Cryocheck Hex LA is for clinical laboratory use as a qualitative test kit intended to aid in the detection of lupus anticoagulants (LA) in 3.2% citrated human plasma by the application of hexagonal phase phospholipids. Cryocheck Hex LA should be used as an integrated test for lupus anticoagulant detection. For in vitro diagnostic use. The performance of this device has not been established in neonate and pediatric patient populations.
Device Story
CRYOcheck Hex LA is an in vitro diagnostic test kit for clinical laboratory use; detects lupus anticoagulants (LA) in 3.2% citrated human plasma. Device uses hexagonal-phase phospholipid neutralization (HPNT) principle; integrates screening, confirmatory, and mixing procedures. Input: patient plasma samples. Process: plasma incubated with LA Start (pooled normal plasma + heparin neutralizer) and LA Correct (pooled normal plasma + heparin neutralizer + hexagonal phase phospholipid) reagents; APTT reagent and CaCl2 added to trigger intrinsic pathway clotting. Output: clot time difference (delta correction) between reaction mixtures. Performed on Diagnostica Stago STA-R Evolution instrument. Results compared to established cutoff (≥ 6.0 seconds = LA positive). Healthcare providers use output to aid in LA detection; supports clinical diagnosis of antiphospholipid syndrome or related coagulopathies.
Clinical Evidence
No clinical studies performed. Evidence based on analytical performance and method comparison. Method comparison study (n=446 clinical samples) against predicate STACLOT-LA showed 95.6% PPA (91-98% CI), 95.2% NPA (92-97% CI), and 95.3% overall agreement (93-97% CI). Precision studies (single-site and multi-site) evaluated within-run and total imprecision across various LA levels. Interference testing confirmed no clinically significant interference from common endogenous/exogenous substances (e.g., heparin, bilirubin, hemoglobin).
Technological Characteristics
Qualitative HPNT assay. Components: LA Start (pooled normal plasma, buffer, heparin neutralizer), LA Correct (pooled normal plasma, buffer, heparin neutralizer, inverted hexagonal phase phospholipid), LA APTT (silica-based reagent). Form factor: frozen reagents. Energy source: instrument-based (STA-R Evolution). Connectivity: standalone instrument-based processing. Software: embedded instrument firmware. Standards: CLSI EP07, EP05-A3, EP25-A, EP28-A3c.
Indications for Use
Indicated for the qualitative detection of lupus anticoagulants (LA) in 3.2% citrated human plasma. Performance not established in neonate or pediatric populations.
Regulatory Classification
Identification
A partial thromboplastin time test is a device used for primary screening for coagulation abnormalities, for evaluation of the effect of therapy on procoagulant disorders, and as an assay for coagulation factor deficiencies of the intrinsic coagulation pathway.
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K193556
B Applicant
Precision BioLogic
C Proprietary and Established Names
Cryocheck Hex LA
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| GFO | Class II | 21 CFR 864.7925 - Partial Thromboplastin Time Tests | HE - Hematology |
## II Submission/Device Overview:
A Purpose for Submission: New device
B Measurand: Lupus anticoagulant
C Type of Test: Qualitative integrated test based on hexagonal-phase phospholipid neutralization (HPNT)
## III Intended Use/Indications for Use:
A Intended Use(s): See Indications for Use below.
B Indication(s) for Use:
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
CRYOcheck Hex LA is for clinical laboratory use as a qualitative test kit intended to aid in the detection of lupus anticoagulants (LA) in 3.2% citrated human plasma by the application of hexagonal phase phospholipids. CRYOcheck Hex LA should be used as an integrated test for lupus anticoagulant detection. For in vitro diagnostic use. The performance of this device has not been established in neonate and pediatric patient populations.
