K182593 · Apex BioTechnology Corp. · JIN · Dec 18, 2018 · Clinical Chemistry
Device Facts
Record ID
K182593
Device Name
KET-1 Blood Ketone Monitoring System
Applicant
Apex BioTechnology Corp.
Product Code
JIN · Clinical Chemistry
Decision Date
Dec 18, 2018
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1435
Device Class
Class 1
Attributes
Pediatric
Indications for Use
The KET-1 Blood Ketone Monitoring system is intended to quantitatively measure β-hydroxybutyrate (β-ketone) in fresh capillary whole blood from fingertips. It should only be used by a single patient and it should not be shared. Testing is done outside the body (In Vitro diagnostic use). It is intended for self-testing by people with diabetes mellitus at home as an aid to monitoring the effectiveness of diabetes control programs. It is not to be used for diagnosis or screening of diabetes, or for neonatal use.
Device Story
KET-1 Blood Ketone Monitoring System measures β-hydroxybutyrate in fresh capillary whole blood; utilizes amperometric detection via test strips; enzyme β-hydroxybutyrate dehydrogenase converts β-hydroxybutyrate to acetoacetate; magnitude of electrical current proportional to ketone concentration; results displayed in mmol/L. Intended for home self-testing by patients with diabetes; single-patient use only. Provides quantitative data to assist patients in monitoring diabetes control programs. System includes KET-1 meter, test strips, and control solutions. Requires 0.8 μL blood sample; analysis time 8 seconds. Not for diagnosis or screening of diabetes.
Clinical Evidence
Lay-user accuracy study conducted with 100 participants comparing self-tested fingertip capillary blood results to laboratory reference (Beckman DxC 800). For concentrations < 1.5 mmol/L, 98% (92/94) were within ± 0.15 mmol/L and 100% within ± 0.30 mmol/L. For concentrations ≥ 1.5 mmol/L, 100% (6/6) were within ± 20%. Linear regression showed R² = 0.9837. Bench testing confirmed precision, linearity (0.1-8.0 mmol/L), interference resistance, and robustness across hematocrit (20-60%), altitude (up to 10,335 ft), and environmental conditions.
Technological Characteristics
Amperometric biosensor; enzyme-based (β-hydroxybutyrate dehydrogenase); 0.8 μL sample volume; 8-second analysis time; 2x CR2032 3V battery power; operating range 10-40°C, 20-90% RH; hematocrit range 20-60%. Single-patient use design; validated for 1825 cleaning/disinfection cycles with Clorox Healthcare Bleach Germicidal Wipes.
Indications for Use
Indicated for self-testing of β-hydroxybutyrate (β-ketone) in fresh capillary whole blood from fingertips by people with diabetes to monitor diabetes control programs. Not for diagnosis or screening of diabetes; not for neonatal use.
Regulatory Classification
Identification
A ketones (nonquantitative) test system is a device intended to identify ketones in urine and other body fluids. Identification of ketones is used in the diagnosis and treatment of acidosis (a condition characterized by abnormally high acidity of body fluids) or ketosis (a condition characterized by increased production of ketone bodies such as acetone) and for monitoring patients on ketogenic diets and patients with diabetes.
Predicate Devices
Nova Max Plus Blood Glucose and β-ketone Monitor System (k091547)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k182593
B. Purpose for Submission:
New Device
C. Measurand:
$\beta$-Ketone, as beta-hydroxybutyrate, in fingertip capillary whole blood
D. Type of Test:
Quantitative amperometry, $\beta$-Ketone (beta-hydroxybutyrate)
E. Applicant:
Apex Biotechnology Corp.
F. Proprietary and Established Names:
KET-1 Blood Ketone Monitoring System
G. Regulatory Information:
1. Regulation section:
21 CFR §862.1435, Ketones (nonquantitative) test system
2. Classification:
Class I, meets the limitation of exemptions 21 CFR §862.9(c)(5)
3. Product code:
JIN, Nitroprusside, Ketones (urinary, non-quantitative)
4. Panel:
Chemistry (75)
{1}
H. Intended Use:
1. Intended use(s):
See indication(s) for use below.
