K253756 · Roche Molecular Systems, Inc. · QEP · May 15, 2026 · Microbiology
Device Facts
Record ID
K253756
Device Name
cobas liat CT/NG nucleic acid test
Applicant
Roche Molecular Systems, Inc.
Product Code
QEP · Microbiology
Decision Date
May 15, 2026
Decision
SESE
Submission Type
Dual Track
Regulation
21 CFR 866.3393
Device Class
Class 2
Indications for Use
The cobas liat CT/NG nucleic acid test is an automated, qualitative in vitro nucleic acid diagnostic test that utilizes real-time polymerase chain reaction (PCR) for the direct detection of Chlamydia trachomatis (CT) and Neisseria gonorrhoeae (NG) nucleic acid in male/female urine and vaginal swabs, all in cobas PCR Media (Roche Molecular Systems, Inc.). This test is intended as an aid in the diagnosis of urogenital infections in both symptomatic and asymptomatic individuals.
Device Story
The cobas liat CT/NG nucleic acid test is an automated, qualitative in vitro diagnostic test performed on the cobas liat analyzer. It processes biological samples (urine or vaginal swabs in cobas PCR Media) to detect Chlamydia trachomatis (CT) and Neisseria gonorrhoeae (NG) DNA. The system integrates sample purification, nucleic acid amplification, and real-time PCR detection within a closed, self-contained assay tube. The analyzer uses multiple processing modules and actuators to move the sample through pre-packed reagent segments, performing lysis, nucleic acid binding to magnetic particles, washing, elution, and PCR amplification. An embedded microprocessor controls all steps without user intervention. The system provides interpreted results in approximately 20 minutes. It is intended for use in clinical settings to aid in the diagnosis of urogenital infections. Healthcare providers use the output to confirm infection status, facilitating clinical decision-making and patient management.
Clinical Evidence
Multi-site, prospective clinical study (n=4852) compared cobas liat CT/NG results to a Patient Infected Status (PIS) or Composite Comparator Algorithm (CCA) using FDA-cleared NAATs. Performance evaluated across male urine, female urine, and vaginal swabs. Sensitivity for CT ranged 94.6%-98.4% and specificity 99.3%-99.9%. Sensitivity for NG ranged 91.7%-100% and specificity 99.8%-100%. Invalid rate was 0.2% after retesting.
Technological Characteristics
The system utilizes real-time PCR for nucleic acid amplification and detection. It features a closed, self-contained assay tube containing magnetic particles, lysis/wash/elution buffers, and PCR mastermix. The analyzer uses automated sample processing modules and an embedded microprocessor for thermal cycling and real-time fluorescence detection. The system is designed for point-of-care or laboratory use, requiring barcode-based specimen identification. It is a standalone system with no external connectivity requirements for basic operation.
Indications for Use
Indicated for symptomatic and asymptomatic individuals, including males and females, for the diagnosis of urogenital Chlamydia trachomatis and Neisseria gonorrhoeae infections using urine or vaginal swab specimens.
Regulatory Classification
Identification
A device to detect nucleic acids from non-viral microorganism(s) causing sexually transmitted infections and associated resistance marker(s) is an in vitro diagnostic device intended for the detection and identification of nucleic acids from non-viral microorganism(s) and their associated resistance markers in clinical specimens collected from patients suspected of sexually transmitted infections. The device is intended to aid in the diagnosis of non-viral sexually transmitted infections in conjunction with other clinical and laboratory data. These devices do not provide confirmation of antibiotic susceptibility since mechanisms of resistance may exist that are not detected by the device.