## C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
## D Special Instrument Requirements:
Diagnostica Stago STA-R Evolution
## IV Device/System Characteristics:
### A Device Description:
CRYOcheck Hex LA is used to perform a qualitative test for the detection of lupus anticoagulants and consists of the following three components:
- LA Start: Pooled normal plasma with buffer and a heparin neutralizer
- LA Correct: Pooled normal plasma with buffer, a heparin neutralizer, and inverted hexagonal phase phospholipid
- LA APTT: Silica-based LA sensitive APTT reagent with stabilizer(s)
### B Principle of Operation:
CRYOcheck Hex LA is a hexagonal-phase phospholipid neutralization test (HPNT), which is an integrated test that combines screening, confirmatory and mixing test procedures into a single assay. The HPNT works on the principle that lupus anticoagulants (LA) are neutralized by hexagonal phase phospholipids (PL). The presence of LA in plasma samples is confirmed by the correction of prolonged APTT clot times in the presence of a reaction mixture containing hexagonal phase phospholipids.
In the CRYOcheck Hex LA assay, the test plasma suspected to contain LA is incubated in two reaction cuvettes, both of which involve dilution with pooled normal plasma. In the first cuvette, the screening test component is performed by mixing the test plasma with the LA Start reagent (pooled normal plasma with a heparin neutralizer). In the second cuvette, the confirmatory test component is performed by mixing the test plasma with the LA Correct reagent (pooled normal plasma with a heparin neutralizer and hexagonal phase phospholipid). The LA APTT reagent is then added to each cuvette, followed by 0.025 M CaCl2 to activate clotting via the intrinsic pathway. Clot times are recorded for the reaction mixture containing LA Start (screen) and the reaction mixture containing LA Correct (confirm). The result is reported as the difference in clot time in seconds ("delta correction") between LA Start and LA Correct cuvettes.
Delta Correction = (CT LA Start) - (CT LA Correct)
K193556 - Page 2 of 9
{2}
The result is then compared to an established cutoff. A result greater than or equal to the established cutoff is considered LA positive, while a result less than the established cutoff is considered LA negative.
# V Substantial Equivalence Information:
A Predicate Device Name(s): STACLOT LA TEST KIT
B Predicate 510(k) Number(s): K923731
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K193556 | K923731 |
| --- | --- | --- |
| Device Trade Name | CRYOcheck Hex LA | STACLOT-LA |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | CRYOcheck Hex LA is for clinical laboratory use as a qualitative test kit intended to aid in the detection of lupus anticoagulants (LA) in 3.2% citrated human plasma by the application of hexagonal phase phospholipids. CRYOcheck Hex LA should be used as an integrated test for lupus anticoagulant detection. For in vitro diagnostic use. The performance of this device has not been established in neonate and pediatric patient populations. | The STACLOT-LA test kit is a reagent system designed for the qualitative detection of lupus anticoagulants (LA) in plasma by the use of hexagonal HII phase phospholipid molecules. |
| Type of Test | Qualitative; hexagonal phase neutralization test | Qualitative; hexagonal phase neutralization test |
| Measurand | clot time delta (seconds) | clot time delta (seconds) |
| Results | Qualitative; results are reported as clot time delta (seconds) and are interpreted as positive or negative relative to an established cut-off value. | Qualitative; results are reported as clot time delta (seconds) and are interpreted as positive or negative relative to an established cut-off value. |
| General Device Characteristic Differences | | |
| Device Description | CRYOcheck Hex LA is comprised of three | Staclot LA is comprised of three |
K193556 - Page 3 of 9
{3}
| Device & Predicate Device(s): | K193556 | K923731 |
| --- | --- | --- |
| Device Trade Name | CRYOcheck Hex LA | STACLOT-LA |
| | of three reagents supplied in a ready to use frozen format as follows:
LA Start: Pooled normal plasma with buffer and a heparin neutralizer.
LA Correct: Pooled normal plasma with buffer, a heparin neutralizer, and inverted hexagonal phase phospholipid.
LA APTT: Silica-based LA sensitive APTT reagent with stabilizer. | lyophilized reagents and two reconstitution liquids as follows:
Reagent 1: ready-for-use buffer
Reagent 2: lyophilized hexagonal phase phosphatidylethanolamine
Reagent 3: lyophilized normal human plasma containing a heparin inhibitor
Reagent 4: lyophilized PTT-LS reagent consisting of cephalin prepared from rabbit cerebral tissues and a particulate siliceous activator
Reagent 5: solvent for reconstitution of Reagent 4. |
| Normal Range and Cutoff | Delta correction: 6 seconds | Delta correction: 8 seconds |
VI Standards/Guidance Documents Referenced:
- CLSI EP07 3rd Edition, Interference Testing in Clinical Chemistry; Approved Guideline, Third Edition, April 2018.
