-over studies indicated potential for low-level contamination (up to 2%).
Technological Characteristics
Automated nucleic acid amplification and detection system. Utilizes target capture, transcription-mediated amplification (TMA), and hybridization protection assay (HPA) technologies. System is a floor-standing automated analyzer. Software-controlled fluidics and thermal cycling. Connectivity for laboratory information systems (LIS).
Indications for Use
Indicated for symptomatic and asymptomatic individuals to aid in the diagnosis of gonococcal and/or chlamydial urogenital disease using endocervical swabs, male urethral swabs, and female/male urine specimens.
Regulatory Classification
Identification
Neisseria spp. direct serological test reagents are devices that consist of antigens and antisera used in serological tests to identify Neisseria spp. from cultured isolates. Additionally, some of these reagents consist of Neisseria spp. antisera conjugated with a fluorescent dye (immunofluorescent reagents) which may be used to detect the presence of Neisseria spp. directly from clinical specimens. The identification aids in the diagnosis of disease caused by bacteria belonging to the genus Neisseria, such as epidemic cerebrospinal meningitis, meningococcal disease, and gonorrhea, and also provides epidemiological information on diseases caused by these microorganisms. The device does not include products for the detection of gonorrhea in humans by indirect methods, such as detection of antibodies or of oxidase produced by gonococcal organisms.
Predicate Devices
Gen-Probe Aptima® Combo 2 Assay (k003395)
Submission Summary (Full Text)
{0}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
DEVICE ONLY TEMPLATE
A. 510(k) Number: k032194
B. Analyte: Chlamydia trachomatis and Neisseria gonorrhoeae rRNA
C. Type of Test: Automation for Aptima Combo 2 Assay
D. Applicant: Gen-Probe, Inc.
E. Proprietary and Established Names: Tigris DTS™ Gen-Probe® Aptima® Combo 2 Assay
F. Regulatory Information:
1. Regulation section: 21 CFR Part 866.3390 and 866.3120, Chlamydia Serological Reagents and Neisseria spp. Direct Serological Test Reagents
2. Classification: Class II
3. Product Code: LSL and MKZ
4. Panel: 83
G. Intended Use: The APTIMA Combo 2 Assay is a target amplification nucleic acid probe test that utilizes target capture for the in vitro qualitative detection and differentiation of ribosomal RNA (rRNA) from Chlamydia trachomatis and/or Neisseria gonorrhoeae in endocervical and male urethral swab specimens, and in female and male urine specimens. The assay may be used to test specimens from symptomatic and asymptomatic individuals to aid in the diagnosis of gonococcal and/or chlamydial urogenital disease using the TIGRIS DTS Automated Analyzer or semi-automated instrumentation as specified.
1. Indication(s) for use: The assay may be used to test specimens from symptomatic and asymptomatic individuals to aid in the diagnosis of gonococcal and/or chlamydial urogenital disease using the TIGRIS DTS Automated Analyzer or semi-automated instrumentation as specified.
2. Special condition for use statement(s): The Tigris DTS can only be used with specimens collected in the Aptima Unisex Swab Specimen Collection kit and the Aptima Urine Specimen Collection kit. PACE Specimen Collection Kits cannot be adapted for use on the Tigris DTS.
{1}
Page 2 of 9
3. Special instrument Requirements: The Tigris DTS instrument is an automated analyzer that has been validated for use with the modified Aptima Combo 2 Assay reagents and procedure.
## H. Device Description:
The reagents for the Tigris DTS APTIMA® Combo 2 assay are unchanged from the semi-manual version. The Tigris instrument platform was developed to fully automate all steps necessary to perform the APTIMA® Combo 2 assay from sample processing through amplification, detection and data reduction. Volumes of reagents are modified for use on the automated instrument, the TIGRIS DTS System.
The two main components of the TIGRIS DTS System are the analyzer and the computer workstation. The computer workstation directs the analyzer modules to perform each assay step. The analyzer houses all of the fluids, reagents, consumables, and mechanical parts that perform the assay.
