Clinical study of human subjects undergoing routine breath testing
A comparative clinical study was conducted to demonstrate substantial equivalence between the modified BreathID® Hp System and the predicate BreathID® System by testing human subjects in a clinical setting.
Clinical validation; Comparative study; H. pylori diagnosis
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Clinical validation of BreathID® Hp System; Single center, non-randomized, comparative study
Adult patients undergoing H. pylori testing; Sample Size: 79; Number of Sites: 1
Unmodified BreathID® System (K011668)
Positive and negative percent agreement between modified and unmodified systems
Indications for Use
The Exalenz BreathID® Hp System is intended for use to continually and non-invasively measure changes in the 13CO2 / 12CO2 ratio of exhaled breath, which may be indicative of increased urease production associated with active Helicobacter pylori (H. pylori) infection in the stomach. The Exalenz BreathID® Hp System is indicated for use as an aid in the initial diagnosis and post treatment monitoring of H. pylori infection in adult patients. The Exalenz BreathID® Hp System consists of the IDkit:Hp™ and the BreathID® Hp test device. The device is for use by trained health care professionals. To be administered under a physician's supervision.
Device Story
The BreathID® Hp System is a non-invasive diagnostic device used by trained healthcare professionals in clinical settings to detect H. pylori infection. The system analyzes patient breath samples collected via a nasal cannula (IDcircuit™ Oridion Nasal FilterLine™) before and after the patient ingests a 13C-urea tablet and Citrica (citric acid) solution. The device utilizes Molecular Correlation Spectroscopy™ (MCS™) to measure the ratio of 13CO2 to 12CO2 in exhaled breath. By calculating the Delta over Baseline (DOB)—the change in the 13CO2/12CO2 ratio—the system identifies increased urease activity, which is indicative of H. pylori. The device provides automated measurements and quality control checks (System Check) using patient breath. Results are used by physicians to aid in diagnosis and monitor treatment efficacy. The system is designed to be compact and portable, featuring a touchscreen interface and Windows® CE operating system.
Clinical Evidence
Comparative clinical study (n=79) evaluated the modified BreathID® Hp System against the predicate device. Primary endpoint: agreement of H. pylori diagnosis. Results: 100% positive percent agreement (95% CI: 81.6–100) and 97% negative percent agreement (95% CI: 89.0–99.1). Analytical performance included precision/reproducibility studies per CLSI EP05-A2 and EP15-A2, showing CVs ranging from 3.4% to 12.9% across various DOB levels. Gas collection and system check verification confirmed hardware modifications perform within specifications.
Technological Characteristics
The device uses Molecular Correlation Spectroscopy™ (MCS™) based on optical absorption of radiation from CO2 discharge lamps to measure 13CO2/12CO2 ratios. It features a compact form factor with a touchscreen interface, Windows® CE operating system, and a single pump configuration. Connectivity includes data acquisition via custom boards. The system performs automated quality control (System Check) using patient breath. It is designed for clinical use by trained professionals.
Indications for Use
Indicated for adult patients as an aid in the initial diagnosis and post-treatment monitoring of active Helicobacter pylori (H. pylori) infection in the stomach.
