ABX PENTRA BILIRUBIN, DIRECT CP, ABX PENTRA BILIRUBIN, TOTAL CP, ABX PENTRA MULTICAL, ABX PENTRA N CONTROL, ABX PENTRA P
Applicant
Horiba Abx
Product Code
CIG · Clinical Chemistry
Decision Date
Aug 16, 2006
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1110
Device Class
Class 2
Indications for Use
ABX PENTRA Bilirubin, Direct CP reagent with associated calibrators and controls are for quantitative in vitro diagnostic determination of direct bilirubin in human serum and plasma based on a photometric test using 2,4-dichloroaniline (DCA) for use on ABX PENTRA 400 Clinical Chemistry Analyzer. ABX PENTRA Bilirubin, Total CP reagent with associated calibrators and controls are for quantitative in vitro diagnostic determination of total bilirubin in human serum and plasma based on a photometric test using 2,4-dichloroaniline (DCA) and detergents for use on ABX PENTRA 400 Clinical Chemistry Analyzer. Measurements of the levels of bilirubin (direct or total), an organic compound formed during the normal and abnormal destruction of red blood cells, are used in the diagnosis and treatment of liver, hemolytic hematological, and metabolic disorders, including hepatitis and gall bladder block. The ABX PENTRA Multical is a calibrator for use in the calibration of quantitative Horiba ABX methods on Horiba ABX clinical chemistry analyzers. The ABX PENTRA N Control is for use in quality control by monitoring accuracy and precision. The ABX PENTRA P Control is for use in quality control by monitoring accuracy and precision.
Device Story
System comprises reagents, calibrators, and controls for use on ABX PENTRA 400 clinical chemistry analyzer; benchtop photometric system. Reagents utilize diazo colorimetry (2,4-dichloroaniline) for quantitative bilirubin measurement. Samples (serum/plasma) processed via automated photometric analysis; analyzer measures absorbance changes to determine analyte concentration. Used in clinical laboratory settings by trained personnel. Output provides quantitative bilirubin levels; assists clinicians in diagnosing/monitoring liver, hemolytic, and metabolic conditions. System includes quality control materials (N Control, P Control) and calibrator (Multical) to ensure measurement accuracy and precision.
Clinical Evidence
Bench testing only. Performance validated via precision (within-run and total), linearity, detection limits, and analytical specificity (interference studies). Method comparison studies performed against predicate devices (n=110 for Direct, n=106 for Total) showed high correlation (r^2 > 0.99). Matrix equivalence confirmed between serum and Heparin-Lithium plasma.
Technological Characteristics
Photometric colorimetric assay using 2,4-dichloroaniline (DCA). Reagents provided in bi-reagent cassettes. Calibrators and controls are serum-based. Testing performed on ABX PENTRA 400 analyzer. Standards referenced: CLSI EP5-A2 (precision), EP6-A (linearity), EP9-A2 (method comparison), EP21-A (total analytical error).
Indications for Use
Indicated for quantitative in vitro diagnostic determination of direct and total bilirubin in human serum and plasma to aid in the diagnosis and treatment of liver, hemolytic hematological, and metabolic disorders (e.g., hepatitis, gall bladder block).
Regulatory Classification
Identification
A bilirubin (total or direct) test system is a device intended to measure the levels of bilirubin (total or direct) in plasma or serum. Measurements of the levels of bilirubin, an organic compound formed during the normal and abnormal distruction of red blood cells, if used in the diagnosis and treatment of liver, hemolytic hematological, and metabolic disorders, including hepatitis and gall bladder block.
Predicate Devices
Roche Reagent for Direct Bilirubin (k910593)
Roche Reagent for Total Bilirubin (k910591)
ABX PENTRA N & P Control (k052007)
ABX PENTRA N Multical (k052007)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k060325
B. Purpose for Submission:
Notification of intent to manufacture and market the devices: a group of reagents and their associated controls and calibrators for use on the ABX PENTRA 400 - ABX PENTRA Bilirubin, Direct CP, ABX PENTRA Bilirubin, Total CP, ABX PENTRA N Control, ABX PENTRA P Control, and ABX PENTRA Multical.
