The PAXgene™ Blood RNA System consists of a blood collection tube (PAXgene™ Blood RNA Tube) and nucleic acid purification kit (PAXgene™ Blood RNA Kit). It is intended for the collection, storage, and transport of blood and stabilization of intracellular RNA in a closed tube and subsequent isolation and purification of host RNA from whole blood for RT-PCR used in molecular diagnostic testing. Performance characteristics for the PAXgene™ Blood RNA System have only been established with "cfos and IL1B." The user is responsible for establishing appropriate PAXgene™ Blood RNA System performance characteristics for other target transcripts.
Device Story
System comprises sterile evacuated blood collection tube containing stabilization solution (tetradecyl trimethyl-ammonium oxalate, tartaric acid) and nucleic acid purification kit (buffers, proteinase K, DNase set, spin columns). Input: 2.5 mL whole blood collected via venipuncture. Operation: stabilization solution lyses cells, inhibits RNases, and prevents gene expression induction; subsequent processing involves centrifugation, enzymatic protein digestion, DNA shearing via shredder column, and selective RNA binding to spin column membrane. Output: purified host RNA suitable for RT-PCR. Used in clinical laboratory settings by trained personnel. Healthcare providers use resulting RNA for molecular diagnostic assays; device ensures sample integrity during storage/transport, enabling accurate downstream diagnostic testing.
Clinical Evidence
No clinical data. Bench testing only. Validation included precision/reproducibility studies using CFOS/18S rRNA and IL1B/18S rRNA Q-RT-PCR duplex assays across 3 laboratories, 3 technicians, and 3 reagent lots. RNA yield, purity (A260/A280 ratio 1.8-2.2), and integrity confirmed via absorbance and electropherograms. Stability studies (real-time and accelerated) confirmed performance for 19 months at 25°C. RT-PCR inhibition testing showed no interference from kit components.
Technological Characteristics
System includes evacuated plastic blood collection tube with stabilization solution (tetradecyl trimethyl-ammonium oxalate, tartaric acid) and purification kit (buffers, proteinase K, DNase I, spin columns). Principle: chemical lysis and stabilization followed by silica-membrane-based spin column purification. Connectivity: none (standalone). Sterilization: sterile tube. Software: none.
Indications for Use
Indicated for professional use only for the collection, storage, transport, and stabilization of intracellular RNA from whole blood in patients with white blood cell counts between 4.8 and 11.0 x 10^6 cells/mL for subsequent RT-PCR molecular diagnostic testing.
Regulatory Classification
Identification
RNA Preanalytical Systems are devices intended to collect, store, and transport patient specimens, and stabilize intracellular RNA from the specimens, for subsequent isolation and purification of the intracellular RNA for RT-PCR used in in vitro molecular diagnostic testing.
Special Controls
*Classification.* Class II (special controls). The special control is FDA's guidance document entitled “Class II Special Controls Guidance Document: RNA Preanalytical Systems (RNA Collection, Stabilization and Purification System for RT-PCR Used in Molecular Diagnostic Testing).” See § 866.1(e) for the availability of this guidance document.
Submission Summary (Full Text)
{0}------------------------------------------------
#### 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
- A. 510(k) Number: k042613
- B. Purpose for Submission: Clearance of new device
- C. Measurand: Ribonucleic acid (RNA)
#### D. Type of Test:
Collection, stabilization, and purification of intercellular RNA from whole blood for RT-PCR use in molecular diagnostic testing.
## E. Applicant:
PreAnalytiX GmbH
## F. Proprietary and Established Names:
PAXgene™ Blood RNA System
#### G. Regulatory Information:
- 1. Regulation section: 21 CFR §866.4070, RNA Preanalytical Systems
- 2. Classification: Class II (de novo)
- 3. Product code: NTW
- 4. Panel: Immunology (82)
#### H. Intended Use:
- 1. Intended use(s):
The PAXgene™ Blood RNA System consists of a blood collection tube (PAXgene™ Blood RNA Tube) and nucleic acid purification kit (PAXgene™ Blood RNA Kit). It is intended for the collection, storage, and transport of blood and stabilization of intracellular RNA in a closed tube and subsequent isolation and purification of host RNA from whole blood for RT-PCR used in molecular diagnostic testing.