Special Controls
A device to detect nucleic acids from non-viral microorganism(s) causing sexually transmitted infections and associated resistance marker(s) must comply with the following special controls: (1) The intended use for the 21 CFR 809.10 labeling must include a detailed description of targets the device detects, the results provided to the user, the clinical indications appropriate for test use, and the specific population(s) for which the device is intended. (2) Any sample collection device used must be FDA-cleared, -approved, or -classified as 510(k) exempt (standalone or as part of a test system) for the collection of specimen types claimed by this device: alternatively, the sample collection device must be cleared in a premarket submission as a part of this device. (3) The 21 CFR 809.10(b) labeling must include: (i) A detailed device description, including reagents, instruments, ancillary materials, all control elements, and a detailed explanation of the methodology, including all pre-analytical methods for processing of specimens; (ii) Detailed discussion of the performance characteristics of the device for all claimed specimen types based on analytical studies, including, but not limited to. Limit of Detection, inclusivity, cross-reactivity, interfering substances, competitive inhibition, carryover/cross contamination, specimen stability, with-in lab precision, and reproducibility, as appropriate; (iii) Detailed descriptions of the test procedure, the interpretation of test results for clinical specimens, and acceptance criteria for any quality control testing. (iv) Limiting statements indicating that: (A)a negative test result does not preclude the possibility of infection; (B) the test results should be interpreted in conjunction with other clinical and laboratory data available to the clinician; (C) reliable results are dependent on adequate specimen collection, transport, storage, and processing. Failure to observe procedures in any one of these steps can lead to incorrect results; and (D)if appropriate (e.g., recommended by CDC, by current well-accepted clinical guidelines, or by published peer reviewed research), that the clinical performance is inferior in a specific clinical subpopulation or for a specific claimed specimen type. (v) If the device is intended to detect antimicrobial resistance markers, limiting statements, as appropriate, indicating that: (A)negative results for claimed resistance markers do not indicate susceptibility of detected microorganisms, as resistance markers not measured by the assay or other potential mechanisms of antibiotic resistance may be present; (B) detection of resistance markers cannot be definitively linked to specific microorganisms and the source of a detected resistance marker may be an organism not detected by the assay, including colonizing flora; (C) detection of antibiotic resistance markers may not correlate with phenotypic gene expression; and (D) therapeutic failure or success cannot be determined based on the assay results, since nucleic acid may persist following appropriate antimicrobial therapy. (4) Design verification and validation must include: (i) Detailed device description documentation, including, but not limited to, methodology from obtaining sample to result, design of primer/probe sequences, rationale for target sequence selection, and computational path from collected raw data to reported result (e.g., how collected raw signals are converted into a reported result). (ii) Detailed documentation of analytical studies including but not limited to, Limit of Detection, inclusivity, cross-reactivity, microbial interference, interfering substances, competitive inhibition, carryover/cross contamination, specimen stability, with-in lab precision, and reproducibility, as appropriate. (iii) Detailed documentation and performance results from a clinical study that includes prospective (sequential) samples for each claimed specimen type and, when determined to be appropriate by FDA, additional characterized clinical samples. The study must be performed on a study population consistent with the intended use population and compare the device performance to results obtained from FDA accepted comparator methods. Documentation from the clinical studies must include the clinical study protocol (including a predefined statistical analysis plan) study report, testing results, and results of all statistical analyses. (iv) A detailed description of the impact of any software, including, but not limited to, software applications and hardware-based devices that incorporate software, on the device's functions.
*Classification.* Class II (special controls). The special controls for this device are:(1) The intended use for the labeling required under § 809.10 of this chapter must include a detailed description of targets the device detects, the results provided to the user, the clinical indications appropriate for test use, and the specific population(s) for which the device is intended.
(2) Any sample collection device used must be FDA-cleared, -approved, or -classified as 510(k) exempt (standalone or as part of a test system) for the collection of specimen types claimed by this device; alternatively, the sample collection device must be cleared in a premarket submission as a part of this device.