C. Measurand:
Direct and Total Bilirubin
D. Type of Test:
Quantitative, colorimetric
E. Applicant:
Horiba ABX
F. Proprietary and Established Names:
Trade/Proprietary Name: ABX PENTRA Bilirubin Direct CP
Common or Usual Name: Bilirubin, Direct
Trade/Proprietary Name: ABX PENTRA Bilirubin Total CP
Common or Usual Name: Bilirubin, Total
Trade/Proprietary Name: ABX PENTRA N Control
Common or Usual Name: Quality Control
Trade/Proprietary Name: ABX PENTRA P Control
Common or Usual Name: Quality Control
Trade/Proprietary Name: ABX PENTRA N Multical
Common or Usual Name: Calibrator
G. Regulatory Information:
1. Regulation section:
21 CFR 862.1110: Bilirubin (Total or Direct) test system
21 CFR 862.1660: Quality control material (assayed and unassayed)
21 CFR 862.1150: Calibrator
{1}
2. Classification:
Class II - ABX PENTRA Bilirubin Direct CP, ABX PENTRA Bilirubin Total CP, ABX PENTRA N Multical
Class I - ABX PENTRA N Control, ABX PENTRA P Control
3. Product code:
ABX PENTRA Bilirubin Direct CP - CIG
ABX PENTRA Bilirubin Total CP - CIG
ABX PENTRA N Control - JJY
ABX PENTRA P Control - JJY
ABX PENTRA N Multical - JIX
4. Panel:
Chemistry
H. Intended Use:
1. Intended use(s):
See indications for use below.
2. Indication(s) for use:
ABX PENTRA Bilirubin, Direct CP reagent with associated calibrators and controls are for quantitative in vitro diagnostic determination of Direct Bilirubin in human serum and plasma based on a photometric test using 2,4-dichloroaniline (DCA) for use on ABX PENTRA 400 Clinical Chemistry Analyzer.
ABX PENTRA Bilirubin, Total CP reagent with associated calibrators and controls are for quantitative in vitro diagnostic determination of Total Bilirubin in human serum and plasma based on a photometric test using 2,4-dichloroaniline (DCA) and detergents for use on ABX PENTRA 400 Clinical Chemistry Analyzer.
Measurements of the levels of Bilirubin (Direct or Total), an organic compound formed during the normal and abnormal destruction of red blood cells, are used in the diagnosis and treatment of liver, hemolytic hematological, and metabolic disorders, including hepatitis and gall bladder block.
The ABX PENTRA Multical is a calibrator for use in the calibration of quantitative Horiba ABX methods on Horiba ABX clinical chemistry analyzers
The ABX PENTRA N Control is for use in quality control by monitoring accuracy and precision.
The ABX PENTRA P Control is for use in quality control by monitoring accuracy and precision.
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
{2}
For use on the Horiba ABX PENTRA 400
# I. Device Description:
The ABX PENTRA Bilirubin Direct CP consists of a cassette containing two liquid reagents (1 – 24ml & 2 – 7ml). The ABX PENTRA Bilirubin Total CP consists of a cassette containing two liquid reagents (1 – 44ml & 2 – 14ml)
The ABX PENTRA N Multical is a 3 level serum based calibrator for use in the calibration of quantitative Horiba ABX PENTRA Bilirubin Total and Direct CP methods on Horiba ABX clinical chemistry analyzers as specified on the vials.
The ABX PENTRA N & P Controls are serum based liquids for use in quality control by monitoring accuracy and precision for the quantitative ABX PENTRA Bilirubin Total and Direct CP methods as specified in the enclosed package insert.
The ABX PENTRA N Multical and ABX PENTRA N & P Controls are prepared from a human blood-based matrix.
All human source materials were shown to be free from HBsAG and antibodies to HCV and HIV by FDA approved methods.