Performance characteristics for the PAXgene™ Blood RNA System have only been established with "cfos and IL1B." The user is responsible for establishing appropriate PAXgene™ Blood RNA System performance characteristics for other target transcripts.
{1}------------------------------------------------
- 2. Indication(s) for use: See intended use above
- 3. Special conditions for use statement(s): For professional use only
- 4. Special instrument requirements: General laboratory equipment (centrifuges, etc.)
## I. Device Description:
The PAXgene™ Blood RNA System consists of:
- the PAXgene™ Blood RNA tubes and .
- the PAXgene™ Blood RNA kit. .
The PAXgene™ Blood RNA tube is of a sterile, plastic, evacuated blood collection tube containing stabilization solution (tetradecyl trimethyl-ammonium oxalate and tartaric acid. These components serve to lyse cells, protect RNA molecules from degradation by ribonucleases (RNases) and prevent induction of gene expression.
The kit consists of 5 aqueous buffer solutions for resuspending, binding, washing, and eluting RNA, RNase-free water, proteinase K, an RNase-Free DNase set, spin columns, microcentrifuge tubes, processing tubes, and secondary blood collection tube closures.
## J. Substantial Equivalence Information:
- 1. Predicate device name(s): None
- 2. Predicate 510(k) number(s): None
- 3. Comparison with predicate: Not applicable
# K. Standard/Guidance Document Referenced (if applicable);
Not applicable
## L. Test Principle:
Blood (2.5 mL) is collected into the PAXgene™ Blood RNA tube by venipuncture. It can be either stored or immediately processed (according to specifications in the labeling). To isolate RNA from the sample, the blood is centrifuged to sediment the nucleic acids and the pellet is resuspended in and washed with RNase-free water. The resulting pellet is dissolved in buffer BR1 and buffer BR2, and proteinase K is added for the enzymatic digestion of proteins. Genomic DNA is sheared by running the sample through a shredder spin column, and ethanol is added to adjust the binding conditions. RNA is selectively bound to the membrane in the PAXgene™ Blood RNA spin column by a short centrifugation. The bound RNA is washed, and residual genomic DNA is removed from the membrane column by treatment of the bound nucleic acid with DNase I. RNA is eluted from the column using the elution buffer
{2}------------------------------------------------
provided.
## M. Performance Characteristics (if/when applicable):
- 1. Analytical performance:
- a. Precision/Reproducibility:
## CFOS/18S rRNA and IL1B/18S rRNA Q-RT-PCR Duplex assays.
Objective: The sponsor submitted validation and performance data for two uncleared O-RT-PCR assays for the assessment of performance of the PAXgene Blood RNA System in comparison to a K2EDTA blood collection tube and acid phenol RNA extraction. The assays determine quantitativly the relative level of the c-fos and IL-1ß transcripts compared to 18S rRNA in RNA samples derived from human whole blood. Since CFOS and IL1B offer no diagnostic information, these assays are not intended for diagnostic use. They are ONLY intended for demonstrating that the PAXgene Blood RNA System can be used for RT-PCR.
The validation study uses two types of samples:
#### K2EDTA (TOTAL: 250 ml blood):
- 5 donors with 5 tubes per donor ●
- 10 ml blood per EDTA tube ●
- RNA was isolated via OIAzol and RNeasy columns, pooled and concentrated via MinElute spin column
- Purified, concentrated RNA was analyzed for yield and purity, aliquoted, and stored at -20 °C.