2. Indication(s) for use:
The KET-1 Blood Ketone Monitoring system is intended to quantitatively measure β-hydroxybutyrate (β-ketone) in fresh capillary whole blood from fingertips. It should only be used by a single patient and it should not be shared. Testing is done outside the body (In Vitro diagnostic use). It is intended for self-testing by people with diabetes mellitus at home as an aid to monitoring the effectiveness of diabetes control programs. It is not to be used for diagnosis or screening of diabetes, or for neonatal use.
The KET-1 Blood Ketone Monitoring System is comprised of the KET-1 Blood Ketone Meter and KET-1 Blood Ketone Test Strip.
3. Special conditions for use statement(s):
- The system should not be used to test neonates
- Do not test samples other than fresh capillary blood obtained from fingertip.
- Do not use the system at altitudes above 10,335 feet (3,150 meters).
- Do not use when Hematocrit is outside the acceptable hematocrit range for testing of 20% to 60%.
- Severe dehydration (excessive water loss) may cause inaccurate results. If you believe you are suffering from severe dehydration, consult your healthcare professional immediately.
- For in vitro diagnosis use only.
- Critically ill patients should not be tested with this device.
- Inaccurate results may occur in severely hypotensive individuals or patients in shock or in a hyperglycemic-hyperosmolar state.
- Incorrect result may occur in individuals who are dehydrated.
- The meter and lancing device are for single patient use. Do not share these items with anyone, including other family members! Do not use on multiple patients!
- Do not reuse; each test strip is for single use only.
- Do not use when humidity is higher than 90% and lower than 10%, as extremes in humidity may affect results.
- For single patient use only.
- For over-the counter use.
- The system is not intended for use in the diagnosis of or screening for diabetes mellitus.
4. Special instrument requirements:
KET-1 Blood Ketone Meter
{2}
I. Device Description:
The KET-1 Blood Ketone Monitoring System consists of the KET-1 Blood Ketone Meter, KET-1 Blood Ketone Test Strips, and KET-1 Control, solutions (level 1 and Level 2). The system is for self-testing of blood ketone. The KET-1 Blood Ketone Test Strips and KET-1 Ketone Control Solutions are purchased separately.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Nova Max Plus Blood Glucose and β-Ketone Monitoring System
2. Predicate 510(k) number(s):
k091547
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Candidate Device
KET-1 Blood Ketone Monitoring System
k182593 | Predicate Device Nova Max Plus Blood Glucose and β-Ketone Monitoring System k091547 |
| Intended use | Quantitatively measure β-hydroxybutyrate (β-Ketone) in fresh capillary whole blood from fingertips as an aid to monitoring the effectiveness of diabetes control programs | Same |
| Measuring Range | 0.1 to 8 mmol/L | Same |
| Assay method | β-hydroxybutyrate dehydrogenase | Same |
| Differences | | |
| --- | --- | --- |
| Item | Candidate Device
KET-1 Blood Ketone Monitoring System
k182593 | Predicate Device Nova Max Plus Blood Glucose and β-Ketone Monitoring System k091547 |
| Hematocrit Range | 20%-60% | 25%-60% |
| Analysis Time | 8 seconds | 10 seconds |
| Power source | 2 X CR2032, 3-volt coin cell battery | 1 X CL2450, 3-volt coin cell battery |
{3}
4
K. Standard/Guidance Document Referenced (if applicable):
CLSI EP05-A2, Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline.
CLSI EP6-A, Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach; Approved Guideline.
CLSI EP07-A2, Interference Testing in Clinical Chemistry; Approved Guideline.