# J. Substantial Equivalence Information:
1. Predicate device name(s):
Roche Reagent for Direct Bilirubin, Roche Reagent for Total Bilirubin
ABX PENTRA N & P Control (Total and Direct Bilirubin ranges added)
ABX PENTRA N Multical (Total and Direct Bilirubin ranges added)
2. Predicate 510(k) number(s): k910593, k910591
k910593 – Direct Bilirubin
k910591 – Total Bilirubin
k052007 ABX PENTRA Control and Calibrator
3. Comparison with predicate:
| | Predicate device (k910593): | Device : Direct Bilirubin |
| --- | --- | --- |
| Device Name | Direct Bilirubin | ABX PENTRA Bilirubin Direct CP |
| Instrument | COBAS Mira | HORIBA ABX |
| Analytes | Direct Bilirubin | Direct Bilirubin |
{3}
| | Predicate device (k910593): | Device : Direct Bilirubin |
| --- | --- | --- |
| Method | Photometric using diazotized sulfanilic acid | Photometric using 2,4-dichloroaniline |
| Specimen | Serum | Serum, Plasma |
| Format | Liquid | Liquid |
| Packaging | Single reagent bottles | Bi-reagent cassette |
| Controls | Commercially available | Recommended ABX PENTRA N and P controls |
| Calibrators | Factor method: uses the factor generated during Total Bilirubin calibration | Uses recommended calibration material ABX PENTRA Multical |
| | Predicate device (k910591): | Device : Total Bilirubin |
| --- | --- | --- |
| Device Name | Total Bilirubin | ABX PENTRA Bilirubin, Total CP |
| Manufactured by | Roche, USA | HORIBA ABX, France |
| Instrument | COBAS MIRA chemistry system | ABX PENTRA 400 |
| Analytes | Total bilirubin | Total bilirubin |
| Method : | Photometric test using diazotized sulfanilic acid, and dimethylsulfoxide (DMSO) and ethylene glycol as solvents | Photometric test using 2,4-dichloroaniline (DCA), and a specific mixture of detergents |
| Specimen : | Serum | Serum Plasma |
| Format | Liquid | Liquid |
| Packaging | Single-reagent bottles | Bi-reagent cassette |
| Calibrators | Commercially available calibration material (not included) | Recommended calibration material (not included): ABX Pentra Multical |
K. Standard/Guidance Document Referenced (if applicable):
{4}
The following standards & FDA guidance documents have been used to support this submission
Guidance for Industry and FDA Staff: “Format for Traditional & Abbreviated 510(k)s”: August 12, 2005
“In vitro diagnostic devices: Guidance for the preparation of 510(k) submissions Jan 1997”
“Guidance for Industry and FDA Staff Bundling Multiple Devices or Multiple Indications in a Single Submission, November 2003”
CLSI (NCCLS):
i) EP5-A2 – Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline-Second Edition
ii) EP6-A - Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach; Approved Guideline
iii) EP9-A2 – Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline -Second Edition
iv) EP21-A - Estimation of Total Analytical Error for Clinical Laboratory Methods; Approved Guideline
L. Test Principle:
Di-azoamine Dye, Colorimetric assay, the presence of bilirubin (total or direct) in plasma or serum combined with 2, 4-dichloroaniline (DCA) results in the formation of a Diazoamine dye which is proportional to bilirubin concentration.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
ABX PENTRA Bilirubin Direct CP
Within Run Precision:
Method: Based upon the Valtec guideline (Vassault et al., Ann. Biol. Clin., 1986,
5
{5}
(44), 686-745); 2 controls (as above) and 3 specimens of low, medium and high concentrations were tested 20 times in a single run for each sample. (note: Human High Sample was done with dilution)
| Material | Mean (mg/dL) | SD (mg/dL) | CV% |
| --- | --- | --- | --- |
| Control N | 0.90 | 0.01 | 0.67 |
| Control P | 1.85 | 0.01 | 0.44 |
| Human Low | 0.23 | 0.01 | 3.23 |
| Human Medium | 1.52 | 0.01 | 0.59 |
| Human High | 7.88 | 0.21 | 2.69 |
Between run and Total Precision
Method: Based upon CLSI/NCCLS EP-5A, two specimens of low & high levels and 2 controls were tested in duplicate for 20 days, two series per day. $(n = 80)$
| Material | Mean (mg/dL) | SD (mg/dL) | CV% |
| --- | --- | --- | --- |
| N Control | 0.94 | 0.04 | 4.26 |
| P Control | 2.02 | 0.09 | 4.22 |
| Sample 1 | 0.69 | 0.02 | 3.27 |
| Sample 2 | 3.83 | 0.11 | 2.98 |
# ABX Pentra Bilirubin, Total CP
# Within Run Precision
Based upon the Valtec guideline (Vassault et al., Ann. Biol. Clin., 1986, (44), 686-745); 2 controls (as above) and 3 specimens of low, medium and high concentrations were tested 20 times in a single run for each sample.