These mechanical parts include a fluid delivery module (syringes, pumps, and valves), holding areas for reagents and waste products, a sample bay (for loading sample racks, pipette tips and TCR reagent), pipettors for reagents and samples, syringes for dispensing reagents and specimens, a magnetic wash station, various mixers, four incubators, and a luminometer. One sample carousel can hold up to 9 racks and each rack can hold 20 specimen tubes. An internal vacuum system controls aspiration of liquid from the magnetic wash station. Barcode scanners (one in the lower bay, one in the sample bay, one in the assay reagent bay, and others) are used for reagent and specimen tracking. System software monitors system status, reagent and supply inventories, worklists, test results, and maintenance.
## I. Substantial Equivalence Information:
1. Predicate device name(s): Gen-Probe Aptima® Combo 2 Assay
2. Predicate K number(s): k003395
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended Use | See above | Same |
| | | |
| Reagent stability | Adapted for Tigris platform | See Package Insert |
| Result output | Software mediated | Software mediated |
| Analytical Sensitivity (per assay) | <0.1 IFU C. trachomatis
15 CFU N. gonorrhoeae | <0.1 CFU C. trachomatis
15 CFU N. gonorrhoeae |
| Analytical specificity | N. elongata – increased signal | N. elongata – increased signal |
| Differences | | |
| Item | Device | Predicate |
| Indications | Automated | Semi-automated |
{2}
# J. Standard/Guidance Document Referenced (if applicable): NA
K. Test Principle: The Tigris allows full automation of the Aptima Combo 2 procedure. Specimen tubes and controls are loaded onto the instrument, along with necessary reagents and other supplies (pipet tips, MTUs, etc.). Test results are handled by software that generates printed worklists.
# L. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
a. Precision/Reproducibility: Agreement of Tigris results with expected results for spiked specimens was reduced compared to manual testing (85% vs. 100% for low level C. trachomatis - 0.25 IFU/mL or 0.1 IFU/assay). All other levels of C. trachomatis and N. gonorrhoeae were 100% reproducible in all specimen pools.
CT/GC Clinical Panel Agreement Study: Agreement with Expected CT and GC Results
| Panel Member CT/GC | Panel Member Concentration1 | | Replicates | CT | | GC | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | CT IFU/mL | GC CFU/mL | | TIGRIS %Agrmt | DTS %Agrmt | TIGRIS %Agrmt | DTS %Agrmt |
| Low/Low | 2.5 | 125 | 20 | 100 | 100 | 100 | 100 |
| Low/High | 2.5 | 125,000 | 20 | 100 | 951 | 100 | 100 |
| High/Low | 2,500 | 125 | 20 | 100 | 100 | 100 | 100 |
| High/High | 2,500 | 125,000 | 20 | 100 | 100 | 100 | 100 |
| Very Low/Neg | 0.252 | 0 | 20 | 854 | 100 | 100 | 100 |
| Low/Neg | 2.5 | 0 | 20 | 100 | 100 | 100 | 100 |
| Medium/Neg | 25 | 0 | 20 | 100 | 100 | 100 | 100 |
| High/Neg | 2,500 | 0 | 20 | 100 | 100 | 100 | 100 |
| Neg/Very Low | 0 | 12.5 | 20 | 100 | 100 | 100 | 100 |
| Neg/Low | 0 | 125 | 20 | 100 | 100 | 100 | 100 |
| Neg/Medium | 0 | 1,250 | 19 | 100 | 100 | 100 | 100 |
| Neg/High | 0 | 125,000 | 20 | 100 | 100 | 100 | 100 |
{3}
Page 4 of 9
Neg/Neg 0 0 20 100 100 100 100
Overall Percent Agreement between TIGRIS and DTS (95% C.I.): 99.3% (98.3% - 99.8%)
IFU – Inclusion Forming Units, CFU – Colony Forming Units, TIGRIS %Agrmt = Agreement between TIGRIS with expected results
DTS %Agrmt = Agreement between DTS with expected results
¹A collection tube contains approximately 2.9 mL of transport medium for swab specimens and 4.0 mL of transport medium/urine mixture for urine specimens.
