K172514 · Sandstone Diagnostics, Inc. · POV · Nov 17, 2017 · Hematology
Device Facts
Record ID
K172514
Device Name
Trak Plus Male Fertility Testing System
Applicant
Sandstone Diagnostics, Inc.
Product Code
POV · Hematology
Decision Date
Nov 17, 2017
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 864.5220
Device Class
Class 2
Indications for Use
The Trak® Male Fertility Testing System is intended for semi-quantitative assessment of sperm concentration at 15 million sperm per milliliter (M/mL) or below, between 15 and 55 M/mL, and above 55 M/mL. It also provides a qualitative assessment of semen volume. Sperm concentration and semen volume are only two factors that could impact a man's fertility status and time to pregnancy. For complete assessment of male reproductive health, the user should consult a physician. For in vitro, over the counter home use.
Device Story
System includes Trak Engine (instrument), disposable Props, Volume Cups, and droppers. User collects semen in Volume Cup; cup markings allow qualitative volume assessment (threshold 1.5 mL). Semen sample introduced into Prop; Engine spins Prop to isolate sperm via density gradient separation. Sperm cells compact into visible column (pellet) in Prop; column height corresponds to sperm concentration (below 15 M/mL, 15-55 M/mL, above 55 M/mL). Contaminants remain suspended above density medium. User visually interprets column height and volume level. Device provides home-based fertility screening; results intended to supplement physician consultation for reproductive health assessment.
Clinical Evidence
Two clinical studies (n=232 and n=127) evaluated lay-user interpretation of semen volume against reference methods. Stage 1: Sensitivity 97.0% (91.6-99.0%), Specificity 95.4% (90.4-97.9%). Stage 2: Sensitivity 95.2% (86.9-98.4%), Specificity 96.9% (89.3-99.1%). Overall accuracy >96%. Bench testing confirmed volume cup precision, liquefaction effectiveness, and concentration category equivalence to previous cup design.
Technological Characteristics
System uses density gradient centrifugation for sperm isolation. Volume cups are coated with digestive enzymes to reduce viscosity. Measurement is visual (fluid height for volume, pellet height for concentration). Battery-operated Engine provides centrifugal force. No software, connectivity, or electronic data transmission.
Indications for Use
Indicated for adult males seeking semi-quantitative assessment of sperm concentration and qualitative assessment of semen volume for fertility monitoring. For OTC home use.
Regulatory Classification
Identification
An automated differential cell counter is a device used to identify one or more of the formed elements of the blood. The device may also have the capability to flag, count, or classify immature or abnormal hematopoietic cells of the blood, bone marrow, or other body fluids. These devices may combine an electronic particle counting method, optical method, or a flow cytometric method utilizing monoclonal CD (cluster designation) markers. The device includes accessory CD markers.
Special Controls
*Classification.* Class II (special controls). The special control for this device is the FDA document entitled “Class II Special Controls Guidance Document: Premarket Notifications for Automated Differential Cell Counters for Immature or Abnormal Blood Cells; Final Guidance for Industry and FDA.”
{0}
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K172514
B. Purpose for Submission:
Modified collection cup
C. Measurand:
Sperm concentration and semen volume
D. Type of Test:
Centrifuged packed cell height via density gradient separation for estimation of sperm concentration and visual readout of fluid height for semen volume
E. Applicant:
Sandstone Diagnostics, Inc.
F. Proprietary and Established Names:
Trak® Male Fertility Testing System
G. Regulatory Information:
1. Regulation section:
21 CFR § 864.5220, Automated differential cell counter
2. Classification:
Class II
3. Product code:
POV – Semen Analysis Device
4. Panel:
Hematology (81)
{1}
H. Intended Use:
1. Intended use(s):
The Trak Male Fertility Testing System is intended for semi-quantitative assessment of sperm concentration at 15 million sperm per milliliter (M/mL) or below, between 15 and 55 M/mL, and above 55 M/mL. It also provides a qualitative assessment of semen volume.