## PAXgene (TOTAL: 960 ml blood):
- 48 donors, 8 tubes per donor (total of 384 PAXgene tubes) ●
- 2.5 ml blood per PAXgene tube
- tubes were incubated at RT for 2 hrs
- RNA was purified, DNase treated, concentrated via MinElute spin ● column and pooled.
- Purified, concentrated RNA was analyzed for yield and purity, aliquoted, and stored at -20 °C.
Experimental design of validation experiments:
The sponsor addressed repeatability and reproducibility and defines these terms within the document as follows:
The repeatability of the assay (within-run precision or intra-assay variability), is the variability of the results from repeated measurements:
- using the same two source samples (n = 10 for each sample) .
- . in the same laboratory (same equipment and same experimenter),
- on the same day, ●
- with the same reagents (identical lots) and ●
{3}------------------------------------------------
- . in the same run.
The repeatability of individual runs is expressed as the weighted mean repeatability used for the calculation of overall precision. The weighted mean repeatability is determined and is included in the overall precision calculation.
The reproducibility of the assay, (robustness, run-to-run precision, or inter-assay variability), is the variability of results from repeat measurements
- using the same two source samples .
- in different laboratories (different lots, different equipment and . different experimenters)
- . on different days
- . and in different runs.
Therefore, reproducibility investigations involve repeats of the complete experiment in different laboratories. To establish the suitability of the precision for day-to-day work, different lots of reagents are investigated as additional parameters that may have a negative impact on precision. The reproducibility between laboratories is determined, but also not specified in detail, because it is included in the overall precision calculation and therefore will be assessed as its part.
| Combi-<br>nation1) | Reagent<br>Combination<br>Run No. (k) | Run2) | RNA<br>sample3) | Replicates<br>per RNA<br>sample | Number of<br>ΔCTvalues per RNA<br>sample | Number of<br>ΔΔCT values per run |
|--------------------|---------------------------------------|-------|-----------------|---------------------------------|------------------------------------------|----------------------------------|
| A | 1 | A1 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| | 2 | A2 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| | 3 | A3 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| B | 4 | B1 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| | 5 | B2 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| | 6 | B3 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| C | 7 | C1 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| | 8 | C2 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| | 9 | C3 | K | 10 | 10 | 10 |
| | | | T | 10 | 10 | 10 |
| Total | | | | | 180 | 90 |
Table 6: Summary of measurement runs for the determination of overall precision
Combination of experimenter, laboratory (equipment), day, TagMan plate
21 Measurement series (run), Established by reagent lots within the combination (A. B. C)
determined by reagent lots 3 K = calibrator RNA, T = test RNA
{4}------------------------------------------------
#### Note: Under 1, technician-to-technician, lab-to-lab, and day-to-day variability has been combined in this study.
Results: The sponsor performed an appropriate validation of their submitted assay by using 3 different component lots, in the hands of 3 different experimenters, in 3 different laboratories (equipment), on 3 different days. The sponsor provided all raw CT data and demonstrated the performance of their assays within the expected limits.
#### Precision/Reproducibility of the PAXgene Blood RNA System.
Objective: Determination of the repeatability, reproducibility and reliability of the PAXgene Blood RNA System.
#### Two experiments were performed: Experiment 1:
- 14 donors (WBC counts within 4.8 to 11.0 x 10° cells/ml blood) ●
- 12 tubes per donor (total 168 PAXgene tubes)
- PAXgene Blood RNA system Lot No. VL1 (ONLY one lot!)
- 3 technicians. Each technician processed 4 tubes per subject (total of 56 ● tubes per technician) in 3 runs (Run #1: donor 1-3 (12 tubes); Run #2: donor 4-9 (24 tubes); Run #3: donor 10-14 (20 tubes)
RNA vield (absorbance at 260 nm) and purity (260nm/280nm absorbance ratio) were determined for each sample.
Repeatibility was determined by evaluating the vield and purity of four samples from one donor processed by one technician.