Regulatory Classification
Identification
Campylobacter fetus serological reagents are devices that consist of antisera conjugated with a fluorescent dye used to identify Campylobacter fetus from clinical specimens or cultured isolates derived from clinical specimens. The identification aids in the diagnosis of diseases caused by this bacterium and provides epidemiological information on these diseases. Campylobacter fetus is a frequent cause of abortion in sheep and cattle and is sometimes responsible for endocarditis (inflammation of certain membranes of the heart) and enteritis (inflammation of the intestines) in humans.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K130524
B. Purpose for Submission:
Clearance for modification of a cleared instrument (K011668)
C. Manufacturer and Instrument Name:
Exalenz Bioscience BreathID Hp System
D. Type of Test or Tests Performed:
H. pylori $^{13}$C-urea Breath Test
E. System Descriptions:
1. Device Description:
The modified BreathID® Hp System is a non-invasive breath test system for detecting the presence of Helicobacter pylori (H. pylori). The system consists of an electro-optical medical device with embedded software designed to measure and compute the changes in ratio between $^{13}\mathrm{CO}_2$ and $^{12}\mathrm{CO}_2$ concentrations in the patient's exhalation and a test kit. The test kit consists of:
- IDcircuit™ - Oridion Nasal FilterLine™ (nasal cannula) (K980325)
- A 75mg $^{13}$C-urea tablet
- A 4.3g package of powdered Citrica (citric acid)
- Drinking straw
- Package Insert (Instructions for Use)
The modified BreathID® Hp System measures and computes the ratio between $^{13}\mathrm{CO}_2$ and $^{12}\mathrm{CO}_2$ in the patient's exhalation before and after the ingestion of $^{13}\mathrm{C}$-urea. The change in the $^{13}\mathrm{CO}_2 / ^{12}\mathrm{CO}_2$ ratio before and after ingestion of $^{13}\mathrm{C}$-urea is referred to as the Delta over Baseline (DOB).
The basis of the $^{13}\mathrm{C}$ measurement method for both the modified and unmodified versions of the BreathID® System is a technology called Molecular Correlation Spectroscopy™ (MCS™). MCS™ is based on the concept of optical absorption of specific radiation emitted from $\mathrm{CO}_{2}$ discharge lamps.
{1}
2. Principles of Operation:
The Exalenz BreathID® Hp System non-invasive breath test is a diagnostic test that analyzes a breath sample before and after ingestion of $^{13}\mathrm{C}$-enriched urea; it is used to identify those patients with *H. pylori* infection. The Exalenz BreathID® Hp System breath test is performed as follows: a $75\,\mathrm{mg}\,^{13}\mathrm{C}$-urea tablet and $4.3\,\mathrm{g}$ Citrica Powder are dissolved in water, and the resulting solution is ingested by the patient. The presence of the Citrica creates an acidic environment in the stomach and also delays the transfer of the ingested solution to the duodenum. These two characteristics facilitate the decomposition of the urea by *H. pylori*, if present. Thus, in the presence of urease associated with gastric *H. pylori*, $^{13}\mathrm{C}$-urea is decomposed to $^{13}\mathrm{CO}_2$ and $\mathrm{NH}_3$ according to the following equation:
$$
2\,^{13}\mathrm{C}\text{-urea} + 2\,\mathrm{H}_2\mathrm{O} \quad \begin{array}{l} \text{H. pylori urease} \\ 2\,^{13}\mathrm{CO}_2 + 2\,\mathrm{NH}_3 \end{array}
$$
The $^{13}\mathrm{CO}_2$ is absorbed into the blood and then exhaled in the breath. Absorption and distribution of $^{13}\mathrm{CO}_2$ is fast. Therefore, the cleavage of urea by the *H. pylori* urease that produces the $^{13}\mathrm{CO}_2$ occurs immediately after the solution is ingested and enables immediate detection of increased $^{13}\mathrm{CO}_2$ in the exhaled breath of *H. pylori*-positive patients.
In the case of *H. pylori*-negative patients, the $^{13}\mathrm{C}$-urea does not produce $^{13}\mathrm{CO}_2$ in the stomach because there are no human enzymes that can decompose the urea in the stomach.