(3) The labeling required under § 809.10(b) of this chapter must include:
(i) A detailed device description, including reagents, instruments, ancillary materials, all control elements, and a detailed explanation of the methodology, including all pre-analytical methods for processing of specimens;
(ii) Detailed discussion of the performance characteristics of the device for all claimed specimen types based on analytical studies, including Limit of Detection, inclusivity, cross-reactivity, interfering substances, competitive inhibition, carryover/cross contamination, specimen stability, within lab precision, and reproducibility, as appropriate;
(iii) Detailed descriptions of the test procedure, the interpretation of test results for clinical specimens, and acceptance criteria for any quality control testing;
(iv) Limiting statements indicating that:
(A) A negative test result does not preclude the possibility of infection;
(B) The test results should be interpreted in conjunction with other clinical and laboratory data available to the clinician;
(C) Reliable results are dependent on adequate specimen collection, transport, storage, and processing. Failure to observe proper procedures in any one of these steps can lead to incorrect results; and
(D) If appropriate (
*e.g.,* recommended by the Centers for Disease Control and Prevention, by current well-accepted clinical guidelines, or by published peer reviewed research), that the clinical performance is inferior in a specific clinical subpopulation or for a specific claimed specimen type; and(v) If the device is intended to detect antimicrobial resistance markers, limiting statements, as appropriate, indicating that:
(A) Negative results for claimed resistance markers do not indicate susceptibility of detected microorganisms, as resistance markers not measured by the assay or other potential mechanisms of antibiotic resistance may be present;
(B) Detection of resistance markers cannot be definitively linked to specific microorganisms and the source of a detected resistance marker may be an organism not detected by the assay, including colonizing flora;
(C) Detection of antibiotic resistance markers may not correlate with phenotypic gene expression; and
(D) Therapeutic failure or success cannot be determined based on the assay results, since nucleic acid may persist following appropriate antimicrobial therapy.
(4) Design verification and validation must include:
(i) Detailed device description documentation, including methodology from obtaining sample to result, design of primer/probe sequences, rationale for target sequence selection, and computational path from collected raw data to reported result (
*e.g.,* how collected raw signals are converted into a reported result).(ii) Detailed documentation of analytical studies, including, Limit of Detection, inclusivity, cross-reactivity, microbial interference, interfering substances, competitive inhibition, carryover/cross contamination, specimen stability, within lab precision, and reproducibility, as appropriate.
(iii) Detailed documentation and performance results from a clinical study that includes prospective (sequential) samples for each claimed specimen type and, when determined to be appropriate by FDA, additional characterized clinical samples. The study must be performed on a study population consistent with the intended use population and compare the device performance to results obtained from FDA accepted comparator methods. Documentation from the clinical studies must include the clinical study protocol (including a predefined statistical analysis plan) study report, testing results, and results of all statistical analyses.
(iv) A detailed description of the impact of any software, including software applications and hardware-based devices that incorporate software, on the device's functions.
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY AND INSTRUMENT
## I Background Information:
A 510(k) Number
K253756
B Applicant
Roche Molecular Systems, Inc.
C Proprietary and Established Names
cobas liat CT/NG nucleic acid test
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QEP | Class 2 | 866.3393 – Device to detect nucleic acids from non-viral microorganism(s) causing sexually-transmitted infections and associated resistance marker(s) | Microbiology |
## II Submission/Device Overview:
A Purpose for Submission:
To obtain market clearance for an additional specimen type, female urine.
B Measurand:
Chlamydia trachomatis (CT) cryptic plasmid DNA and 23S ribosomal RNA Neisseria gonorrhoeae (NG) pivNG and NGR9 DNA
C Type of Test:
Qualitative, real time nucleic acid amplification test (NAAT)
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
K253756 - Page 2 of 9
## III Intended Use/Indications for Use:
### A Intended Use(s):
See Indications for Use below.
### B Indication(s) for Use:
The cobas liat CT/NG nucleic acid test is an automated, qualitative in vitro nucleic acid diagnostic test that utilizes real-time polymerase chain reaction (PCR) for the direct detection of *Chlamydia trachomatis* (CT) and *Neisseria gonorrhoeae* (NG) in male/female urine and vaginal swabs, all in cobas PCR Media (Roche Molecular Systems, Inc.).
This test is intended as an aid in the diagnosis of urogenital infections in both symptomatic and asymptomatic individuals.