Reproducibility was determined by evaluating the yield and purity of 12 samples from one donor processed by three technicians. The repeatability and reproducibility was determined separately for each donor because of the differences between individuals.
## Experiment 2:
- 30 donors (WBC counts within 4.8 to 11.0 x 10° cells/ml blood) ●
- 12 tubes per donor (total 360 PAXgene tubes) ●
- Blood from filled PAXgene tubes from 3 donors were pooled and realiquoted into empty tubes, generating 10 donor pools with 36 tubes each.
- PAXgene Blood RNA system Lot No. VL1, VL2, VL3
- 3 technicians. Each technician processed 4 tubes per donor pool per ● day. This was repeated with 2 additional kit lots.
RNA yield (absorbance at 260 nm) and purity (260nm/280nm absorbance ratio) were determined for each sample. For this experiment the RNA purity was also evaluated by electropherograms generated by BioAnalyzer. The isolated total RNA was further tested for degradation with the CFOS and IL1B Q-RT-PCR assay.
{5}------------------------------------------------
Results: the sponsor was able to show that the RNA vield and the RNA purity and quality were within the specification ranges. The min/max % CV repeatability for the quadruplicate preparation per donor pool within each lot and user were 3.4 and 28.8, respectively, with an overall % CV of 11.9. The min/max % CVs reproducibility within each user and between all lots were 8.7 and 20.1, respectively, with an overall % CV of 14.9. The min/max % CV reproducibility within all lots and between all users were 8.7 and 23.1, respectively, with an overall % CV of 16.4. The electropherograms demonstrated that the device repeatedly generates high quality total cellular RNA from whole blood. The Q-RT-PCR assay demonstrated that the transcripts CFOS and IL1B can be repeatedly measured within the assays limits utilizing different device lots, at different days, with different users in different laboratories.
#### RNA Purity, DNA Contamination, RNA Yield.
#### Objective:
Determination of the purity of RNA in samples, the genomic DNA (gDNA) in RNA samples and the nucleic acid yield from human whole blood specimens taken from normal subject population resulting from collection and processing of human whole blood in the PAXgene RNA Blood System.
#### Experimental design:
- . 10 donors
- 2 tubes per donor (total 20 PAXgene tubes) + 1 EDTA tube per . donor for WBC count (10 EDTA tubes)
- storage for 24 hrs at 18-22 ℃, tubes were processed, RNA isolated ●
- . RNA vield and purity were determined via absorbance measurement at 260 and 280 nm
- . Percent gDNA in total nucleic acid preparation was determined using beta-actin PCR
Results: All samples for all parameter fulfilled the acceptance criteria.
## RT-PCR Inhibition.
#### Objective:
Determination of RT-PCR inhibition introduced into RNA isolates by components of the PAXgene Blood RNA Kit
## Experimental Design:
- 22 blank eluates form columns
- template RNA for RT-PCR assay was isolated from confluent layer of HeLa cells
{6}------------------------------------------------
- Test samples were formulated each containing 40 ng of HeLa RNA template plus 0, 10, 20, 30, 40% volume of volume of blank eluate
- Template RNA with eluate was tested in duplicate in a one-step ACTB RT-PCR assay
Results: All samples demonstrated that the kit components do not introduce any inhibition for an RT-PCR assay.
- b. Linearity/assay reportable range:
The linearity and range was determined within 0.2 to 7.8 ng for CFOS and 0.1 to 7.8 ng for IL1B total input nucleic acid per reaction. The total input mass of nucleic acid per reaction can contain up to 25% DNA for CFOS and up to 5% DNA for IL1B without affecting the performance characteristics of the assay.
- Traceability, Stability, Expected values (controls, calibrators, or methods): C. Stability of PAXgene Tubes:
Objective: Determine the shelf life of the PAXgene Blood RNA Tube. Determination of physical attributes of the tubes:
- draw volume
- liquid additive volume
- closure performance .