The test begins with the collection of a baseline breath sample. The patient breathes normally while the BreathID® Hp System collects samples through the IDcircuit™ nasal cannula. The IDcircuit™ extracts moisture and patient secretions from the breath samples to provide accurate $\mathrm{CO}_2$ readings, and the device measures the $^{13}\mathrm{CO}_2 / ^{12}\mathrm{CO}_2$ ratio of the baseline measurement. The patient then ingests a test drink consisting of $^{13}\mathrm{C}$-urea tablet $75\,\mathrm{mg}$ and $4.3\,\mathrm{g}$ of citric Powder (4g citric acid). While the patient continues to breathe normally, the BreathID® Hp System continually and non-invasively samples the patient’s breath (via the cannula) and measures the changes in the $^{13}\mathrm{CO}_2 / ^{12}\mathrm{CO}_2$ ratio versus the original baseline sample. These changes are displayed as a graph on the display screen while the test continues. The graph shows multiple points that allow the physician to identify the change in the DOB of the $^{13}\mathrm{CO}_2 / ^{12}\mathrm{CO}_2$ ratio in response to the administered $^{13}\mathrm{C}$-urea. Once the BreathID® Hp System has collected enough data to determine whether or not a patient is *H. pylori*-positive, (i.e. the graph passes the threshold unambiguously), it automatically ends the test and prints out the results.
3. Modes of Operation:
Single sample
{2}
4. Specimen Identification:
Manual
5. Specimen Sampling and Handling:
Specimen acquired through nasal cannula
6. Calibration:
Calibration is performed by the instrument by diluting pre-dose patient breath or operator breath into five different concentrations within an absolute maximum concentration range. The device uses these five concentrations to determine the systematic error of the system and to ensure that the estimated systematic error is below a specified value. If the systematic error is not below the specified value, the device prompts the user to contact Exalenz for repair or replacement.
7. Quality Control:
To ensure correct functioning of the BreathID® Hp System in the field, a self test is required every 25 breath tests. BreathID® Hp System will automatically perform a self test after 25 tests are completed, during the baseline measurement phase of the next patient test. This procedure confirms that the BreathID® Hp System is functional and is performing within specifications.
8. Software:
FDA has reviewed applicant’s Hazard Analysis and Software Development processes for this line of product types:
Yes ☐ X ☐ or No ☐
The sponsor provided all software documentation in Section 18 of the submission. They followed the Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices and provided adequate documentation. The current BreathID Hp System software version is 2.1.7.
F. Regulatory Information:
1. Regulation section:
21 CFR 866.3110 Campylobacter fetus serological agents
2. Classification:
Class I
{3}
3 Product code:
MSQ
4. Panel:
83 Microbiology
## G. Intended Use:
1. Indication(s) for Use:
The Exalenz BreathID® Hp System is intended for use to continually and non-invasively measure changes in the $^{13}\mathrm{CO}_2 / ^{12}\mathrm{CO}_2$ ratio of exhaled breath, which may be indicative of increased urease production associated with active Helicobacter pylori (H. pylori) infection in the stomach. The Exalenz BreathID® Hp System is indicated for use as an aid in the initial diagnosis and post treatment monitoring of H. pylori infection in adult patients. The Exalenz BreathID® Hp System consists of the IDkit:Hp™ and the BreathID® Hp test device.
The device is for use by trained health care professionals. To be administered under a physician's supervision.
2. Special Conditions for Use Statement(s):
For prescription use only
## H. Substantial Equivalence Information:
1. Predicate Device Name(s) and 510(k) numbers:
BreathID® System, Exalenz Bioscience Ltd., K011668
2. Comparison with Predicate Device:
| Similarities | | |
| --- | --- | --- |
| Item | Exalenz Modified BreathID® Hp System | Exalenz BreathID® System (K011668) |
| Product Code | MSQ – Test, Urea (Breath or Blood) | MSQ – Test, Urea (Breath or Blood) |
| Regulation Number | 21 CFR 866.3110
Campylobacter fetus serological reagents | 21 CFR 866.3110
Campylobacter fetus serological reagents |
| Regulatory Class | Class I | Class I |
| Intended Use / Indications for Use | The Exalenz BreathID® Hp System is intended for use to continually and non- | The Exalenz BreathID® Hp System is intended for use to continually and non- |
{4}
| Similarities | | |
| --- | --- | --- |
| Item | Exalenz Modified BreathID® Hp System | Exalenz BreathID® System (K011668) |
| | invasively measure changes in the $^{13}\mathrm{CO}_2 / ^{12}\mathrm{CO}_2$ ratio of exhaled breath, which may be indicative of increased urease production associated with active Helicobacter pylori (H. pylori) infection in the stomach. The Exalenz BreathID® Hp System is indicated for use as an aid in the initial diagnosis and post treatment monitoring of H. pylori infection in adult patients. The Exalenz BreathID® Hp System consists of the IDkit:Hp™ and the BreathID® Hp test device.