²The CT concentration in this CT/GC clinical panel member is one log below the APTIMA Combo 2 Assay analytical sensitivity claim of 1 IFU/assay (7.25 IFU/swab, 5 IFU/mL urine).
³One of 5 female urine panel replicates was CT- on the DTS System.
⁴Three of 5 female urine panel replicates were CT- on the TIGRIS System.
b. Linearity/assay reportable range: NA
RLU levels cannot be compared because the kinetic algorithm moderates interpretation
c. Traceability (controls, calibrators, or method): Controls are prepared in-house by the manufacturer and are not traceable to a standard or independent measure.
d. Detection limit:
<0.1 IFU C. trachomatis
15 CFU N. gonorrhoeae
e. Analytical specificity:
N. elongata – increased signal in a clean system
f. Assay cut-off:
The kinetic profiles were modified with the Tigris application.
Although the cutoffs measured in RLUs is the same, the computation of the kinetic profiles was changed (specifications for parameters A, B, C, and D and for Zone A1, A2, A4, A5, B3, C1, C2, C3 and C4)
g. Carry-over testing performed:
Results
| | Negative | Equivocal | Positive | Total |
| --- | --- | --- | --- | --- |
| Instrument 1 | 345 | 3 | 4 | 352 |
| Instrument 2 | 347 | 0 | 0 | 347 |
| Instrument 3 | 393 | 2 | 3 | 398 |
| | | | | 1097 |
2. Comparison studies:
a. Method comparison with predicate device:
{4}
Page 5 of 9
Aptima Combo 2 testing was done with the Tigris and manual DTS on swab and urine specimens from symptomatic and asymptomatic males and females. C. trachomatis agreement for asymptomatic females and other groups was reduced or not statistically interpretable (lower 95% CI were <90%).
b. Matrix comparison: NA
3. Clinical studies: NA; the sponsor performed an evaluation of agreement between the Tigris and manual DTS on the same specimen. As a result clinical sensitivity and specificity of the Tigris could not be established.
a. Clinical sensitivity: NA
b. Clinical specificity: NA
c. Other clinical supportive data (when a and b are not applicable): The Aptima Combo 2 assay was previously shown to have predictable performance with urine and urogenital swab specimens from males and females, both symptomatic and asymptomatic for the detection of C. trachomatis and N. gonorrhoeae. Parallel testing of these specimen types was done with the semi-manual and the fully automated Tigris system. Agreement between the two methods is shown in the attached tables. Females, especially asymptomatic females, are at highest risks for adverse consequences of a false positive or negative assay test results, and this group had the lowest agreement for both swab and urine specimen types when Chlamydia trachomatis was detected by the semi-manual method.
For CT swab testing, for both asymptomatic males and asymptomatic females, point estimates for positive agreement is <95% and lower confidence boundaries are both <75%. GC agreement had reduced positivity (<95%) with asymptomatic males and also symptomatic females. Even when all groups are combined, for swabs tested by Tigris for both males and females, agreement is 90% (83.2 – 94.7%, 95% CI) with AC2CT+/GC- done semi-manually; agreement for urines is 92.6% (85.9 – 96.7% CI) overall for CT+/GC-.