### C Special Conditions for Use Statement(s):
Rx – For Prescription Use Only
### D Special Instrument Requirements:
To be used on the Roche cobas liat system only
## IV Device/System Characteristics:
### A Device Description:
The cobas liat CT/NG nucleic acid test is performed on the cobas liat analyzer which automates and integrates sample purification, nucleic acid amplification, and detection of the target sequence in biological samples using real-time PCR assays. The assay targets both the Cryptic plasmid and 23S rRNA of CT, and the pivNG and NGR9 of NG. An Internal Control (IC) is also included. The IC is present to control for adequate processing of the target bacteria through steps of sample purification, nucleic acid amplification, and to monitor the presence of inhibitors in the PCR processes. The cobas liat CT/NG nucleic acid test requires the following:
1. A cobas liat CT/NG assay tube which contains the following:
- Internal process control (IPC)
- PCR mastermix (assay specific oligonucleotides and polymerase)
- Co-factor, liat magnetic particles, Lysis buffer, Wash buffer, and Elution buffer
2. Specimen sample stored in cobas PCR Media
3. cobas liat CT/NG/MG Control Kit
- Contains positive and negative control tubes for validating new cobas liat CT/NG/MG assay tube lots.
4. cobas liat System
5. liat Assay Specific Package (LASP)
### B Principle of Operation:
A specimen in cobas PCR Media is collected and then transferred into the assay tube using a transfer pipette. The assay tube is loaded into the analyzer and processing begins. The cobas liat assay tube uses a flexible tube as a sample processing vessel and contains all requisite PCR
{2}
reagents pre-packed in tube segments that are separated by breakable seals. When a cobas liat assay tube containing a raw biological sample is inserted into the cobas liat analyzer, multiple sample processing actuators in the cobas liat analyzer compress the cobas liat assay tube to selectively release the reagents, moving the sample from one segment to the next, and controlling reaction conditions.
The analyzer automates sample preparation by mixing the sample with an internal control, lysis reagents and liat Magnetic Particles, which are then incubated for nucleic acid binding to the liat Magnetic Particles, and then washed to remove possible inhibitors. Subsequently, the nucleic acid is eluted from the liat Magnetic Particles, mixed with MasterMix and cofactor, and transferred alternately between assay tube segments at different temperatures for rapid PCR amplification and real-time detection.
An embedded microprocessor controls and coordinates these actions to perform all required assay processes with no user intervention required. The detection unit monitors the reaction in real-time while an on-board computer analyzes the collected data and outputs an interpreted result. All assay steps are performed within the closed and self-contained cobas liat assay tube, minimizing cross-contamination between samples. The sample to result time is approximately 20 minutes
## C Instrument Description Information:
1. Instrument Name:
cobas liat system
2. Specimen Identification:
The cobas liat system maintains positive identification of each sample and assay tube during processing and analysis by means of barcode labels.
Before starting a run, the user is required to scan the assay tube barcode and then scan the sample barcode. The user then transfers the sample into the assay tube and is required to scan the assay tube barcode again before inserting the assay tube into the analyzer and starting the run
3. Specimen Sampling and Handling:
Specimen sampling and handling during the assay is controlled automatically using multiple sample processing modules contained within the cobas liat System.
4. Calibration:
Not applicable
5. Quality Control:
## External Control
Before using a new lot of cobas liat CT/NG assay tubes, the "Lot Validation" procedure must be performed on the analyzer to validate the cobas liat CT/NG assay tube lot. The procedure includes running a negative control and a positive control in separate runs. After processing
K253756 - Page 3 of 9
{3}
is completed for each control, the system will inform the user that the control result has been accepted. The user can now use that specific lot of assay tubes for processing samples.
## Internal Control
An armored RNA is included in the cobas liat CT/NG assay tube. This control acts to monitor the successful execution of the entire assay, from nucleic acid extraction from the targeted microorganisms, amplification, and detection and reporting. The internal control also acts to identify any PCR inhibitors detected in the sample.
## V Substantial Equivalence Information:
A Predicate Device Name(s): cobas 6800/8800 CT/NG
B Predicate 510(k) Number(s): K202408
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K253756 | K202408 |
| --- | --- | --- |
| Device Trade Name | cobas liat CT/NG | cobas 6800/8800 CT/NG |
| | | |
| Intended Use/Indications For Use | The cobas liat CT/NG nucleic acid test is an automated, qualitative in vitro nucleic acid diagnostic test that utilizes real-time polymerase chain reaction (PCR) for the direct detection of Chlamydia trachomatis (CT) and Neisseria gonorrhoeae (NG) in male/female urine and vaginal swabs, all in cobas PCR Media (Roche Molecular Systems, Inc.).