Chemical attributes of the liquid reagent:
- . pH
- conductivity ●
- density
- . chemical component concentration
Analysis of tube function:
- RNA yield (A260 nm, 95% ≥3 µg/tube) ●
- Purity (ratio of A260 and A280, between 1.8 2.2) .
- Relative levels of CFOS and IL1B (CFOS/18S rRNA and IL1B/18S rRNA . duplex Q-RT-PCR assay, CFOS within 2.34 CT and IL1B within 1.94 CT).
Blood was collected in PAXgene tubes that had been stored at designated test time points (TTP's). RNA stabilizing properties of the tubes were investigated by preparing purified RNA from blood-filled tubes stored at 18-25°C for 0, 1 and 3 days with the PAXgene blood RNA kit (10 donors x 3 times of storage of blood filled tubes x 2 preparations). All PAXgene Blood RNA kits used in these studies were stored prior to use at 2-8°C to minimize kit aging. IMPORTANT: All claims of stability that are based on data from accelerated stability studies will be confirmed in parallel in real time stability studies. Table 1 shows the number of tubes tested in functional tests at each TTP.
{7}------------------------------------------------
| Stability Conditions | TTPs at this<br>temperature | number of tubes for<br>thistemperature study | total |
|--------------------------|-----------------------------------------------|----------------------------------------------|-------|
| 40°C study (accelerated) | 19w, 28w | 2 TTP x 60tubes/TTP | 120 |
| 50°C study (accelerated) | 10w, 15w | 2 TTP x 60 tubes/TTP | 120 |
| 25°C study (real time) | 0, 6m, 9m, 12m,<br>13m, 15m, 16m,<br>18m, 19m | 9 TTP x 60 tubes/TTP | 810 |
Table 1: Functional Test TTPs and number of tubes scheduled for testing
Results: Accelerated stability studies have been completed at the time of this report. Real time stability studies are ongoing, and only results of 6 months storage at 25°C are presented. The sponsor interprets that the data support a shelf live of 19 months storage at 25 °C.
The physical attributes were evaluated for 3 different lots of tubes. The draw volume, liquid additive volume, and closure performance meet the acceptance criteria. For the chemical attributes as well as the functional performance it is not clear whether 1 or 3 lots of tubes were used. For the presented data the pH. conductivity, and density as well as the RNA yield, purity and CFOS and IL1B transcript stability were in the expected ranges for the 6 months real time storage.
## Stability of PAXgene Blood RNA Kit component:
Objective: Determine the shelf life of the PAXgene Blood RNA Kit component. Evaluation of different storage conditions via:
- Real time and accelerated stability study
- Open bottle study
- . Simulated transportation study (simulated extreme temperatures, -20°C-40°C)
Determination of functional stability done with purified HeLa cell RNA as starting material. Two reagent sets were used per tested time point (4 blank eluates (RNase-free water as starting material), and 8 RNA eluates. The following parameters were addressed:
- Determination of recovery of input RNA (HeLa cell RNA) ●
- Determination of variability of recovery of input RNA ●
- . Determination of the degree of inhibition of an RT-PCR assay (via ACTB RT-PCR monoplex assay.
Evaluation of physical and chemical parameters:
- pH
- conductivity ●
- . density
Bioburden Analysis:
● Test of buffers for total bacterial and yeast counts per ml
Results: The RNA recovery, CV of recovery, degree on inhibition, pH, conductivity, and density (for all buffers) were in the expected ranges for the 6 months real time storage. Furthermore, the Proteinase K and the DNase I activity performed to the sponsors claims for the 6 month real time storage.
{8}------------------------------------------------
The bioburden analysis did not show any bacteria, yeast of fungi growth in the same time period. The transportation simulation also revealed acceptable performance of all kit components after extreme temperature simulation.
#### RNA In Situ Stability:
To determine the stability of RNA in samples stored at different temperatures and times, the sponsor performed several RNA In Situ stability experiments that are summarize in Table 2.