Sperm concentration and semen volume are only two factors that could impact a man's fertility status and time to pregnancy. For complete assessment of male reproductive health, the user should consult a physician. For in vitro, over the counter home use.
2. Indication(s) for use:
Same as Intended Use
3. Special conditions for use statement(s):
For over-the-counter (OTC) use
4. Special instrument requirements:
The Trak Male Fertility Testing System (Trak) includes a small instrument, the Engine. It spins a test Prop to compact sperm cells within an introduced semen sample into a visible column.
I. Device Description:
The Trak Male Fertility Testing System (Trak) includes: (1) small instrument (the Engine), (2) AA batteries for the engine, (4) disposable units in which liquefied semen is introduced and where the sperm concentration is interpreted (the Prop), (4) volume cups with lids, (8) sample droppers, (1) bottle of control solution A, and (8) "seal before spin" stickers.
The volume cup is a single-use disposable collection cup with an integrated volume measurement feature. The volume cup contains a small measurement column with markings incorporated into the outer surface, two channels to collect and drain the semen sample into the measurement region, and a sloped surface that funnels captured semen into the column and channels. Once the semen is liquefied the volume cup is used to qualitatively assess the semen volume: low semen volume (≤ 1.5 mL) or normal semen volume (>1.5 mL).
J. Substantial Equivalence Information:
1. Predicate device name(s):
Trak® Male Fertility Testing System
{2}
2. Predicate 510(k) number(s):
K153683
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended Use | The Trak® Male Fertility Testing System is intended for semi-quantitative assessment of sperm concentration at 15 million sperm per milliliter (M/mL) or below, between 15 and 55 M/mL, and above 55 M/mL. It also provides a qualitative assessment of semen volume.Sperm concentration and semen volume are only two factors that could impact a man's fertility status and time to pregnancy. For complete assessment of male reproductive health, the user should consult a physician. For in vitro, over the counter home use. | The Trak® Male Fertility Testing System is intended for semi-quantitative assessment of sperm concentration at 15 million sperm per milliliter (M/mL) or below, between 15 and 55 M/mL, and above 55 M/mL.Sperm concentration is only one factor that could impact a man's fertility status and time to pregnancy. For complete assessment of male reproductive health, the user should consult a physician. For in vitro, over the counter home use |
| Sample Type | Human Semen | Same |
| Threshold Values | 15 M/mL (lower reference limit)15–55 M/mL>55 M/mL | Same |
| Test Control Method | External quality control | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Measurand | Semen volume and sperm concentration | Sperm concentration |
| Test Type | Semi-quantitative & Qualitative | Semi-quantitative |
| Test Reporting | Visual readout of fluid height in volume cup and visual readout of cell column height in Prop | Visual readout of cell column height in Prop |
| Test Principle | Centrifuged packed cell volume in Prop and graduated chamber fluid in volume cup | Centrifuged packed cell volume in Prop |
WHO laboratory manual for the Examination and processing of human semen, fifth edition, 2010
{3}
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Volume Cut-off | 1.5 mL (lower reference limit)^{1} | None |
## K. Standard/Guidance Document Referenced (if applicable):
World Health Organization. (2010). WHO laboratory manual for the examination and processing of human semen, 5th Ed. Geneva: WHO Press
CLSI EP12-A2: User Protocol for Evaluation of Qualitative Test Performance; Approved Guideline - Second Edition
## L. Test Principle:
The Trak volume cups are used to collect, liquefy, and assess the volume of the semen sample. The volume cups are coated with a digestive enzyme to liquefy the semen sample and reduce viscosity. Markings on the volume cup allow for the qualitative interpretation of volume at, below, or above the 1.5 mL threshold.
