StatusFirst™ hCG Serum/Urine test is in vitro diagnostic use for a qualitative detection of Human Chorionic Gonadotropin(hCG) in serum or urine for the detection of pregnancy.
Device Story
StatusFirst™ hCG Serum/Urine is an immunochromatographic assay for qualitative hCG detection in serum or urine. The device utilizes the LifeSign DXpress™ Reader, a reflectance photometer, to measure test signals. The reader replaces visual interpretation of the assay, providing an objective result based on light reflectance density. The system is used in clinical settings by healthcare professionals. The reader processes the test strip signal at 5 minutes for both serum and urine samples. By automating the reading process, the device aims to provide consistent results, particularly for borderline samples that might be interpreted differently via visual inspection, thereby assisting clinicians in pregnancy diagnosis.
Clinical Evidence
Bench testing only. Precision study (N=180 per reader) showed no significant differences between readers, days, or lots. Sensitivity study (N=20 per concentration) confirmed 25 mIU/mL cutoff. Specificity testing showed no cross-reactivity with LH, FSH, or TSH, and no interference from common substances. Method comparison with predicate (N=116) showed high agreement; discrepant results at <25 mIU/mL were correctly identified as borderline/negative by the subject device. Physician office laboratory evaluation (N=120) showed 100% agreement with expected results.
Technological Characteristics
Solid-phase, chromatographic immunoassay. Uses LED light source for reflectance photometry. Portable tabletop form factor. Includes barcode scanner for data entry. Calibration performed via 1-line Calibrator and preprogrammed Data Chip. Software-controlled image analysis.
Indications for Use
Indicated for the qualitative detection of human chorionic gonadotropin (hCG) in human serum or urine for the purpose of pregnancy detection. Intended for prescription use.
Regulatory Classification
Identification
A human chorionic gonadotropin (HCG) test system is a device intended for the early detection of pregnancy is intended to measure HCG, a placental hormone, in plasma or urine. A human chorionic goadotropin (HCG) test system is a device intended for any uses other than early detection of pregnancy (such as an aid in the diagnosis, prognosis, and management of treatment of persons with certain tumors or carcinomas) is intended to measure HCG, a placental hormone, in plasma or urine.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
K050955
B. Purpose for Submission:
New device
C. Measurand:
Human Chorionic Gonadotropin (hCG)
D. Type of Test:
Qualitative solid-phase, chromatographic immunoassay
E. Applicant:
PRINCETON BIOMEDITECH CORP.
F. Proprietary and Established Names:
LIFESIGN DXPRESS, MODEL LSR2000
G. Regulatory Information:
1. Regulation section:
21CFR Sec.-862.1155-Human chorionic gonadotropin (HCG) test system.
21CFR Sec.- 862.2300-Colorimeter, photometer, or spectrophotometer for clinical use.
2. Classification:
2, 1 respectively
3. Product code:
JHI - RADIOIMMUNOASSAY, HUMAN CHORIONIC GONADOTROPIN
JJQ - COLORIMETER, PHOTOMETER, SPECTROPHOTOMETER FOR CLINICAL USE
4. Panel:
Chemistry (75)
H. Intended Use:
1. Intended use(s):
See indications for use
2. Indication(s) for use:
- Reflectance photometer for the measurement of concentration of analyte in various assays manufactured by PBM. The concentration is measured by density of light reflectance.
- Reflectance photometer for a reading of test signal instead of visual reading in various qualitative assays manufactured by PBM.
- StatusFirst™ hCG Serum/Urine test is in vitro diagnostic use for a qualitative detection of Human Chorionic Gonadotropin(hCG) in serum or urine for the detection of pregnancy.
3. Special conditions for use statement(s):
prescription use
4. Special instrument requirements:
LIFESIGN DXPRESS
I. Device Description:
{1}
In the test procedure, sample is added to the sample well with the aid of a transfer pipette and sample is allowed to soak in. If hCG is present in the specimen, it will react with the conjugate dye, which binds to the antibody on the membrane to generate a colored line. The DXpress reader interprets the test result automatically by comparing the intensity of the test line to the preset cutoff value.