Qualitative Agreement findings for clinical specimens (tested at Gen-Probe)
Clinical Specimen Agreement Study: Swab Specimen Results
| TIGRIS System | DTS System | | | | Total |
| --- | --- | --- | --- | --- | --- |
| | CT+/GC+ | CT+/GC- | CT-/GC+ | CT-/GC- | |
| CT+/GC+ | 30 | 0 | 0 | 0 | 30 |
| CT+/GC- | 0 | 108 | 0 | 2^{5} | 110 |
| CT-/GC+ | 1^{2} | 0 | 67 | 0 | 68 |
| CT-/GC- | 0 | 12^{3} | 2^{4} | 796 | 810 |
{5}
Clinical Specimen Agreement Study: Urine Specimen Results
| TIGRIS System | DTS System | | | | Total |
| --- | --- | --- | --- | --- | --- |
| | CT+/GC+ | CT+/GC- | CT-/GC+ | CT-/GC- | |
| CT+/GC+ | 32 | 0 | 0 | 0 | 32 |
| CT+/GC- | 0 | 100 | 0 | 13 | 101 |
| CT-/GC+ | 0 | 0 | 52 | 0 | 52 |
| CT-/GC- | 0 | 81 | 12 | 776 | 785 |
| Total | 32 | 108 | 53 | 777 | 970 |
| Percent | 100% | 92.6% | 98.1% | 99.9% | n/a |
| | Overall Percent Agreement (95% C.I.): 99.2% (98.1% - 99.5%) | | | | |
+ denotes Positive, - denotes Negative, n/a = Not Applicable
Clinical Specimen Agreement Study: CT Results
| Gender | Specimen | Symptom | N | DTS+ TIGRIS+ n | DTS+ TIGRIS- n | DTS- TIGRIS+ n | DTS- TIGRIS- n | Positive Agreement (95% C.I.) | Negative Agreement (95% C.I.) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| All | Swab | Symptomatic | 425 | 84 | 32 | 0 | 338 | 96.6 (90.3-99.3) | 100 (98.9-100) |
| | | Asymptomatic | 596 | 54 | 103 | 26 | 530 | 84.4 (73.1-92.2) | 99.6 (98.6-100) |
| | | All | 1021 | 138 | 13 | 2 | 868 | 91.4 (85.7-95.3) | 99.8 (99.2-100) |
| | Urine | Symptomatic | 407 | 80 | 44 | 0 | 323 | 95.2 (88.3-98.7) | 100 (98.9-100) |
| | | Asymptomatic | 563 | 52 | 45 | 17 | 506 | 92.9 (82.7-98.0) | 99.8 (98.9-100) |
| | | All | 970 | 132 | 8 | 1 | 829 | 94.3 (89.1-97.5) | 99.9 (99.3-100) |
Clinical Specimen Agreement Study: GC Results
| Gender | Specimen | Symptom | N | DTS+ TIGRIS+ n | DTS+ TIGRIS- n | DTS- TIGRIS+ n | DTS- TIGRIS- n | Positive Agreement (95% C.I.) | Negative Agreement (95% C.I.) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| All | Swab | Symptomatic | 423 | 80 | 12 | 0 | 342 | 98.8 (93.3-100) | 100 (98.9-100) |
| | | Asymptomatic | 595 | 18 | 13 | 0 | 576 | 94.7 (74.0-99.9) | 100 (99.4-100) |
| | | All | 1018 | 98 | 2 | 0 | 918 | 98.0 (93.0-99.8) | 100 (99.6-100) |
| | Urine | Symptomatic | 407 | 72 | 14 | 0 | 334 | 98.6 (92.6-100) | 100 (98.9-100) |
| | | Asymptomatic | 563 | 12 | 0 | 0 | 551 | 100 (73.5-100) | 100 (99.3-100) |
| | | All | 970 | 84 | 1 | 0 | 885 | 98.8 (93.6-100) | 100 (99.6-100) |
| Female5 | Swab | All | 567 | 26 | 1 | 0 | 540 | 96.3 (81.0-99.9) | 100 (99.3- 100) |
| | Urine | All | 562 | 20 | 1 | 0 | 541 | 95.2 (76.2-99.9) | 100 (99.3- 100) |
{6}
Page 7 of 9
| Male^{5} | Swab | All | 451 | 72 | 1 | 0 | 378 | 98.6 (92.6- 100) | 100 (99.0- 100) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Urine | All | 408 | 64 | 0 | 0 | 344 | 100 (94.4- 100) | 100 (98.9- 100) |
+ denotes Positive, - denotes Negative, C.I. = Confidence Interval
FDA requested additional evidence to support the comparability of the two methods. The company reported additional data from comparison of the 2 methods at an independent laboratory evaluating the automated system. In that report, disagreement was not seen for a large sampling of specimens, presumably representing the targeted population (asymptomatic females).