L. Test Principle:
The test principle of KET-1 Blood Ketone Monitoring System is based on the amperometry detection of beta-hydroxybutyrate in whole blood. β-hydroxybutyrate is converted by the enzyme β-hydroxybutyrate dehydrogenase to acetoacetate. The magnitude of electrical current resulting from this enzymatic reaction is proportional to the amount of β-hydroxybutyrate present in the sample. The result is displayed on the meter in mmol/L.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Repeatability
Repeatability was assessed using two ketone concentration ranges (1.2 – 0.6 mmol/L and 1.4 – 2.2 mmol/L) and five lithium heparinized whole blood samples and five lithium heparinized whole blood samples spiked with β-hydroxybutyrate to create concentrations of (0.55, 2.17, 3.76, 6.26, and 7.58 mmol/L) and tested on ten KET-1 meters. Ten replicates were tested per meter per concentration with each of the three lots of the test strips. The results are summarized below:
| Concentrations (mmol/L) | N | Men (mmol/L) | SD (mmol/L) | % CV |
| --- | --- | --- | --- | --- |
| 0.55 | 300 | 0.5 | 0.06 | 11.8 |
| 2.27 | 300 | 2.2 | 0.09 | 4.2 |
| 3.76 | 300 | 4.1 | 0.17 | 4.2 |
| 6.26 | 300 | 6.3 | 0.24 | 3.7 |
| 7.58 | 300 | 7.2 | 0.25 | 3.4 |
| Level 1 control 0.2-0.6 mmol/L | 300 | 0.5 | 0.05 | 11.1 |
| Level 2 control 1.4-2.2 mmol/L | 300 | 1.8 | 0.06 | 3.2 |
Intermediate Precision study:
Intermediate precision was evaluated using three lots of KET-1 blood Ketone Strip
{4}
with 10 meters. Two levels of control solutions were used with $\beta$ -ketone ranges of $0.2 - 0.6 \, \mathrm{mmol/L}$ (Level 1) and $1.4 - 2.2 \, \mathrm{mmol/L}$ (Level 2). For each control, ten replicates were taken each day for ten days, so that 100 individual measurements were generated per control level. The results from all strip lots are summarized below:
| Control Level | N | Mean (mmol/L) | SD (mmol/L) | % CV |
| --- | --- | --- | --- | --- |
| 1 | 300 | 0.5 | 0.05 | 11.1 |
| 2 | 300 | 1.8 | 0.06 | 3.2 |
# b. Linearity/assay reportable range:
The Linearity of the KET-1 Blood Ketone Monitoring System was evaluated using Lithium Heparin venous whole blood spiked with $\beta$ -hydroxybutyrate. Seven whole blood samples were adjusted to the following $\beta$ -hydroxybutyrate concentrations: 0.04, 0.51, 2.23, 4.12, 6.03, 7.11, and $8.52 \mathrm{mmol} / \mathrm{L}$ . The concentrations were assigned using the Beckman Coulter UniCel DxC800 Clinical System with STANBIO $\beta$ -Hydroxybutyrate LiquiColor Test Kit. The summary of the of the linear regression analysis for each lot was as follow:
| Test Strip Lot | Slope | y-intercept | R value |
| --- | --- | --- | --- |
| Lot 1 | 0.9911 | 0.0158 | 0.9985 |
| Lot 2 | 0.9829 | 0.0338 | 0.9983 |
| Lot 3 | 0.9887 | 0.0265 | 0.9984 |
The results of the study support the sponsor's claimed (β-ketone) measuring range of 0.1-0.8 mmol/L.
Validation testing was performed demonstrating that the meter displays 'HI' when the measurement result is greater than $8.0\mathrm{mmol / L}$ and "LOW" when the measurement result is less than $0.1\mathrm{mmol / L}$ , as intended.
# c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The KET-1 Blood Ketone Monitoring system is traceable to an in-house standard prepared from commercially available control materials.
# Test strip stability:
The KET-1 Blood Ketone Test Strip are provided in individual foil packages. The shelf life stability of the foil packaged strips was assessed with real-time testing. The study protocol and acceptance criteria were reviewed and found acceptable to support the sponsor's claimed stability of 18 months when stored under recommended storage conditions of $39^{\circ}\mathrm{F} - 86^{\circ}\mathrm{F}$ $(4 - 30^{\circ}\mathrm{C})$ and relative humidity of $10 - 85\%$ .
{5}
d. Detection limit:
Please refer to Linearity study above, Section M.1.b.
e. Analytical specificity:
To evaluate interference of exogenous and endogenous interfering substances, three lithium heparinized whole blood samples with ketone concentrations of $0.8\mathrm{mmol / L}$ , $3.3\mathrm{mmol / L}$ and $5.8\mathrm{mmol / L}$ were divided into two aliquots: control (with no added interferent) and test (with assessed interferent). Each sample was tested using 10 KET-1 meters and the difference between meter results obtained with the test sample compared to the control samples calculated. The sponsor defined no significant interference as bias within $0.3\mathrm{mmol / L}$ for $\beta$ -ketone $< 1.5\mathrm{mmol / L}$ and $\leq 20\%$ for $\beta$ -ketone $\geq 1.5\mathrm{mmol / L}$ . The following table lists the highest tested concentration of each substance at which no significant interference was detected.