The device is for use by trained health care professionals. To be administered under a physician’s supervision. | invasively measure changes in the $^{13}\mathrm{CO}_2 / ^{12}\mathrm{CO}_2$ ratio of exhaled breath, which may be indicative of increased urease production associated with active Helicobacter pylori (H. pylori) infection in the stomach. The Exalenz BreathID® Hp System is indicated for use as an aid in the initial diagnosis and post treatment monitoring of H. pylori infection in adult patients. The Exalenz BreathID® Hp System consists of the IDkit:Hp™ and the BreathID® Hp test device.
The device is for use by trained health care professionals. To be administered under a physician’s supervision. |
| Use Environment | By healthcare professionals in the clinical setting | By healthcare professionals in the clinical setting |
| Test Sample | Gas Sample continually transported to test measurement device by Exalenz (formerly Oridion) nasal cannula FilterLine™ (K980325) | Gas Sample continually transported to test measurement device by Exalenz (formerly Oridion) nasal cannula FilterLine™ (K980325) |
| $^{13}\mathrm{C}$ Urea | 75mg tablet dissolved in water (NDA 21-314) | 75mg tablet dissolved in water (NDA 21-314) |
| Applicable pre- and post-treatment | Yes | Yes |
| Test Meal | 4.3g Citrica (citric acid) dissolved in water | 4.3g Citrica (citric acid) dissolved in water |
| Test Duration | 10-30 minutes | 10-30 minutes |
| Breath Collection | Continually over test duration | Continually over test duration |
| Cut-off Point | 5.0 DOB per mil (post dose | 5.0 DOB per mil (post dose |
{5}
| Similarities | | |
| --- | --- | --- |
| Item | Exalenz Modified BreathID® Hp System | Exalenz BreathID® System (K011668) |
| | minus pre dose) | minus pre dose) |
| Organism | Helicobacter pylori in vivo | Helicobacter pylori in vivo |
| Reagent | \( ^{13}\mathrm {C} \) Urea | \( ^{13}\mathrm {C} \) Urea |
| Result | \( ^{13}\mathrm {CO}_{2}/^{12}\mathrm {CO}_{2} \) ratio – Molecular Correlation SpectroscopyTM (MCSTM) | \( ^{13}\mathrm {CO}_{2}/^{12}\mathrm {CO}_{2} \) ratio – Molecular Correlation SpectroscopyTM (MCSTM) |
| Differences | | |
| --- | --- | --- |
| Item | Exalenz Modified BreathID® Hp System | Exalenz BreathID® System (K011668) |
| Operating System | Windows® CE | Windows® 95 |
| Software Development Language / Environment | C# within Microsoft Visual Studio | LabView™ and its associated code generation functions |
| User Interface | Touchscreen monitor | Mechanical push button for operation |
| Footprint | Small footprint for desktop use with an integrated touchscreen monitor | Standalone device with wheels, including a monitor on an extendable arm |
| Data Acquisition Board | A custom data acquisition card | An off-the-shelf data acquisition card |
| Pneumatic Unit | 1 pump | 2 pumps |
| CO2 sensor | \( ^{12}\mathrm {CO}_{2} \) cell in \( ^{13}\mathrm {CO}_{2}/^{12}\mathrm {CO}_{2} \) measurement subsystem | Capnograph |
| System Check (Quality Control) | Utilizes operator breath or pre-dose patient breath | Utilizes a supplied gas canister containing approximately 100% CO2 |
| In-Measurement Variability Reduction | Performed by the \( ^{13}\mathrm {CO}_{2}/^{12}\mathrm {CO}_{2} \) measurement subsystem | Performed by the sealed reference cell, fibers, shutter and second detector |