- CLSI EP05-A3, Evaluation of Precision Performance of Quantitative Measurement Procedures; Approved Guideline, Third Edition, October 2014.
- CLSI EP25-A, Evaluation of Stability of In Vitro Diagnostic Reagents; Approved Guideline, September 2009.
- CLSI EP28-A3c, Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory; Approved Guideline, Third Edition, October 2010.
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
a. Single Site Precision
This study was conducted at one internal site over 20 days with two runs per day and two replicates per run, for a total of 80 determinations per sample per lot. The study design included a single STA-R Evolution instrument, three reagent lots, one normal and two abnormal reference controls, as well as five patient plasma samples representing negative, near cut-off, weak positive, moderate positive and strong positive levels of lupus anticoagulant. Precision estimates were calculated for each of the following variance components: within-run, between-run, between-day, between-lot and total
K193556 - Page 4 of 9
{4}
imprecision. The results for within-run and total imprecision for all lots combined are provided in the summary table below.
| Sample | Within Laboratory Precision LA Start | | | Within Laboratory Precision LA Correct | | |
| --- | --- | --- | --- | --- | --- | --- |
| | Mean Clot Time (s) | SD | %CV | Mean Clot Time (s) | SD | %CV |
| CRYOcheck Lupus Negative Control | 53.0 | 1.6 | 3.0 | 52.8 | 2.8 | 5.3 |
| CRYOcheck Weak Lupus Positive Control | 87.3 | 3.2 | 3.7 | 65.4 | 2.8 | 4.2 |
| CRYOcheck Lupus Positive Control | 125.4 | 5.2 | 4.2 | 79.8 | 4.5 | 5.7 |
| LA Negative Plasma Sample | 55.9 | 1.7 | 3.1 | 55.1 | 2.5 | 4.5 |
| LA Near Cut-Off Plasma Sample | 67.6 | 2.5 | 3.8 | 58.4 | 2.6 | 4.5 |
| LA Weak Positive Plasma Sample | 89.8 | 3.3 | 3.7 | 66.4 | 3.0 | 4.6 |
| LA Moderate Positive Plasma Sample | 146.5 | 6.0 | 4.1 | 85.9 | 5.8 | 6.7 |
| LA Strong Positive Plasma Sample | 270.7 | 9.6 | 3.6 | 118.0 | 9.0 | 7.6 |
# b. Multisite Study
This study was conducted at three sites over five days, with two runs per day and three replicates per run for a total of 90 determinations. The study design included a single STA-R Evolution instrument (one instrument per site), three reagent lots, three operators, one normal and two abnormal reference controls, as well as four pooled patient plasmas (single donor LA positive plasma diluted with single donor normal plasma) representing negative, near cut-off, weak positive, and strong positive levels of lupus anticoagulant. Precision estimates were calculated for each of the following variance components: within-run, between-run, between-day, between-site and total imprecision. The results for total imprecision of all lots combined are provided in the summary table below.