| Material | Mean (mg/dL) | SD (mg/dL) | CV% |
| --- | --- | --- | --- |
| Control N | 0.97 | 0.02 | 1.77 |
| Control P | 5.35 | 0.04 | 0.66 |
| Human Low | 0.91 | 0.02 | 2.51 |
| Human Medium | 3.25 | 0.03 | 0.90 |
| Human High | 8.73 | 0.05 | 0.60 |
{6}
Between run and Total Precision
Based upon NCCLS (CLSI) EP-5A, two specimens of low & high levels and 2 controls were tested in duplicate for 20 days, two series per day. $\mathrm{N} = {80}$
| Material | Mean (mg/dL) | SD (mg/dL) | CV% |
| --- | --- | --- | --- |
| Control N | 1.04 | 0.03 | 3.35 |
| Control P | 4.30 | 0.09 | 1.98 |
| Human Low | 3.03 | 0.06 | 1.88 |
| Human High | 8.51 | 0.13 | 1.55 |
b. Linearity/assay reportable range:
# ABX PENTRA Bilirubin Direct CP
Linearity studies across the measuring range were performed via protocols based upon CLSI EP6-A. The studies demonstrated linearity of the assays and the linear statistics listed below. In addition, post dilution studies were performed to validate the automated dilution function and range.
# ABX PENTRA Bilirubin Direct CP
The measuring range of the assay is 0.69 to $6.79\mathrm{mg / dl}$ . Post dilution up to 33.0 mg/dL.
Linear regression statistics: $y = 0.9279x + 1.8604r^2 = 0.9976$
# ABX Pentra Bilirubin, Total CP
The measuring range of the assay is 0.20 to $26.30\mathrm{mg / dl}$ . Post dilution up to 181.5 mg/dL.
Linear regression statistics: $y = 0.9037x + 0.9705r^2 = 0.9988$
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
# Sample stability
The sponsor states the following related to sample stability:
Exposure to sunlight may result in a decrease in total bilirubin by up to $30\%$ after 1 hour.
At normal room temperature and protected from light exposure stable for 3 days.
{7}
Reference:
Thomas L. Clinical Laboratory Diagnostics. 1st ed. Frankfurt: TH-Books Verlagsgesellschaft; 1998. p. 192-202.
## ABX PENTRA Bilirubin Direct CP
Reagent Shelf-life: Real time stability of the reagent stored at 2-8°C has been evaluated on 3 different lots. Results support a real time stability of 18 months.
Reagent Stability on board: Reagent stability on-board has been evaluated testing accuracy and linearity periodically. The results support reagent stability on-board (refrigerated) after opening of 25 days.
## ABX PENTRA Bilirubin, Total CP
Reagent Shelf-life: Real time stability of the reagent stored at 2-8°C has been evaluated on 3 different lots. Results support a real time stability of 18 months.
Reagent Stability on board: Reagent stability on-board has been evaluated testing accuracy and linearity periodically. The results support reagent stability on-board (refrigerated) after opening of 25 days.
## ABX PENTRA N Control & ABX PENTRA P Control traceability
The values of the ABX PENTRA Controls are assigned from the ABX PENTRA calibrator, reagents and analyzers. The target value is determined by the median of results from 150 measurements/parameter. Confidence range is determined as the calculated range in percent which is based on the experimental results from the previous target value trials. The range declared in the target value sheet is equal to the assigned value +/- 3 standard deviations (3 SD).
## ABX Pentra Multical traceability
ABX Pentra Multical is prepared from reference materials. Commercial calibrators are standardized by means of a master lot which is stored at -80°C. Two controls are used to ensure that the calibration values of the master lot, as well as the entire measurement system (calibrator, reagent, and analyzer), remain stable during the storage period. The target value is determined by the median of results from 150 measurements/parameter.
## ABX PENTRA N Control, ABX PENTRA P Control, and ABX PENTRA Multical
Protocols and acceptance criteria for open and closed stability of the controls and
8
{8}
calibrators were described and found to be acceptable.
d. Detection limit:
## ABX PENTRA Bilirubin Direct CP
Minimum Detection Limit (MDL) was calculated from 30 measurements of saline water (0.9 g/l) using the Valtec guideline (Vassault et al., Ann. Biol. Clin., 1986, (44), 686-745). The claimed MDL value is 0.69 mg/dl.