# I. Special Control/Guidance Document Referenced (if applicable):
FDA Draft Guidance "Establishing Performance Characteristics of In Vitro Diagnostic Devices for the Detection of Helicobacter pylori," September 23, 2010
# J. Performance Characteristics:
1. Analytical Performance:
a. Accuracy:
See Precision study
{6}
b. Precision/Reproducibility:
Precision
The Precision study was performed in accordance with the following standards:
- Clinical and Laboratory Standards Institute EP05-A2 Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline – Second Edition, 2004
- Clinical and Laboratory Standards Institute EP15-A2 User Verification of Performance for Precision and Trueness; Approved Guideline – Second Edition, 2005
The Precision study was performed with three H. pylori samples that included a high positive, low positive and moderate positive, as defined in the FDA Draft Guidance “Establishing Performance Characteristics of In Vitro Diagnostic Devices for the Detection of Helicobacter pylori,” September 23, 2010. The Precision validation was performed using one modified BreathID® Hp System for twelve days, executing two runs per day. Each test run included three different combinations of baseline / post-ingestion combinations, and each combination of baseline / post-ingestion gases was consecutively tested twice. Calibration was performed on the first and seventh days of the Precision study. The tabulated accuracy results and the tabulated repeatability results are provided in the tables below, respectively.
Precision Study DOB Accuracy Results
| Expected DOB | Accuracy (Mean) | 95% CI |
| --- | --- | --- |
| DOB: 4.3‰ | 4.67 | [4.5 – 4.85] |
| DOB: 5.9‰ | 5.85 | [5.52 – 6.17] |
| DOB: 15.5‰ | 15.78 | [15.57 – 15.99] |
DOB Repeatability and Between-Day Precision
| Expected DOB | Parameter | SD Value | 95% CI | CV |
| --- | --- | --- | --- | --- |
| DOB: 4.3‰ | Repeatability | 0.559 | [0.499 – 0.635] | 12.0% |
| | Between-Days Precision | 0.603 | [0.525 – 0.681] | 12.9% |
| DOB: 5.9‰ | Repeatability | 0.479 | [0.427 – 0.544] | 8.2% |
| | Between-Days Precision | 0.691 | [0.621 – 0.760] | 11.8% |
| DOB: 15.5‰ | Repeatability | 0.689 | [0.615 – 0.784] | 4.4% |
| | Between Days Precision | 0.738 | [0.664 – 0.811] | 4.7% |
Reproducibility
The Reproducibility study was performed in accordance with the following standards:
- Clinical and Laboratory Standards Institute EP05-A2 Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline – Second Edition, 2004
{7}
- Clinical and Laboratory Standards Institute EP15-A2 User Verification of Performance for Precision and Trueness; Approved Guideline – Second Edition, 2005
The Reproducibility study was performed with three *H. pylori* samples that included a high positive, low positive and moderate positive, as defined in the FDA Draft Guidance “Establishing Performance Characteristics of *In Vitro* Diagnostic Devices for the Detection of *Helicobacter pylori*,” September 23, 2010. The Reproducibility study was performed using three devices in three different sites for five days. Two test runs were executed per day by different operators. Each test run utilized three different combinations of baseline / post-ingestion gases and each combination of baseline / post-ingestion gases was consecutively tested three times. Calibration was performed on the first day of the Reproducibility study. The tabulated accuracy results and the tabulated reproducibility results are provided in the tables below, respectively.