This test is intended as an aid in the diagnosis of urogenital infections in both symptomatic and asymptomatic | The cobas CT/NG on the cobas 6800/8800 system is an automated, qualitative in vitro nucleic acid diagnostic test, that utilizes real-time polymerase chain reaction (PCR), for the direct detection of Chlamydia trachomatis (CT) and/or Neisseria gonorrhoeae (NG) DNA in male and female urine, clinician-instructed self-collected vaginal swab specimens (collected in a clinical setting), and clinician-collected vaginal swab specimens, endocervical swab specimens, oropharyngeal (throat) swab specimens and |
K253756 - Page 4 of 9
{4}
| | individuals. | anorectal swab specimens all collected in cobas PCR Media (Roche Molecular Systems, Inc.), and cervical specimens collected in PreservCyt solution. This test is intended as an aid in the diagnosis of chlamydial and gonococcal disease in both symptomatic and asymptomatic individuals. |
| --- | --- | --- |
| Sample Preparation | Automated | Same |
| Amplification Technology | Real-Time PCR | Same |
| Analyte Targets | Detection CT or NG | Detection CT or NG |
| Specimens Utilized | Male urine
Female urine
Vaginal swab | Male urine
Female urine
Self-collected vaginal swab
Clinician-collected vaginal swab
Endocervical swab
Endocervical specimen in PreservCyt
Oropharyngeal (throat) swab
Anorectal swab specimens |
| Detection Chemistry | Assay using different reporter dyes for targets and control | Paired reporter and quencher fluorescence labeled probes (TaqMan Technology) using fluorescence resonance energy transfer (FRET) |
| | | |
VI Standards/Guidance Documents Referenced:
Class II Special Controls as per 21 CFR 866.3393
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
K253756 - Page 5 of 9
{5}
1. Precision/Reproducibility:
See previous submission, K240217
2. Linearity:
Not applicable.
3. Analytical Specificity/Interference:
See previous submission, K240217
4. Detection Limit and Assay Reportable Range:
See previous submission, K240217
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
See previous submission, K240217
6. Assay Cut-Off:
See previous submission, K240217
## B Comparison Studies:
1. Method Comparison with Predicate Device:
See Clinical Studies section below
2. Matrix Comparison:
Not applicable
## C Clinical Studies:
1. Clinical Performance:
Clinical performance for the cobas liat CT/NG nucleic acid test for vaginal swab and male urine specimens is described in K240217.
Clinical performance of the cobas liat CT/NG nucleic acid test in female urine specimens was established in a multi-site, prospective study (described in K240217) comparing the results to a Composite Comparator Algorithm (CCA) for CT and NG. CCA for CT and NG was derived from testing female urine specimens on three FDA-cleared NAATs. The subject was considered positive for CT and NG if two out of three comparator NAATs were positive. The subject was considered negative for CT and NG if two out of three NAATs were negative. Female urine specimens were collected and tested at 13 geographically diverse
K253756 - Page 6 of 9
{6}
intended use clinical sites across the US. There were 48 operators that took part in cobas liat CT/NG testing, of which, 43 represented CLIA-waived operators. Five of the 48 operators represented experienced laboratorians in a moderate complexity laboratory. A total of 2512 female subjects were enrolled in the study and provided specimens for collection. Of the evaluable subjects, there were 2459 specimens included in the final clinical performance. Subjects provided a urine specimen that was aliquoted into the respective manufacturers' collection devices and cobas PCR Media.
A supplemental study was conducted to evaluate the performance of cobas liat CT/NG nucleic acid test for the assessment of detecting CT in female urine specimens. Specimen collection was performed at one external site. Nine operators with minimal or no hands-on laboratory training performed the testing. There were a total of 785 prospective samples from subjects who met the study eligibility criteria. Of these 785 samples, there were a total of 751 samples with evaluable results and included in the final data set. The final evaluation was determined by comparing results from cobas liat CT/NG nucleic acid test to CCA.