## ABX Pentra Bilirubin, Total CP
Minimum Detection Limit (MDL) was calculated from 30 measurements of saline water (0.9 g/l) using the Valtec guideline (Vassault et al., Ann. Biol. Clin., 1986, (44), 686-745). The claimed MDL value is 0.20 mg/dl.
e. Analytical specificity:
## ABX PENTRA Bilirubin Direct CP
**Study materials:** Hemoglobin and triglycerides (as Intralipid®, representative of lipemia) were added to pooled Human serum at two different direct bilirubin concentrations (normal and high). The base serum with each substance was then serially diluted with unspiked base serum to adjust direct bilirubin concentration.
**Method:** Based upon the Valtec guideline (Vassault et al., Ann. Biol. Clin., 1986, (44), 686-745); specimens of low, medium and high concentrations were tested 20 times in a single run for each sample.
Due to hemoglobin interference, hemolyzed samples should not be used.
## ABX Pentra Bilirubin, Total CP
**Study materials:** Hemoglobin up to 220 µmol/L (380 mg/dL) and triglycerides (as Intralipid®, representative of lipemia) up to 7 mmol/L (612.5 mg/dL) were added to pooled Human serum at two different direct bilirubin concentrations (normal and high). The base serum with each substance was then serially diluted with unspiked base serum to adjust direct bilirubin concentration
**Method:** **Method:** Based upon the Valtec guideline (Vassault et al., Ann. Biol. Clin., 1986, (44), 686-745); specimens of low, medium and high concentrations were tested 20 times in a single run for each sample.
Hemoglobin up to 220 µmol/L (380 mg/dL) and triglycerides (as Intralipid®, representative of lipemia) up to 7 mmol/L (612.5 mg/dL) do not interfere with total bilirubin determination by this test.
f. Assay cut-off:
Not applicable
{9}
10
2. Comparison studies:
a. Method comparison with predicate device:
ABX PENTRA Bilirubin Direct CP
A total of 110 samples were compared with the Roche Direct Bilirubin reagent (predicate) on the Roche MIRA Plus.
$$
\mathrm{Y} = 1.0571\mathrm{x} - 1.0551, \mathrm{r}^{2} = 0.9974
$$
ABX Pentra Bilirubin, Total CP
A total of 106 samples were compared with the Roche Total Bilirubin reagent (predicate) on the Roche MIRA Plus.
$$
\mathrm{Y} = 1.0303\mathrm{x} - 2.7861, \mathrm{r}^{2} = 0.9961
$$
b. Matrix comparison:
ABX PENTRA Bilirubin Direct CP
To demonstrate equivalence of direct bilirubin results in serum and Plasma Heparin-Lithium samples, comparison study was performed. 39 matched samples were evaluated on ABX Pentra 400 analyzer using ABX Pentra Bilirubin, Direct CP reagent. $\mathrm{Y} = 0.9981\mathrm{x} + 0.0837\mathrm{r}^{2} = 0.9693$. The results show that there is no significant difference between serum specimens and Heparin-Lithium Plasma.
ABX Pentra Bilirubin, Total CP
To demonstrate equivalence of total bilirubin results in serum and Plasma Heparin-Lithium samples, comparison study was performed. 39 samples were evaluated on Pentra 400 analyzer using ABX Pentra Bilirubin, Total CP reagent. $\mathrm{Y} = 0.9917\mathrm{x} + 0.0577\mathrm{r}^{2} = 0.9779$. The results show that there is no significant difference between serum specimens and Heparin-Lithium Plasma.
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:
{10}
Not applicable
5. Expected values/Reference range:
ABX PENTRA Bilirubin Direct CP
Adults and children: 0 - 0.2 mg/dL (0 - 3.4 µmol/L).
Reference:
Thomas L. ed. Clinical Laboratory Diagnostics. 1st ed. Frankfurt: TH-Books Verlagsgesellschaft, 1998. p 192-202.
ABX Pentra Bilirubin, Total CP
Adults: 0.1 – 1.2 mg/dL (1.7 – 21 µmol/L)
Reference:
Thomas L. ed. Clinical Laboratory Diagnostics. 1st ed. Frankfurt: TH-Books Verlagsgesellschaft, 1998. p 192-202.
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
11
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.