Reproducibility Study DOB Accuracy Results
| Expected DOB | Accuracy (Mean) | 95% CI |
| --- | --- | --- |
| DOB: 4.5‰ | 4.82 | 4.60 – 5.05 |
| DOB: 5.9‰ | 6.18 | 4.97 – 7.40 |
| DOB: 15.5‰ | 15.69 | 15.41 – 15.98 |
DOB Reproducibility, Between-Day Reproducibility and Between-Operator Reproducibility
| Expected DOB | Parameter | SD Value | 95% CI | CV |
| --- | --- | --- | --- | --- |
| DOB: 4.5‰ | Reproducibility | 0.524 | 0.483 – 0.573 | 10.9% |
| | Between-Days Reproducibility | 0.533 | 0.455 – 0.624 | 11.0% |
| | Between-Operators Reproducibility | 0.524 | 0.444 – 0.619 | 10.9% |
| DOB: 5.9‰ | Reproducibility | 0.563 | 0.518 – 0.615 | 9.2% |
| | Between-Days Reproducibility | 0.648 | 0.576 – 0.712 | 10.6% |
| | Between-Operators Reproducibility | 0.697 | 0.612 – 0.780 | 11.4% |
| DOB: 15.5‰ | Reproducibility | 0.536 | 0.494 – 0.586 | 3.4% |
| | Between-Days Reproducibility | 0.536 | 0.479 – 0.585 | 3.4% |
| | Between-Operators Reproducibility | 0.538 | 0.485 – 0.591 | 3.4% |
{8}
c. Linearity:
Not applicable
d. Carryover:
Not applicable
e. Interfering Substances:
Not applicable
2. Other Supportive Instrument Performance Data Not Covered Above:
## BreathID® Hp System
The modified BreathID® Hp System has the same fundamental scientific technology and principle of operation utilized in the unmodified BreathID® System. The technological modifications of the BreathID® Hp System are modifications to the configuration of the system and software revisions as a result of the modified hardware configuration.
This modified BreathID® Hp System is designed to be more compact, less expensive and easier to maintain than the unmodified system. In addition, the modified BreathID® Hp System either eliminates or consolidates components that have become redundant or obsolete.
## Analytical studies
### Gas Collection Verification
A Gas Collection Verification was performed to verify that the $^{12}\mathrm{CO}_2$ cell of the $^{13}\mathrm{CO}_2$ and $^{12}\mathrm{CO}_2$ measurement subsystem of the BreathID® Hp System could adequately replace the Capnograph of the unmodified BreathID® System for measuring the $\mathrm{CO}_2$ concentration in incoming gases. Twenty (20) tests were performed with breath samples that were not $^{13}\mathrm{C}$ enriched from ten (10) different subjects. Each of the twenty (20) tests also included seven (7) DOB measurements from the measurement phase (MP) in various calibration ranges. The results of the Gas Collection Verification demonstrated that the DOB standard deviation of all measurement phase (MP) test results were within the specifications, all MP test sample concentrations were within the calibration range, and that all MP sample concentrations had a standard deviation of less than 0.2. Therefore, the $^{12}\mathrm{CO}_2$ cell of the $^{13}\mathrm{CO}_2$ and $^{12}\mathrm{CO}_2$ measurement subsystem of the BreathID® Hp System has been verified to adequately replace the Capnograph of the unmodified BreathID® System for measuring the $\mathrm{CO}_2$ concentration in incoming gases.
### System Check Verification
A System Check Verification was performed to verify that operator breath or pre-dose
9
{9}
patient breath could adequately replace the gas canister containing approximately 100% CO₂ for the purposes of the System Check, one of the Quality Control functions of the BreathID® Hp System and the unmodified BreathID® System. Twenty (20) tests were performed with breath samples from eleven (11) different subjects. Each of the twenty (20) tests also included seven (7) DOB measurements. The results of the System Check Verification demonstrated that in all cases where the ¹²C curves were randomly changed and a calibration was then required, the situation was correctly identified by the BreathID® Hp System and a calibration was performed. In all cases where the ¹²C curves were unchanged and the calibration process was unable to expand the calibration range, the BreathID® Hp System correctly identified the situation and did not perform a calibration. In the case where the ¹²C curve was unchanged, but the calibration range was expanded and a calibration was then required the BreathID® Hp System correctly identified the situation and performed a calibration. All test results following a System Check and calibration were within the specifications of the BreathID® Hp System. Additionally, all test results following a System Check that did not require calibration were within the specifications of the BreathID® Hp System. Therefore, the System Check Verification not only demonstrated that operator breath or pre-dose patient breath could be adequately used for the System Check procedure, but it also demonstrated that the calibration process was effective.