## J. Substantial Equivalence Information:
1. Predicate device name(s): ACON LABORATORIES, Icon 25 hCG test.
2. Predicate 510(k) number(s): K993065
3. Comparison with predicate: StatusFirst™ hCG Serum/Urine Test vs. Icon 25 hCG test
### Similarities:
1. Both assays measure hCG in urine or serum.
2. Both assays are in-vitro immunological assays using immunochromatographic method.
3. Both assays give the result with the colored signal.
4. Both assays are qualitative test.
5. Both assays detect hCG at 25 mIU/mL in serum or urine.
### Differences:
1. StatusFirst™ hCG Serum/Urine Test read the result by DXpress reader, whereas Icon25 hCG read the result visually.
2. StatusFirst™ hCG Serum/Urine Test reads the result at 5 min for both serum and urine samples, whereas Icon25 hCG read the result at 3 min for urine sample and 5 min for serum sample.
## K. Standard/Guidance Document Referenced (if applicable):
None referenced
## L. Test Principle:
The StatusFirst™ hCG Serum/Urine Test is a rapid serum or urine test for detecting hCG qualitatively. The test employs a solid-phase, chromatographic immunoassay technology to selectively detect elevated levels of hCG in serum or urine with a high degree of sensitivity.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
The precision study of StatusFirst™ hCG Serum/Urine Test was performed by carrying out the test for three days with three different readers. Two lots of devices were tested. Serum or urine samples for the study were prepared by
2
{2}
spiking hCG into pooled negative serum or urine. The prepared hCG concentrations were 0, 5, 25, 40 mIU/mL. The data are summarized below. There were no significant differences between readers, between days or between lots.
Table 2. Precision Study Data: Three days' and two lots' of data were combined for each reader.
Serum
| | hCG (mIU/mL) | Percent Positive (N) | Percent Borderline (N) | Percent Negative (N) |
| --- | --- | --- | --- | --- |
| Reader 1 (0490) | 0 | 0 | 0 | 100 (60) |
| | 5 | 0 | 0 | 100 (60) |
| | 25 | 100 (60) | 0 | 0 |
| | 40 | 100 (60) | 0 | 0 |
| Reader 2 (0598) | 0 | 0 | 0 | 100 (60) |
| | 5 | 0 | 0 | 100 (60) |
| | 25 | 100 (60) | 0 | 0 |
| | 40 | 100 (60) | 0 | 0 |
| Reader 3 (0662) | 0 | 0 | 0 | 100 (60) |
| | 5 | 0 | 0 | 100 (60) |
| | 25 | 100 (60) | 0 | 0 |
| | 40 | 100 (60) | 0 | 0 |
| Total | 0 | 0 | 0 | 100 (180) |
| | 5 | 0 | 0 | 100 (180) |
| | 25 | 100 (180) | 0 | 0 |
| | 40 | 100 (180) | 0 | 0 |
{3}
Urine
| | hCG (mIU/mL) | Percent Positive (N) | Percent Borderline (N) | Percent Negative (N) |
| --- | --- | --- | --- | --- |
| Reader 1 (0490) | 0 | 0 | 0 | 100 (60) |
| | 5 | 0 | 1.7 (1) | 98.3 (59) |
| | 25 | 98.3 (59) | 1.7 (1) | 0 |
| | 40 | 100 (60) | 0 | 0 |
| Reader 2 (0598) | 0 | 0 | 0 | 100 (60) |
| | 5 | 0 | 2.3 (2) | 96.7 (58) |
| | 25 | 100 (60) | 0 | 0 |
| | 40 | 100 (60) | 0 | 0 |
| Reader 3 (0662) | 0 | 0 | 0 | 100 (60) |
| | 5 | 0 | 0 | 100 (60) |
| | 25 | 100 (60) | 0 | 0 |
| | 40 | 100 (60) | 0 | 0 |
| Total | 0 | 0 | 0 | 100 (180) |
| | 5 | 0 | 1.7 (3) | 98.3 (177) |
| | 25 | 99.4 (179) | 0.6 (1) | 0 |
| | 40 | 100 (180) | 0 | 0 |
b. Linearity/assay reportable range:
Qualitative cut-off - positive is above 25
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
hCG calibration (cut-off) is performed using several levels of hCG between 0 to 40 mIU/mL. hCG made from a commercial source calibrated against the 4th WHO International Standard.