| Reproducibility: LA Start | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | Mean Clot Time (s) | Within-Run | | Between-Run | | Between-Day | | Between-Site | | Reproducibility | |
| | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| CRYOcheck Lupus Negative Control | 52.8 | 1.4 | 2.7 | 0.3 | 0.6 | 0 | 0 | 0.4 | 0.7 | 1.6 | 3.0 |
| CRYOcheck Weak Lupus Positive Control | 85.6 | 3.3 | 3.9 | 0.5 | 0.6 | 0.5 | 0.6 | 1.9 | 2.2 | 3.9 | 4.6 |
| CRYOcheck Lupus Positive Control | 123.6 | 5.0 | 4.0 | 0 | 0 | 1.5 | 1.3 | 2.1 | 1.7 | 5.7 | 4.6 |
| LA Negative Plasma Sample | 55.8 | 1.5 | 2.6 | 0.1 | 0.2 | 0.3 | 0.5 | 0.7 | 1.3 | 1.8 | 3.2 |
| LA Near Cut-Off Plasma Sample | 66.9 | 2.3 | 3.5 | 0.4 | 0.6 | 0.8 | 1.2 | 0.8 | 1.2 | 2.7 | 4.0 |
| LA Weak Positive Plasma Sample | 88.3 | 3.7 | 4.1 | 0 | 0 | 1.1 | 1.3 | 1.8 | 2.0 | 4.3 | 4.8 |
| LA Strong Positive Plasma Sample | 264.9 | 6.9 | 2.6 | 0.3 | 0.1 | 2.3 | 0.9 | 4.5 | 1.7 | 10.3 | 3.9 |
K193556 - Page 5 of 9
{5}
| Reproducibility: LA Correct | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | Mean Clot Time (s) | Within-Run | | Between-Run | | Between-Day | | Between-Site | | Reproducibility | |
| | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| CRYOcheck Lupus Negative Control | 53.7 | 1.7 | 3.1 | 0.8 | 1.6 | 0 | 0 | 0 | 0 | 3.1 | 5.8 |
| CRYOcheck Weak Lupus Positive Control | 65.7 | 2.4 | 3.6 | 1.0 | 1.5 | 0.7 | 1.0 | 0.7 | 1.1 | 3.1 | 4.8 |
| CRYOcheck Lupus Positive Control | 80.2 | 3.2 | 4.0 | 1.5 | 1.8 | 1.4 | 1.7 | 1.8 | 2.2 | 4.8 | 5.9 |
| LA Negative Plasma Sample | 56.0 | 1.7 | 3.0 | 0.6 | 1.1 | 0.2 | 0.4 | 0 | 0 | 2.9 | 5.2 |
| LA Near Cut-Off Plasma Sample | 59.2 | 2.2 | 3.7 | 1.2 | 2.0 | 0.7 | 1.1 | 0.3 | 0.6 | 3.0 | 5.0 |
| LA Weak Positive Plasma Sample | 66.9 | 2.7 | 4.0 | 1.3 | 2.0 | 1.2 | 1.8 | 2.2 | 3.3 | 4.0 | 6.0 |
| LA Strong Positive Plasma Sample | 117.4 | 4.5 | 3.9 | 3.1 | 2.6 | 2.0 | 1.7 | 2.6 | 2.2 | 9.4 | 8.0 |
2. Linearity:
Not applicable in Section.
3. Analytical Specificity/Interference:
Interference studies were conducted based on the CLSI EP07 guideline. The study design included a single reagent lot and one STA-R Evolution instrument. Potentially interfering endogenous and exogenous substances were spiked into the control samples (one normal and one abnormal reference control plasma sample). None of the substances in the following table (endogenous or exogenous substances) were found to lead to clinically significant interference.
| Interfering Substance | Concentration Tested |
| --- | --- |
| Hemoglobin | ≤ 500 mg/dL |
| Bilirubin (unconjugated) | ≤ 20 mg/dL |
| Bilirubin (conjugated) | ≤ 2 mg/dL |
| Intralipid | ≤ 500 mg/dL |
| Unfractionated heparin | ≤ 2 IU/mL |
| Low molecular weight heparin | ≤ 2 IU/mL |
| Elevated factor VIII activity | ≤ 180% |
| Factor VIII inhibitor antibodies | ≤ 15 BU/mL |
| Abnormally low factor II | ≥ 50% |
| elevated INR | ≤ 4.5 |
K193556 - Page 6 of 9
{6}
| Interfering Substance | Concentration Tested |
| --- | --- |
| C-reactive protein | ≤ 15 μg/mL |
| platelet counts | <10,000/ μL |
4. Assay Reportable Range:
Not Applied in Section.