## Software Verification and Validation
Software Verification evaluated all system functionality and consisted of evaluations of the software through unit, integration and system level testing, as well as code reviews. Software Validation consisted of various test cases to qualitatively test the software system of the BreathID® Hp System. The test case categories that were utilized for the software validation of the BreathID® Hp System were:
- H. Pylori Patient Mode Tests
- System Test
- Utilities, and
- System Failures
All test cases were implemented with a known input and an expected output. The expected output was visually compared against the actual output. All test cases were verified to have passing results.
## Comparative Validation
A Comparative Validation was performed to evaluate the agreement of the modified BreathID® Hp System DOB measurements to its predicate device, the unmodified BreathID® System. The Comparative Validation was performed in accordance with the following standard:
- Clinical and Laboratory Standards Institute EP09-A2 Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline – Second Edition
The Comparative Validation was performed with three H. pylori samples that included a high positive, low positive and moderate positive, as defined in the FDA Draft Guidance "Establishing Performance Characteristics of In Vitro Diagnostic Devices for the Detection of Helicobacter pylori," September 23, 2010. The Comparative Validation was performed with one modified BreathID® Hp System and one unmodified BreathID®
10
{10}
System, executing two runs per day for five days. Each test run included three different combinations of baseline / post-ingestion gases and each combination of baseline / post-ingestion gases was consecutively tested twice. The modified BreathID® Hp System and the unmodified BreathID® System were evaluated simultaneously by connecting the two devices with a Y-Connector. Calibration was performed on the first day of the Comparative Validation. The table below provides the results and analysis of the Comparative Validation.
11
{11}
Distribution of DOB Measurements Between Modified and Unmodified BreathID® Systems
| Expected DOB | Parameter | N | Mean | SD | Min | Median | Max |
| --- | --- | --- | --- | --- | --- | --- | --- |
| DOB: 4.5‰ | DOB Modified BreathID® | 20 | 4.96 | 0.350 | 4.3 | 4.97 | 5.6 |
| | DOB Unmodified BreathID® | 20 | 4.69 | 0.233 | 4.2 | 4.65 | 5.2 |
| | Difference in DOB Between Devices | | 0.27 | 0.368 | -0.5 | 0.28 | 1.0 |
| DOB: 5.8‰ | DOB Modified BreathID® | 20 | 6.37 | 0.297 | 6.0 | 6.33 | 7.0 |
| | DOB Unmodified BreathID® | 20 | 6.07 | 0.266 | 5.5 | 6.07 | 6.5 |
| | Difference in DOB Between Devices | | 0.30 | 0.366 | -0.3 | 0.20 | 0.9 |
| DOB: 13‰ | DOB Modified BreathID® | 20 | 14.09 | 0.424 | 13.2 | 14.03 | 14.9 |
| | DOB Unmodified BreathID® | 20 | 13.32 | 0.358 | 12.4 | 13.37 | 13.8 |
| | Difference in DOB Between Devices | | 0.78 | 0.526 | -0.3 | 0.75 | 1.7 |
A Pearson’s correlation coefficient was calculated between the DOB measurements from the unmodified and modified BreathID® Systems. A correlation plot of the DOB measurements from the modified and unmodified BreathID® Systems is provided in the figure below. The following values were calculated:
- r = 0.9944 (95% CI: [0.9904, 0.9966]
- p < 0.0001
{12}

Correlation Plot of DOB Measurements from Unmodified and Modified BreathID® Systems
The table below presents the slope and intercept of the Deming Regression, along with the respective $95\%$ confidence interval (CI).