Objective: Evaluation of the quantity, quality and integrity of whole blood intracellular RNA after storage in the PAXgene tubes.
| Storage Temperature | 2 – 8 °C | 18, 22, 25 °C | - 20 °C | - 70 °C | Freeze/Thaw |
|---------------------------------------|---------------------------------------------------------------------------------------------------|------------------------------------------------|--------------------------------------------------------------------------------------------------------------------|-------------------------------------------------|------------------------------------------------------------------------------|
| # of donors | 10 | 10 | 10 | 10 | 10 |
| Eligibility | 1.8 to | 1.9 to | 1.10 to | 1.11 to | 1.12 to |
| WBC per ml | 11.0 x 106 cells | 11.0 x 106 cell | 11.0 x 106 cell | 11.0 x 106 cell | 11.0 x 106 cells |
| PAXgene tubes/donor | 12 | 14 | 14 | 10 | 6 |
| Total # of tubes | 120 | 140 | 140 | 100 | 60 |
| Used in experiment | | | | | |
| Storage before start<br>of experiment | 2 hrs RT | 2 hrs RT | 2 hrs RT | 2 hrs RT | 24 hrs RT |
| Time points<br>(# of tubes) | t0 (2 tubes)<br>t1D (2 tubes)<br>t2D (2 tubes)<br>t3D (2 tubes)<br>t4D (2 tubes)<br>t5D (2 tubes) | t0 (2 tubes)<br>t1D (2 tubes)<br>t3D (2 tubes) | t0 (2 tubes)<br>t1m (2 tubes)<br>t2m (2 tubes)<br>t3m (2 tubes)<br>t4m (2 tubes)<br>t5m (2 tubes)<br>t6m (2 tubes) | t0 (2 tubes)<br>t3m (2 tubes)<br>t6m (2 tubes)) | t0 (2 tubes)<br>1st freeze/thaw<br>(2 tubes)<br>2nd freeze/thaw<br>(2 tubes) |
| Yield (> 3 µg/tube) | 260 nm | 260 nm | 260 nm | 260 nm | 260 nm |
| Purity (ratio 1.8-2.2) | 260nm/280nm | 260nm/280nm | 260nm/280nm | 260nm/280nm | 260nm/280nm |
| CFOS/18S rRNA | X | X | X | X | NA |
| Il1b/18S rRNA | X | X | X | X | X |
Table 2: Experimental Design of RNA In Situ Stability at different conditions
The RNA yield, purity, integrity based on the sponsors developed Q-RT-PCR assays showed that all samples at all the time points, temperatures and freeze/thaw cycles were within the acceptance range for the individual parameters (one exception). The sponsor limited the samples to blood donors with White Blood Cell (WBC) counts between 4.8 – 11.0 x 10° cell/ml of blood. The performance is only evaluated for this range of WBC counts, and is specified in the package insert.
d. Detection limit:
Performance evaluation demonstrated that the PAXgene™ Blood RNA system could purify at least 3 µg of RNA with an A260/A280 ratio between 1.8 and 2.2.
{9}------------------------------------------------
- e. Analytical specificity: See above
- Assay cut-off: f. Not applicable.
- 2. Comparison studies:
- a. Method comparison with predicate device: Not applicable.
- b. Matrix comparison: Not applicable.
- 3. Clinical studies:
- a. Clinical Sensitivity: Not applicable.
- b. Clinical specificity: Not applicable.
- c. Other clinical supportive data (when a. and b. are not applicable): Not applicable.
- 4. Clinical cut-off: Not applicable
- 5. Expected values/Reference range: Not applicable
#### N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
## O. Conclusion:
The petition for Evaluation of Automatic Class III Designation for this device is accepted. The device is classified as Class II under regulation 21 CFR 866.4060 with special controls. The special control guidance document "RNA Preanalytical Systems (RNA Collection, Stabilization and Purification Systems for RT-PCR used in Molecular Diagnostic Testing)" will be available shortly.
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.