To estimate the sperm concentration the Trak uses the principle of density gradient separation to isolate sperm cells from human semen. The Trak Engine spins a test Prop to compact sperm cells within an introduced semen sample into a visible column (or "pellet"). The Prop gives a defined shape to the column, the height of which corresponds to the concentration of sperm cells in the sample. Since semen may also contain cell debris, immature sperm cells, and other contaminant particulates that could contribute to the apparent size of a pellet, it is necessary to filter out the contaminants. Trak filters by removing contaminants from view based on density across a predefined liquid density medium.
During operation, approximately 0.17 mL of semen is metered by centrifugal action from the sample inlet into the metering chamber of the Prop. During rotation, the semen floats on "top" of the pre-loaded density medium. Sperm cells pass through the medium due to their high density while contaminants remain floating on the medium. When the spin sequence is complete, the sperm cells form a visible column that is displayed to the user for interpretation. Contaminants that are less dense than the liquid density medium are suspended "above" the medium, substantially separated from the sperm cells and are generally too diffuse to visualize.
## M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
A five-day precision study was carried out by three operators using three lots of volume cups on five artificial semen samples with different volumes. The semen
{4}
volumes selected consisted of volumes around the 1.5 mL threshold which included: 1.2 mL, 1.3 mL, 1.5 mL, 1.7 mL, and 1.8 mL. For each volume tested, each operator tested a distinct lot of volume cups over five days with five replicates per day for a total of 75 replicates per semen volume. The following table includes averages for each condition, sum for each category, and percent correct calls with respect to the reference method.
| Sample # | Reference Volume (mL) | Number of Results ≤ 1.5 mL | Number of Results > 1.5 mL | % Correct | Quant Volume result grand average ± SD (mL) |
| --- | --- | --- | --- | --- | --- |
| 1 | 1.2 mL | 75 | 0 | 100 | 1.32 ± 0.12 |
| 2 | 1.3 mL | 74 | 1 | 98.7 | 1.43 ± 0.09 |
| 3 | 1.5 mL | 17 | 58 | n/a* | 1.61 ± 0.10 |
| 4 | 1.7 mL | 1 | 74 | 98.7 | 1.86 ± 0.16 |
| 5 | 1.8 mL | 0 | 75 | 100 | 1.93 ± 0.10 |
* no performance goal at the threshold; data tabulated for information only
SD and %CV for between-day, between-operator/lot, and total precision for each concentration are tabulated below. Results were within the predefined acceptance criteria.
| Sample Number | N | Mean | Repeatability | | Between Day | | Between Operator/lot | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| 1 | 75 | 1.32 | 0.08 | 6.1% | 0.07 | 5.0% | 0.00 | 0.0% | 0.12 | 9.2% |
| 2 | 75 | 1.43 | 0.06 | 4.0% | 0.02 | 1.6% | 0.02 | 1.3% | 0.09 | 6.5% |
| 3 | 75 | 1.61 | 0.09 | 5.5% | 0.00 | 0.0% | 0.00 | 0.0% | 0.10 | 6.2% |
| 4 | 75 | 1.86 | 0.09 | 5.0% | 0.03 | 1.4% | 0.00 | 0.3% | 0.10 | 5.2% |
| 5 | 75 | 1.93 | 0.10 | 5.1% | 0.02 | 1.2% | 0.01 | 0.6% | 0.10 | 5.3% |
b. Linearity/assay reportable range:
Not applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Shelf Life
A shelf-life stability study was conducted using two lots of volume cups with a total of 8 time points (1 day, 1 month, 3 months, 6 months, 9 months, 12 months, 15 months and 18 months) to assess the enzymatic activity of protein used to coat the volume cup. The enzyme activity was tested by using solidified gelatin. The data provided support that the enzyme activity is acceptable up to 15 months. Stability testing is still ongoing; therefore, the shelf-life stability of the volume cup is 12 months.