Additionally, a contrived panel of simulated specimens was parallel tested on the 2 systems. Agreement was shown for most levels tested, except for the female urine pool containing very low numbers of Chlamydia trachomatis IFUs.
Carryover studies showed that low levels of contamination could be expected (up to 2% on one of three instruments evaluated).
Warnings are included in the package insert to advise laboratories.
4. Clinical cut-off: Analytically, there was no difference in CT/GC results using the new kinetic profiles (Tigris-specific) for 5 different instruments, different temperatures (13, 15, 18-22, 25, and 27°), relative humidity of 20-80%, 2 different reagent kit lots, when AutoDetect volumes were varied, or when injection rates were varied). rRNA solutions in a clean system were used for this verification. FDA believes that these solutions may not be representative of actual testing conditions with specimen material and evaluated the differences in RLU levels for different specimen types from the parallel testing done with clinical specimens and spiked pooled specimen material.
5. Expected values/Reference range: The presence of C. trachomatis or N. gonorrhoeae in any amount is considered indicative of urogenital infection.
M. Instrument Name: Tigris DTS Automated Analyzer
N. System Descriptions:
1. Modes of Operation: Batch, closed tube
2. Software: Release version will be 1.05; FDA reviewed submitted materials for 1.04 that will be updated prior to release. The system uses Windows NT (Service Pack 6). The analyzer relies on the computer workstation for instruction, communicating system status, and results through a standard serial interface, and provides a link to the LIS.
FDA has reviewed applicant's Hazard Analysis and software development processes for this line of product types:
{7}
Page 8 of 9
Yes ☐ x ☐ or No ☐
3. Sample Identification: Barcode and MTU/rack position
Sample tube barcodes may use any of the formats specified below. Tigris must be configured to read Code 39 and Codabar formatted barcodes. The analyzer is always enabled to read Code 128 (ISBT 128) and Code 12 of 5 (I 2 of 5) formatted barcodes. All barcodes must have 2-20 characters (with no commas) and have a feature size from 6.5 mil (0.16 mm) to 10 mil (0.245 mm).
| Type | Enable Options | Checksum Options |
| --- | --- | --- |
| Code 39 | Enabled through TIGRIS DTS checksum. | Use checksum, send System software. |
| Code 128 (ISBT 128) | Always enabled | None |
| Code 12 of 5 | Always enabled. | No checksum allowed. |
| Codabar | Enabled through TIGRIS DTS System software. | Send checksum, send start/stop characters. |
4. Specimen Sampling and Handling: Specimens are collected (either a swab or a urine specimen) and transferred to the Aptima Specimen Collection device (swab or urine transport tubes containing transport/stabilizing medium). These tubes are placed into racks containing 20 tubes each. The tubes must be visually checked for adequate volume and precipitates.
5. Assay Types: Aptima Combo 2
6. Reaction Types: kinetic fluorescent (luminometer)
7. Calibration: SysCheck reagent for luminometer; Assay RNA controls
8. Quality Control: Assay controls are RNA preparations that would not monitor factors associated with matrix in the test system; users must prepare controls from ATCC preparations, culture growth, or use previously positive specimen material.
{8}
Page 9 of 9
O. Conclusion:
The Tigris DTS test system appears to produce results similar to results obtained with the Aptima Combo 2 Assay performed as previously cleared (semi-manual). Labeling precautions and warnings are incorporated to advise users of potential errors that may occur and when software will not alert users of potential problems.
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.