Analysis of both studies show that the cobas liat CT/NG nucleic acid test detected $8.4\%$ fewer CT infections and $6.9\%$ fewer NG infections in female urine when compared to a vaginal swab CCA versus a female urine CCA. Clinical performance of the cobas liat CT/NG nucleic acid test is shown in Tables 1 and 2.
Table 1: CT Clinical Performance in Female Urine against the CCA Result
| Study | Symptom Status | N | TP | FP | TN | FN | PPA (95% CI) | NPA (95% CI) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Supplemental Study | Symptomatic | 312 | 17 | 2 | 293 | 0 | 100% (81.6%-100%) | 99.3% (97.6%-99.8%) |
| Supplemental Study | Asymptomatic | 439 | 15 | 3 | 420 | 1 | 93.8% (71.7%-98.9%) | 99.3% (97.9%-99.8%) |
| Supplemental Study | Overall | 751 | 32 | 5 | 713 | 1 | 97.0% (84.7%-99.5%) | 99.3% (98.4%-99.7%) |
| K240217 Study | Symptomatic | 1113 | 53 | 2 | 1054 | 4 | 93.0% (83.3%-97.2%) | 99.8% (99.3%-99.9%) |
| K240217 Study | Asymptomatic | 1346 | 40 | 3 | 1302 | 1 | 97.6% (87.4%-99.6%) | 99.8% (99.3%-99.9%) |
| K240217 Study | Overall | 2459 | 93 | 5 | 2356 | 5 | 94.9% (88.6%-97.8%) | 99.8% (99.5%-99.9%) |
| Combined | Symptomatic | 1425 | 70 | 4 | 1347 | 4 | 94.6% (86.9%-97.9%) | 99.7% (99.2%-99.9%) |
| Combined | Asymptomatic | 1785 | 55 | 6 | 1722 | 2 | 96.5% (88.1%-99.0%) | 99.7% (99.2%-99.8%) |
| Combined | Overall | 3210 | 125 | 10 | 3069 | 6 | 95.4% (90.4%-97.9%) | 99.7% (99.4%-99.8%) |
Table 2: NG Clinical Performance in Female Urine against the CCA Result
| Symptom Status | N | TP | FP | TN | FN | PPA (95% CI) | NPA (95% CI) |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Symptomatic | 1111 | 20 | 1 | 1090 | 0 | 100% (83.9%-100%) | 99.9% (99.5%-100%) |
| Asymptomatic | 1347 | 17 | 1 | 1329 | 0 | 100% (81.6%-100%) | 99.9% (99.6%-100%) |
| Overall | 2458 | 37 | 2 | 2419 | 0 | 100% (90.6%-100%) | 99.9% (99.7%-100%) |
K253756 - Page 7 of 9
{7}
K253756 - Page 8 of 9
2. Clinical Cut-Off
Not applicable
D Expected Values/Reference Range:
Table 3: Positivity rate for the cobas liat CT/NG nucleic acid test in female urine specimens during the study by collection site is shown below.
| Collection Site | CT | NG |
| --- | --- | --- |
| 1 | 6.6%
(10/151) | 2.0%
(3/151) |
| 2 | 5.4%
(13/240) | 3.8%
(9/240) |
| 3 | 7.4%
(27/365) | 0.6%
(2/362) |
| 4 | 0.0%
(0/161) | 1.2%
(2/161) |
| 5 | NC | NC |
| 6 | 2.4%
(2/83) | 0.0%
(0/83) |
| 7 | 7.5%
(3/40) | 2.5%
(1/40) |
| 8 | 0.0%
(0/17) | 0.0%
(0/17) |
| 9 | 1.9%
(10/524) | 1.5%
(8/526) |
| 10 | 0.9%
(3/348) | 0.9%
(3/348) |
| 11 | 4.6%
(14/304) | 2.3%
(7/304) |
| 12 | 9.6%
(13/136) | 1.5%
(2/136) |
| 13 | 4.0%
(4/101) | 2.0%
(2/101) |
| 14 | 4.9%
(37/751) | - |
NC: non calculable as no female subjects were enrolled at this site
E Other Supportive Instrument Performance Characteristics Data:
Not applicable.
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
IX Conclusion:
{8}
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K253756 - Page 9 of 9
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.