| Substance | Highest concentration at which no significant interference is observed (mg/dL) |
| --- | --- |
| Acetaminophen | 20 |
| Acetone | 10 |
| Acetoacetate | 10 |
| Ascorbic acid | 4 |
| Bilirubin | 10 |
| Captopril | 10 |
| Cholesterol | 500 |
| Creatinine | 6 |
| Dopamine | 2 |
| Glucose | 900 |
| Ibuprofen | 50 |
| L-DOPA | 3 |
| Methyl-Dopa | 7.5 |
| N-acetylcysteine | 10 |
| Tetracycline | 10 |
| Tolazamide | 15 |
| Triglyceride | 750 |
| Uric acid | 20 |
| EDTA | 180 |
| Heparin | 18IU/mL |
| Salicylate | 60 |
| Tolbutamide | 100 |
f. Assay cut-off:
Not Applicable.
{6}
7
2. Comparison studies:
a. Method comparison with predicate device:
Not applicable. See section M.3.c below for accuracy in the hands of the intended user.
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):
Lay-user accuracy study:
To assess the performance of the KET-1 Blood meter monitoring system in the hands of the intended users, a lay user study was conducted with 100 lay user participants using one KET-1 Blood meter monitoring system and three lots of. KET-1 test strips. Each lay user participants self-tested their own fingertip capillary blood using the KET-1 Blood meter ketone monitoring system unassisted and were instructed to use instructions provided in the labeling.
The lay user $\beta$-Ketone measurements were compared to those obtained by results obtained trained users with the who used Beckman DxC 800 with the STANBIO $\beta$-Hydroxybutyrate LiquiColor Test Kit. The range of $\beta$-Ketone concentrations across all subjects was 0.11 to $2.40 \mathrm{mmol/L}$. Each sample was measured in singlicate. The results are summarized below:
Results for samples with $\beta$-ketone concentration $< 1.5 \mathrm{mmol/L}$
| Within ± 0.15 mmol/L | Within ± 0.225 mmol/L | Within ± 0.30 mmol/L |
| --- | --- | --- |
| 92/94 (98%) | 94/94 (100%) | 94/94 (100%) |
Results for samples with $\beta$-ketone concentration $\geq 1.5 \mathrm{mmol/L}$
| Within ± 10% | Within ± 15% | Within ± 20% |
| --- | --- | --- |
| 6/6 (100%) | 6/6 (100%) | 6/6 (100%) |
{7}
Linear regression analysis of the results:
| Sample | Slope | Intercept | R2 | N | Ketone Concentration (mmol/L) |
| --- | --- | --- | --- | --- | --- |
| Fingertip blood | 0.9857 | 0.0038 | 0.9837 | 100 | 0.11-2.40 |
Readability Evaluation: The readability of the over-the counter, home use labeling was evaluated using a Flesch-Kincaid analysis and demonstrated that the grade level scores were less than 8th grade.
4. Clinical cut-off:
Not Applicable.
5. Expected values/Reference range:
Based on published literature, the sponsor included the following in the labeling:
The normal adult blood $\beta$-Ketone range for a person without diabetes is less than 0.6 mmol/L.
A. Rewers, Current Controversies in Treatment and Prevention of Diabetic Ketoacidosis, Advances in Pediatrics 57 (2010) 247–267.
N. Instrument Name:
KET-1 Blood Ketone Monitoring System
O. System Descriptions:
1. Modes of Operation:
Does the applicant’s device contain the ability to transmit data to a computer, webserver, or mobile device?
Yes ☐ or No ☑
Does the applicant’s device transmit data to a computer, webserver, or mobile device using wireless transmission?
Yes ☐ or No ☑
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
{8}
Yes ☐ X ☐ or No ☐
3. Specimen Identification:
There is no sample identification function with this device. Samples are applied directly to the test strip as they are collected.
4. Specimen Sampling and Handling:
The KET-1 Blood Ketone Monitoring System is intended to be used with capillary whole blood from the fingertip which is applied directly to the test strip.