{5}
Track Prop Shelf Life:
Refer to K153683
Quality Control Shelf Life:
Refer to K153683
d. Detection limit:
Not applicable
e. Analytical specificity:
Not applicable
f. Assay cut-off:
Refer to K153683
2. Comparison studies:
a. Method comparison with reference method:
See Consumer Use Study (3.c)
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):
Consumer Use Study:
Two studies were performed to demonstrate that the 1.5 mL reference marking on the new volume cup are interpreted correctly by lay users. Study 1 was to demonstrate
{6}
the accuracy of semen volume in the new volume cup as interpreted by the intended users using semen sample photographs and study 2 was to assess interpretation and ease of use of the physical volume cup filled with known volumes of artificial semen as interpreted by the intended users.
Study 1: Semen samples were collected by consenting donors, weighed and converted to volume as recommended in the WHO semen analysis manual, 5th edition, then photographed. The photographs were used to challenge both technicians and lay users. Demographics of the lay users include (n=52, male (57.7%) and female (42.3%), age range 18.0–68.0, 44.2% Caucasian, 25% Asian, 13.5% Latino/Hispanic, 3.8% Black or African American and 15.3% other and varying levels of education, 40.4% some college, 23.1% 4-year degree (bachelor's), 23.1% high school, 7.7% post graduate). A total of 232 semen sample photographs were interpreted as ≤ 1.5 mL or > 1.5 mL by lay users as well as trained technicians (blinded to the results), and were confirmed with the result obtained by the reference method.
Lay User Interpretation Compared to the Reference Method:
| Sensitivity, % (95% CI) | Specificity, % (95% CI) | Overall Percent Agreement (95% CI) |
| --- | --- | --- |
| 97.0% (91.6 – 99.0%) | 95.4% (90.4 – 97.9%) | 96.1% (92.8 – 97.9%) |
Trained Technician Interpretation Compared to the Reference Method:
| Sensitivity, % (95% CI) | Specificity, % (95% CI) | Overall Percent Agreement (95% CI) |
| --- | --- | --- |
| 96.2% (90.5 – 98.5%) | 96.9% (92.2 – 98.8%) | 96.6% (93.3-98.2%) |
Results of Lay Users Compared to Trained Technicians:
| Overall Percent Agreement (95% CI) | Percent Positive Agreement (95% CI) | Negative Percent Agreement (95% CI) |
| --- | --- | --- |
| 97.8% (95.1 – 99.1%) | 96.2% (90.5 – 98.5%) | 99.2% (95.7 – 99.9%) |
Study 2: Lay users (n=32, age range 25–59) with different ethnicities and varying levels of education were to assess interpretation and ease of use of the physical volume cup filled with known volumes of artificial semen. A total of 127 artificial semen samples were interpreted as ≤ 1.5 mL, > 1.5 mL, or Invalid. Each lay user interpreted 4 cups filled with 1 mL, 1.2 mL, 1.8 mL, or 2 mL of artificial semen in random order. Results for sensitivity 95.2% and specificity 96.9% suggest that in the hands of lay users, the volume cup with appropriate instructions provides
{7}
adequate resolution of semen volume using ≤1.5 mL or >1.5 mL of the WHO threshold for hypospermia.
## Lay User Questionnaire Results:
After completing the volume cup reader study, lay users (n=32) also completed a Tester Questionnaire with 11 multiple choice questions. Five of the questions were designed to capture the user's perceptions of ease of use of the Trak device, and the remaining six questions were to gauge interpretation and understandability of the instructions. While slightly more than a quarter of the respondents assigned "somewhat difficult" or "difficult" to the task of finding the liquid level, more than 95% of the responses for interpreting cups were assigned correctly with respect to the reference method. Additionally, 90.6% of users gave answers indicating an understanding of the instructions according to the intended interpretation.
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Not applicable
N. Instrument Name:
Trak® Male Fertility Testing System
O. System Descriptions:
1. Modes of Operation:
Not applicable
Does the applicant's device contain the ability to transmit data to a computer, webserver, or mobile device?
Yes _______ or No ___X___
Does the applicant's device transmit data to a computer, webserver, or mobile device using wireless transmission?