Internal Control: Each StatusFirst™ Serum/Urine Test device has a built-in control. The Control line is an internal positive procedural control. A distinct reddish-purple Control line should appear at the C position, indicating an adequate sample volume is used, the sample and reagent are wicking on the
{4}
membrane, and the reagents at the Control line and the conjugate-color indicator are reactive. In addition, the clearing background in the Result window, by providing a distinct readable result, may be considered an internal negative procedural control.
# d. Detection limit:
To evaluate the sensitivity of StatusFirst™ hCG Serum/Urine Test the following experiment was performed.
The hCG (calibrated to the WHO $4^{\text{th}}$ international standard) was spiked to the pooled negative serum or urine and made several levels of concentration. At each concentration the test was repeated 10 times with one lot of devices. Two lots of devices were used for the experiment. Therefore total 20 replicates were tested at each concentration.
The reader is tuned to read hCG levels below the cut-off, to detect hCG levels above $5\mathrm{mIU / mL}$ and less than $25\mathrm{mIU / mL}$ however since the reader does not identify $100\%$ of hCG levels in this range the results are reported out as Borderline and are considered indeterminate. The results are summarized below (Table 1).
The results supported the sensitivity of $25\mathrm{mIU / mL}$ in both urine and serum.
# Table 1. Sensitivity Study
# Serum
| hCG (mIU/mL) | Percent Positive (N) | Percent Borderline (N) | Percent Negative (N) |
| --- | --- | --- | --- |
| 0 | 0 | 0 | 100 (20) |
| 3 | 0 | 0 | 100 (20) |
| 5 | 0 | 0 | 100 (20) |
| 10 | 0 | 60 (12) | 40 (8) |
| 15 | 35 (7) | 55 (11) | 10 (2) |
| 20 | 85 (17) | 15 (3) | 0 |
| 25 | 100 (20) | 0 | 0 |
| 40 | 100 (20) | 0 | 0 |
# Urine
| hCG (mIU/mL) | Percent Positive (N) | Percent Borderline (N) | Percent Negative (N) |
| --- | --- | --- | --- |
| 0 | 0 | 0 | 100 (20) |
| 3 | 0 | 0 | 100 (20) |
| 5 | 0 | 0 | 100 (20) |
{5}
| hCG (mIU/mL) | Percent Positive (N) | Percent Borderline (N) | Percent Negative (N) |
| --- | --- | --- | --- |
| 10 | 0 | 55 (11) | 45 (9) |
| 15 | 30 (6) | 60 (12) | 10 (2) |
| 20 | 80 (16) | 20 (4) | 0 |
| 25 | 100 (20) | 0 | 0 |
| 40 | 100 (20) | 0 | 0 |
e. Analytical specificity:
The cross-reactivity of Leteinizing hormone (LH), Follicle Stimulating Hormone (FSH), and Thyroid Stimulating Hormone (TSH), which are commonly known homologous hormones were tested.
No cross-reactivity was observed when tested at the levels specified below.
| Homologous Hormones | Urine | Serum |
| --- | --- | --- |
| hFSH | 1000 mIU/mL | 1000 mIU/mL |
| hLH | 300 mIU/mL | 300 mIU/mL |
| hTSH | 1000 μIU/mL | 1000 μIU/mL |
Potentially interfering substances were prepared at the following concentrations in both serum and urine containing either 0 or $25\mathrm{mIU / mL}$ hCG. These samples were tested with the StatusFirstTM hCG Serum/Urine Test. No interference was found at these concentrations.
