K020489 · Tosoh Medics, Inc. · JPD · May 14, 2002 · Hematology
Device Facts
Record ID
K020489
Device Name
G7 AUTOMATED HPLC ANALYZER, BETA-THALASSEMIA MODE
Applicant
Tosoh Medics, Inc.
Product Code
JPD · Hematology
Decision Date
May 14, 2002
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 864.7400
Device Class
Class 2
Indications for Use
The G7 Automated HPLC Analyzer: Beta-thalassemia Mode is intended for IN VITRO DIAGNOSTIC USE ONLY for the separation and area percent determinations of hemoglobins A2 and F and as an aid in the detection and presumptive identification of abnormal hemoglobins in whole blood using ion-exchange high performance liquid chromatography (HPLC). The G7 Automated HPLC Analyzer: Beta-thalassemia Mode reagents and software are intended only for use on the Tosoh G7 Automated HPLC Analyzer.
Device Story
G7 Automated HPLC Analyzer: Beta-thalassemia Mode is an automated ion-exchange HPLC system for clinical laboratory use. Input: EDTA whole blood samples. Operation: Automated sampling unit, liquid pump, degasser, and cation exchange column separate hemoglobin fractions via salt concentration gradient elution. Detection: Colorimetric measurement at 415 nm. Output: Quantitative area percentages for HbA2 and HbF; chromatographic tracings; presumptive identification of hemoglobin variants (e.g., A, F, S, C, D) based on retention time windows. Data management: On-board printer, floppy disk storage, and RS232 host computer transmission. Clinical utility: Aids clinicians in diagnosing hemoglobinopathies by providing quantitative hemoglobin profiles and identifying abnormal patterns. Benefits: Automated processing reduces manual labor and improves consistency in hemoglobin analysis compared to traditional electrophoresis or manual chromatography.
Clinical Evidence
Clinical performance evaluated via comparative analysis of patient samples. HbA2 quantitation (n=75) compared to micro-chromatographic method showed slope 0.9318, r=0.9318. HbF quantitation (n=57) compared to HPLC method showed slope 0.778, r=0.9906. Qualitative identification of hemoglobin variants (n=155) compared to electrophoresis showed high concordance. Precision studies: intra-assay CVs 4.3-13.5% (HbF) and 1.3-2.1% (HbA2); between-day CVs 2.2-7.7% (HbF) and 2.4-3.3% (HbA2). Recovery: 99.4-107.1%.
Technological Characteristics
Automated HPLC system using cation exchange column. Energy source: electrical (microprocessor-controlled). Connectivity: RS232 port for host computer. Form factor: benchtop analyzer with sampling unit, pump, degasser, detector, and printer. Software: microprocessor-controlled, floppy disk-loaded. Detection: 415 nm colorimetric. Reagents: elution buffers with salt gradients.
Indications for Use
Indicated for in vitro diagnostic use in patients requiring quantitative measurement of Hemoglobin A2 and F and presumptive identification of abnormal hemoglobins in EDTA whole blood samples.
Regulatory Classification
Identification
A hemoglobin A2 assay is a device used to determine the hemoglobin A2 content of human blood. The measurement of hemoglobin A2 is used in the diagnosis of the thalassemias (hereditary hemolytic anemias characterized by decreased synthesis of one or more types of hemoglobin polypeptide chains).
{0}------------------------------------------------
1020489
MAY 1 4 2002
Image /page/0/Picture/2 description: The image shows the logo for Tosoh Medics, Inc. The logo consists of a stylized four-leaf clover shape with a square in the center, followed by the text "TOSOH MEDICS, INC." to the right. Below the clover shape is the text "TOSOH" with a horizontal line underneath.
# 510(k) Summary
# Tosoh G7 Automated HPLC Analyzer: Beta-thalassemia Mode
| Submitter: | Tosoh Medics, Inc.<br>347 Oyster Point Blvd., Suite 201<br>South San Francisco, CA 94080<br>Phone: (800) 248-6764<br>Fax: (610) 615-4970 |
|------------------------------|------------------------------------------------------------------------------------------------------------------------------------------|
| Contact Person: | Lois Nakayama<br>Manager, Quality Assurance |
| Date of Summary Preparation: | February 8, 2002 |
| Device Name: | G7 Automated HPLC Analyzer: Beta-<br>thalassemia Mode |
| Classification Name: | Class II, JPD<br>21 CFR 864.7400<br>Hemoglobin A2 quantitation |
| Predicate Device: | HbA2: Beta-Thal HbA2 Quik ColumnTM<br>Helena Laboratories<br>Beaumont, TX<br>K823870 |
| | HbF: VARIANT BETA-THALASSEMIA<br>SHORT PROGRAM<br>Bio-Rad Laboratories<br>Hercules, CA<br>K924122 |
| | Presumptive Hb identification:<br>Beckman Paragon® Electrophoresis<br>Beckman Instruments, Inc.<br>Fullerton, CA<br>K802821 |
{1}------------------------------------------------
## Device Description:
The G7 Automated HPLC Analyzer and the HbA1c Variant Analysis Mode reagent system and software have previously cleared by the Food and Drug Administration (K011434). The subject of this submission is merely the reagent system/software specific for the Beta-thalassemia Mode that is intended for the separation and area percent determinations of hemoglobins A2 and F and as an aid in the detection and presumptive identification of abnormal hemoglobins in whole blood using ion-exchange high performance liquid chromatography (HPLC).