Yes _______ or No ___X___
2. Software/Firmware & Cybersecurity:
FDA has reviewed applicant's Hazard Analysis and software development processes for this line of product types:
{8}
Yes ☐ X ☐ or No ☐
Software Consult Needed? Yes ☐ or No ☐ X ☐
Cybersecurity Review Needed? Yes ☐ or No ☐ X ☐
Cybersecurity Consult Needed? Yes ☐ or No ☐ X ☐
3. Specimen Identification:
No specimen identification is available.
4. Specimen Sampling and Handling:
Refer to K153683
5. Calibration:
Not applicable
6. Quality Control:
Refer to K153683
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
Semen Liquefaction
The purpose of this study was to determine the effectiveness of new volume cup in promoting semen liquefaction. A total of 20 semen sample aliquots from three semen samples were tested for liquefaction by measuring the volume of semen dispensed by the transfer devices included with the Trak System (250 μL exact volume pipettes) after incubation according to the instructions for use. The total average for these volume measures was 253.05 μL, with a 95% CI of 249.60–256.00 μL, meeting the acceptance criteria for liquefaction from the volume cups.
Trak Sperm Concentration
The objective of this study was to determine whether samples incubated in the new volume cup give equivalent Trak category results to samples incubated in the collection cup included with the predicate device. Two sperm concentrations 10 M/mL and 20 M/mL of the WHO threshold cutoff (15 M/mL) were tested in 20 replicates for each cup type on Trak Props, and results were categorized as ≤15 M/mL (Low), 15–55 M/mL (Moderate), and >55 M/mL (Optimal). Sperm concentrations were confirmed by CASA, and then aliquots of the pooled semen samples were incubated in the new volume cups
{9}
and in the previous collection cups.
| Nominal Condition | Average CASA result (M/mL) | # Trak Results ≤ 15 M/mL | # Trak Results 15 ~ 55 M/mL | # Trak Results > 55 M/mL |
| --- | --- | --- | --- | --- |
| Concentration #1, control | 11.4 | 20 | 0 | 0 |
| Concentration #1, volume cup | 11.7 | 20 | 0 | 0 |
| Concentration #2, control | 20.7 | 0 | 20 | 0 |
| Concentration #2, volume cup | 19.7 | 0 | 20 | 0 |
Trak results for both the new volume cup and the collection cup with the predicate device were correctly categorized with respect to the reference method. Results from this study met the defined acceptance criteria.
## Semen Homogenization
The objective of this study was to determine whether sperm concentration is evenly distributed within the new volume cup compared to the previous collection cup with the predicate device when agitated. Semen samples were pooled and diluted to two sperm concentrations differing by more than 50%. Sperm concentrations were evaluated by CASA using multiple aliquots of the pooled semen samples after incubation in the new volume cups and in the previous collection cups. Twenty (20) aliquots were taken from the top and bottom of each cup for each pool, and its sperm concentration was accessed.
| Sample ID | Cup Type | Location | n | Mean ± SD (M/mL) | Cup type Mean ± SD (M/mL) |
| --- | --- | --- | --- | --- | --- |
| A | Collection Cup (Predicate) | Top | 20 | 17.1 ± 0.7 | 17.1 ± 0.7 |
| | | Bottom | 20 | 17.2 ± 0.7 | |
| | Volume Cup (Candidate) | Top | 19 | 17.5 ± 0.7 | 17.5 ± 0.8 |
| | | Bottom | 20 | 17.5 ± 0.9 | |
| B | Collection Cup (Predicate) | Top | 20 | 36.4 ± 2.2 | 35.3 ± 2.5 |
| | | Bottom | 20 | 34.3 ± 2.5 | |
| | Volume Cup (Candidate) | Top | 20 | 36.7 ± 2.6 | 36.9 ± 2.2 |
| | | Bottom | 20 | 37.1 ± 1.8 | |
No significant differences between variances between the two cup types were found. These data support that the new volume cup provides equivalent semen homogenization to the previous collection cup.
## Cleaning Robustness
Refer to K153683
{10}
Q. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
R. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.