| | in Urine | in Serum |
| --- | --- | --- |
| Acetaminophen | 20 mg/dL | 20 mg/dL |
| Acetylsalicylic Acid | 20 mg/dL | 20 mg/dL |
| Ampicillin | 20 mg/dL | 20 mg/dL |
| Ascorbic Acid | 20 mg/dL | 20 mg/dL |
| Atropine | 20 mg/dL | 20 mg/dL |
| Caffeine | 20 mg/dL | 20 mg/dL |
| Gentisic Acid | 20 mg/dL | 20 mg/dL |
| Phenothiazine | 20 mg/dL | 20 mg/dL |
| Phenylpropanolamine | 20 mg/dL | 20 mg/dL |
| Salicylic Acid | 20 mg/dL | 20 mg/dL |
| Tetracycline | 20 mg/dL | 20 mg/dL |
| Bilirubin | 1mg/dL | 15 mg/dL |
{6}
| Glucose | 2000 mg/dL | 2000 mg/dL |
| --- | --- | --- |
| Hemoglobin | 1 mg/dL | 125 mg/dL |
| Ketones | 100 mg/dL | - |
f. Assay cut-off: See Detection limit above
# 2. Comparison studies:
a. Method comparison with predicate device:
A total of 116 clinical samples (51 serum samples and 65 urine samples) were collected and studied. Since the samples with hCG in near sensitivity level was hard to find some samples were made by diluting clinical samples with high hCG concentration with negative samples. These specimens were tested with StatusFirst™ hCG Serum/Urine Test and predicate device, Icon® 25 hCG by Beckman Coulter, according to the package inserts. The summary of the results is shown below tables (Table 3).
Table 3. StatusFirst ${}^{\mathrm{{TM}}}$ vs. Predicate Device (Icon ${}^{\text{® }}$ 25 hCG)
Serum
| | StatusFirst™ hCG Serum/Urine | | | Total | |
| --- | --- | --- | --- | --- | --- |
| | | Positive | Borderline | | Negative |
| Predicate Device | Positive | 25 | 5 | 1 | 31 |
| | Negative | 0 | 0 | 20 | 20 |
| Total | | 25 | 5 | 21 | 51 |
Urine
| | StatusFirst™ Serum/Urine | | | Total | |
| --- | --- | --- | --- | --- | --- |
| | | Positive | Borderline | | Negative |
| Predicate Device | Positive | 37 | 1 | 0 | 38 |
| | Negative | 0 | 1 | 26 | 27 |
| Total | | 37 | 2 | 26 | 65 |
{7}
In serum sample testing, 6 samples showed discrepant results between the StatusFirst test and the predicate device. All 6 of the discrepant samples contained hCG but the amount of hCG present in these samples was less than 25mIU/mL. The predicate device gave positive results for these 6 discrepant samples. The StatusFirst(TM) Serum/Urine test gave borderline results for 5 of the 6 discrepant samples and a negative result for 1 of the 6 discrepant samples.
In urine sample testing, two samples gave discrepant results between the two devices. These two samples contained hCG, but the amount of hCG present in these samples was less than 25mIU/mL. The StatusFirst gave borderline (indeterminate) results for these two samples, while the predicate device gave 1 positive and 1 negative result for these two samples.
All discrepant samples had less than 25 mIU/mL hCG. StatusFirst Serum/Urine test gave correct results (borderline or negative) for all these samples.
b. Matrix comparison:
See method comparison
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):
Physicians' Office Laboratory Evaluation
The study was performed at three different physician's offices using a total of 120 blind control samples.
Testing Sites
1. Paramount Medical Group
8 Mountain Blvd.
Warren, NJ 07059
2. B. Bang, MD
666 Plainsborough Road Building 100, Suites A & B
Plainsboro, NJ 08536
3. Oberlin Road Pediatrics
Oberlin Road
Raleigh, NC
{8}
9
# Preparation of Samples
The test samples were prepared by spiking hCG into the pooled negative serum or urine. Each panel consisted of five negative (−) samples, five at 5 mIU/mL, five at 25 mIU/mL, and five at 100 mIU/mL hCG. The samples were aliquoted for each test and numbered for the blind test.