5. Calibration:
There is no calibration required for KET-1 Blood Ketone Monitoring System by the user.
6. Quality Control:
Two levels of KET-1 Ketone Control Solutions are available and are purchased separately.
P. Other Supportive Instrument Performance Characteristics Data Not Covered in the "Performance Characteristics" Section above:
1. Hematocrit Study:
The effects of varying hematocrit levels on the measurement of $\beta$-ketone concentration was evaluated using venous whole blood samples with hematocrit levels at $20\%$, $25\%$, $30\%$, $40\%$, $45\%$, $50\%$ and $60\%$. Four different with $\beta$-ketone concentrations of 0.4-0.6 mmol/L, 1.5-2.5 mmol/L, 3.5-5.4 mmol/L, and 5.0-6.5 mmol/L were prepared at each of the four levels with seven hematocrit levels. The $\beta$-ketone concentration was measured using ten KET-1 meters and three test strips. The % bias at each hematocrit level relative to the result obtained STANBIO $\beta$-Hydroxybutyrate LiquiColor Test Kit was calculated. The result support the claimed acceptance hematocrit range of $20 - 60\%$.
2. Altitude Study:
An altitude/oxygen dependability study was performed to assess the effect of low oxygen levels when the system is used at elevations above sea level. For testing two levels sea level (0 and 10, 335 feet). Venous whole blood samples at five levels approximately 0.5, 2.0, 4.0, 6.0 and $7.5\mathrm{mmol / L}$ and two levels of KET-1 control solution were tested at sea level and 10, 335 feet elevation. Twenty ketone readings per ketone level were taken at each of the two elevations. The results demonstrated acceptable bias to support the claim that altitude up to 10, 335 feet have no significance effect on $\beta$ -Ketone measurement when measured with KET-1 monitoring system.
9
{9}
10
3. Operating Conditions Study:
The sponsor performed testing in operating condition studies to evaluate the operating temperature and relative humidity (RH) ranges. Venous whole blood samples with β-Ketone concentrations ranges of 0.47 mmol/L, 2.21 mmol/L, 3.76 mmol/L 6.15 mmol/L were tested. Each sample was tested at the combined temperature and humidity conditions shown below using 10 KET-1 meters, and 3 lots of KET-1 test strip. The results obtained on the KET-1 Blood Ketone meter were compared to results obtained using the STANBIO β-Hydroxybutyrate LiquiColor Test Kit.
| Temperature | 10, 20, 25, 30, 40±2°C at 45-55%RH |
| --- | --- |
| Relative Humidity | 20%±5% at 10°C and 40°C |
| | 50%±5% at 25°C |
| | 90%±5% at 10°C and 40°C |
The results support the sponsor’s claimed operating temperature range of 50-104°F (10°C – 40°C) and 20-90% RH.
4. Sample Volume Study:
A sample volume study was conducted to verify the minimum sample volume required for the KET-1 monitoring system. Venous whole blood samples were tested at 0.6 μL, 0.7 μL, 0.8 μL, 0.9 μL and 10 μL volume. Samples had concentration of (0.50 mmol/L, 3.91 mmol/L, 7.44mmol/L). Testing was performed using 10 test strips for each of three lots of test strips for each test volume and each ketone level. Results from the study support the claimed sample volume of 0.8 μL.
5. Electromagnetic Compatibility:
The sponsor provided documentation certifying that acceptable electromagnetic testing had been performed and the KET-1 Monitoring System was found compliant.
6. Infection Control Studies:
This device system is intended for single-patient use only. Disinfection efficacy studies were previously performed (k131750) on the materials comprising the meter by an outside commercial testing laboratory demonstrating complete inactivation of hepatitis B virus (HBV) with the chosen disinfectant, Clorox Healthcare Bleach Germicidal Wipes (EPA Registration # 67619-12-5813). Robustness testing was conducted by the sponsor demonstrating that there was no change in performance or external materials of the meter after 1825 cleaning and disinfection cycles with Clorox Healthcare Bleach Germicidal Wipes. The robustness studies were designed to simulate 5 years of single-patient use. Labeling was reviewed for adequate instructions for the validated cleaning and disinfection procedures.
{10}
Q. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Parts 809.10.
R. 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.