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
a. Shelf-Life Stability:
Shelf-life stability studies were performed to support the recommended storage and handling instructions found in the device labeling. Three control samples were tested by using three lots of CRYOcheck Hex LA after storage in the following temperature ranges up to 37 months, -70°C (-66 to -72°C) and -80°C (-76 to -82°C). The study was performed using a single STA-R Evolution instrument with ten replicate measurements at each time point for each sample. The study data demonstrate that a shelf-life stability claim of 12 months when stored at -70°C or colder.
b. In-Use Stability:
In-use stability studies were performed to support the recommended storage and handling instructions found in the device labeling. Three control plasmas and four test plasmas with varying levels of LA (Negative, Near Cut-off, Weak Positive and Strong Positive) were tested by using three lots of CRYOcheck Hex LA after storage in the following conditions, room temperature (18–25°C) or on-board the instrument. The study was performed using three reagent lots on a STA-R Evolution instrument with five replicate measurements at each time point for each sample. The in-use stability claim was established at 4 hours when reagents are maintained at room temperature or 8 hours when stored on-board the instrument.
c. Sample Stability
Sample stability studies were performed to support the recommended storage and handling instructions found in the device labeling. Sixty-four citrated plasma samples were tested after storage in the following temperature ranges, room temperature (15–25°C) and below -70°C. The study was performed using one reagent lot of CRYOcheck Hex LA on STA-R Evolution instrument with four replicate measurements at each time point for each sample. The study data demonstrate that citrated plasma samples are stable for four hours when stored at room temperature (15–25°C), two months when stored at < -70°C, including one freeze thaw cycle.
d. Expected Values – Controls
CRYOcheck Lupus Negative Control (CCLN): a HEPES-buffered pooled normal citrated human plasma, which is negative for Lupus Anticoagulant.
K193556 - Page 7 of 9
{7}
CRYOcheck Weak Lupus Positive Control (CCWLP, K032804): a HEPES-buffered pooled normal citrated human plasma, mixed with LA positive plasma to give a weakly positive LA test result which is reported on its assay certificate.
CRYOcheck Lupus Positive Control (CCLP, K952623): a HEPES buffered pooled normal citrated human plasma, to give a moderate-strong LA test result which is reported on its assay certificate.
6. Detection Limit:
Not applicable
7. Normal Range and Assay Cut-Off:
The reference interval study was conducted at one laboratory site. The LA level of plasma samples collected from 137 normal, ostensibly healthy individuals (≥ 18 years) were tested by two operators using three lots of CRYOcheck Hex LA on a STA-R Evolution instrument. The reference interval for delta correction was established by calculating the pooled mean ±2 SD. The calculated normal reference range for delta correction results of CRYOcheck Hex LA is shown in the table below:
| Normal Range | |
| --- | --- |
| Lower Range | Upper Range |
| -5.9 | 2.0 |
The cut-off results were determined by using pooled data from the normal range study. The cut-off is calculated as the mean of the delta correction + 4 SD.
| Delta Correction | Interpretation |
| --- | --- |
| < 6.0 seconds | LA Negative |
| ≥ 6.0 seconds | LA Positive |
This method of establishing cut-off is different than that indicated for confirmatory tests. Each laboratory should verify its own cut-off, for example, by testing the plasma of at least 20 normal individuals.
B Comparison Studies:
1. Method Comparison with Predicate Device:
The method comparison study was conducted using the CRYOcheck Hex LA on the STA-R Evolution by testing n=446 clinical samples (citrated plasma) collected from the intended use population. Results from the CRYOcheck Hex LA were compared to results from the STACLOT LA assay on a STA-R Evolution. The following tables summarize the 95% confidence intervals for PPA, NPA, and overall agreement were calculated using the Clopper-Pearson (exact) method.
K193556 - Page 8 of 9
{8}
| | CRYOcheck Hex LA | | | |
| --- | --- | --- | --- | --- |
| | | Negative | Positive | Total |
| STACLOT-LA | Negative | 295 | 15 | 310 |
| | Positive | 6 | 130 | 136 |
| | Total | 301 | 145 | 446 |
| Agreement | Point Estimate (95% Confidence Interval) |
| --- | --- |
| Positive Percent Agreement | 95.6% (91% - 98%) |
| Negative Percent Agreement | 95.2% (92% - 97%) |
| Overall Agreement | 95.3% (93% - 97%) |
2. Matrix Comparison: Not applicable
C Clinical Studies:
1. Clinical Sensitivity: Not applicable
2. Clinical Specificity: Not applicable
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable): Not applicable
D Clinical Cut-Off: Not applicable
E Expected Values/Reference Range: Not applicable
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K193556 - 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.