# Testing
The test protocol, data recording sheets, test devices, test samples, and a reader were given to the operator of each site. The operator tested each sample by following the test procedure.
# Results
The results obtained at each site agreed 100% with expected results in both serum and urine samples.
The summary of the results are shown below.
# Site Study results
## Serum
| Sample Concentration | Results (Actual/Expected) | | |
| --- | --- | --- | --- |
| | Site 1 | Site2 | Site3 |
| Negative | 5 (−) /5 (−) | 5 (−) /5 (−) | 5 (−) /5 (−) |
| 5 mIU/mL | 5 (−) /5 (−) | 5 (−) /5 (−) | 5 (−) /5 (−) |
| 25 mIU/mL | 5 (+) /5 (+) | 5 (+) /5 (+) | 5 (+) /5 (+) |
| 100 mIU/mL | 5 (+) /5 (+) | 5 (+) /5 (+) | 5 (+) /5 (+) |
## Urine
| Sample Concentration | Results (Actual/Expected) | | |
| --- | --- | --- | --- |
| | Site 1 | Site2 | Site3 |
| Negative | 5 (−) /5 (−) | 5 (−) /5 (−) | 5 (−) /5 (−) |
| 5 mIU/mL | 5 (−) /5 (−) | 5 (−) /5 (−) | 5 (−) /5 (−) |
| 25 mIU/mL | 5 (+) /5 (+) | 5 (+) /5 (+) | 5 (+) /5 (+) |
| 100 mIU/mL | 5 (+) /5 (+) | 5 (+) /5 (+) | 5 (+) /5 (+) |
4. Clinical cut-off: Not Applicable
{9}
5. Expected values/Reference range:
Positive is 25 mIU/mL or greater see detection limit.
HCG levels in normal early pregnant women vary and hCG levels often exceed 100 mIU/mL by the first day of the missed menstrual period (Braunstein, G.D., Rasor, J., Adler, D., Danzer, H., and Wade, M.E. Serum Human Chorionic Gonadotropin Levels Throughout Normal Pregnancy. Am. J. Obstet. Gynecol. 126:678, 1976)
N. Instrument Name:
LifeSign DXpress™ reader
O. System Descriptions:
1. Modes of Operation:
The DXpress™ Reader is a multi-functional portable tabletop camera-based instrument used to read results of in vitro immunodiagnostic assays manufactured according to standards developed by LifeSign, LLC. The DXpress™ Reader uses an LED light source to illuminate an inserted test device. The reader captures and analyzes the reflected image. For quantitative tests, the reader converts the intensity of the test result line into a concentration of analyte using a calibration profile contained in a preprogrammed Data Chip provided with each lot of test devices. For qualitative tests, the reader reports a qualitative positive or negative result.
The barcode scanner enables rapid entry of information, including lot number, expiration date, and operator and patient identification.
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☐ or No ☑
3. Specimen Identification:
Keypad alpha numeric or bar code
4. Specimen Sampling and Handling:
Single sample
10
{10}
5. Calibration:
Calibration QC checks and calibrates the reader optical system using the reference values in a 1-line Calibrator (included) to read test devices accurately. The Calibration QC is required at preset daily intervals determined by the laboratory supervisor. After the power-on and completion of the Self Check, the reader will instruct when to perform a Calibration QC if more than 24 hours have elapsed since the last calibration.
Calibration QC requires a 1-line Calibrator which is included with each DXpress. The barcode contains the quality control parameters for the Calibrator.
After completion of the Calibration QC, the reader will print a hard copy of the result and store it in memory.
6. Quality Control:
External QC follows the same procedure as Run Patient. The only difference is that Run Patient requires a Patient ID, whereas External QC requires a Sample ID.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
Software documentation conforms to documentation in FDA premarket guidance and hazards identified and controlled for are similar to devices of the same type demonstrating the device was developed using good software lifecycle practices.
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.
11
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.