Deming Regression Slope and Intercept
| Deming Slope [95% CI] | Deming Intercept [95% CI] |
| --- | --- |
| 1.06 [1.029, 1.095] | -0.05 [-0.302, 0.197] |
# Clinical Study
A single center, non-randomized, blinded, comparative study was conducted to compare the modified BreathID® Hp System to the unmodified BreathID® System. The breath test was performed according to the standard procedure described in the device's instructions for use and routine clinical practice while the subject was connected simultaneously to both the BreathID® Hp System and the unmodified BreathID® System via two standard nasal cannulae. The outcome measures of both devices were used for the comparison.
In order to prevent a spectrum bias, the breath test was performed in addition to, and independent of the local clinical practice. In cases were a serum blood test was performed, these blood tests were the only means used to diagnose the presence of $H$ .
{13}
pylori. In other cases, where the investigator did not feel a blood test was warranted (change in diet prescribed, or symptoms not specific to $H$ pylori), the patient was periodically followed up at the clinic as routine general practice with no eradication therapy prescribed. In these cases, only if symptoms persisted or became more related to $H$ pylori infection, was the patient sent for blood tests. The breath testing was performed by a site technician and not in the proximity of the Principal Investigator. The breath test results were made available to the treating physician (Principal Investigator) only once the patient's management protocol had been determined. Thus, the test results from both devices were masked from the treating physician and did not have an impact on the patient's treatment.
The clinical study was conducted in compliance with its protocol and in accordance with the ethical principles under Investigational Review Board (IRB) approval consistent with Good Clinical Practice (GCP) and with applicable regulatory requirements. The table below presents the subjects' accountability and the subjects' baseline characteristics per protocol (PP).
Subject Baseline Characteristics
| Parameter | | Statistic | PP |
| --- | --- | --- | --- |
| Age | N | 79 | |
| | | Mean (SD) | 49.2 (16.54) |
| | | Median [min-max] | 50.5 [18.4 – 87.8] |
| Height | N | 77 | |
| | | Mean (SD) | 164.0 (9.90) |
| | | Median [min-max] | 163.0 [142.0 – 185.0] |
| Weight | N | 79 | |
| | | Mean (SD) | 69.5 (16.65) |
| | | Median [min-max] | 66.0 [43.0 – 117.0] |
| BMI | N | 77 | |
| | | Mean (SD) | 25.7 (4.92) |
| | | Median [min-max] | 24.4 [17.4 – 44.4] |
| Sex | Male | % (n/N) | 41.77% (33/79) |
| | Female | % (n/N) | 58.23% (46/79) |
| Ethnicity | African-American | % (n/N) | 1.27% (1/79) |
| | Asian-Pacific | % (n/N) | 68.35% (54/79) |
| | Caucasian | % (n/N) | 12.66% (10/79) |
| | Hispanic | % (n/N) | 15.19% (12/79) |
| | Other | % (n/N) | 2.53% (2/79) |
# PP Analysis Set
The PP analysis set consisted of all subjects enrolled in the study that did not have any major protocol deviations and had no other relevant $H$ pylori testing prior to enrollment
{14}
in the study, which was defined as no positive test results within 2012 and no negative test results within three months prior to enrollment. The cross tabulation of the diagnosis as assessed by both the modified and unmodified BreathID® Systems in the PP analysis set is provided in the table below. The PP analysis set included 79 valid subjects per the protocol.
PP Analysis Set Agreement
| | Unmodified BreathID® System | | Total | |
| --- | --- | --- | --- | --- |
| | | Positive | | Negative |
| BreathID® Hp System | Positive | 17 | 2 | 19 |
| | Negative | --- | 60 | 60 |
| Total | | 17 | 62 | 79 |
- Positive percent agreement = 100% [95% CI (81.6, 100)]
- Negative percent agreement = 97% [95% CI (89.0, 99.1)]
This result satisfied the acceptance criterion of $\geq 95\%$ and therefore the study was successful in demonstrating equivalence of the two devices.
K. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
L. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.