The G7 Automated HPLC Analyzer - Beta-thalassemia Mode is an automated High Performance Liquid Chromatography (HPLC) system that separates and reports HbF and HbA2 quantitative percentages in whole blood. A chromatographic tracing of the hemoglobin products found in the sample is also produced which allows for the comparison of an individual chromatogram with standard patterns of known composition. The operational portion of the G7 Beta-thalassemia Mode is composed of a sampling unit, liquid pump, degasser, detector, microprocessors, sample loader, floppy disk drive unit, operational panel and a printer all of which have already been cleared by the FDA (K011434). The reagents and software program specific to the Beta-thalassemia Mode consist of calibrators, elution buffers, column and software only.
The G7 Automated HPLC System - Beta-thalassemia Mode uses a cation exchange column and separates the hemoglobin in the blood into fractions. The separation is accomplished by eluting the hemoglobins from the column with a gradient of three elution buffers containing increasing salt concentrations. The resulting report is printed out on the on-board printer and can be stored on a floppy disk in the on-board floppy disk drive. The data can also be transmitted to a host computer through the RS232 port. The result report includes a sample ID, date, time, area percentages and retention time in minutes of each individual peak detected. Peaks that meet the retention time "windows" pre-set in the software are labeled as F, A0, A2, D+, S+, C+. All others are designated in order of appearance as PXX and are listed in order of appearance.
All automated processes in the G7 Beta-thalassemia Mode are controlled by internal microprocessors using software downloaded via the on-board floppy disk drive.
#### Statement of Intended Use:
The G7 Automated HPLC Analyzer: Beta-thalassemia Mode is intended for IN VITRO DIAGNOSTIC USE ONLY for the separation and area percent determinations of hemoglobins A2 and F and as an aid in the detection and presumptive identification of abnormal hemoglobins in whole blood using ion-exchange high performance liquid chromatography (HPLC).
The G7 Automated HPLC Analyzer: Beta-thalassemia Mode reagents and software are intended only for use on the Tosoh G7 Automated HPLC Analyzer.
#### Substantial Equivalence:
#### Comparison Data
The Tosoh G7 Automated HPLC Analyzer: Beta-thalassemia Mode is substantially equivalent in intended use to instrument and reagent systems in commercial distribution
Image /page/1/Picture/11 description: The image shows the logo for TOSOH. The logo consists of the word "TOSOH" in a simple, sans-serif font, with the letters stacked vertically. Above the text is a stylized graphic element that appears to be a square with rounded corners, with the top left corner filled in black and the rest of the shape in white.
{2}------------------------------------------------
that are used to quantitate Hemoglobin A2 and Hemoglobin F in whole blood and qualitatively identify clinically important abnormal human hemoglobins.
Specifically, the Tosoh G7 Automated HPLC Analyzer: Beta-thalassemia Mode is substantially equivalent to the Helena Laboratories, Inc. (Beaumont, TX) Beta-Thal HbA2 Quik Column™ (K823870) method for quantitating Hemoglobin A2 and is substantially equivalent to the Bio-Rad Laboratories (Hercules, CA) VARIANT™ BETA-THALASSEMIA SHORT PROGRAM for quantitatiing Hemoglobin F (K924122) and to the Beckman Paragon® Hemoglobin Electrophoresis as an aid in identifying broad presumptive classes of abnormal human hemoglobins. A summary comparison of the capabilities and specifications of these systems is provided below in Table 1, Table 2 and Table 3.
| Table 1 |
|-------------------------------------------------------------|
| Tosoh G7 Automated HPLC Analyzer: Beta-thalassemia Mode HbA |
| vs. |
| Helena Quik ColumnTM HbA2 |
| | G7 Automated HPLC<br>Analyzer: Beta-thal Mode | Beta-Thal HbA2 Quik<br>Column™ |
|---------------------------|----------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------|
| Intended Use | Quantitative measurement<br>of HbA2 in whole blood | Quantitative measurement<br>of HbA2 in whole blood |
| Methodology | High Performance Liquid<br>Chromatography using<br>cation exchange | Micro-chromatographic<br>technique using anion<br>exchange |
| Separation Method | Based on differences in<br>electrical charge between<br>column material and<br>hemogoblin molecule | Based on differences in<br>electrical charge between<br>column material and<br>hemoglobin molecules |
| Sample Type | EDTA whole blood | EDTA whole blood |
| Microprocessor Controlled | YES | NO |
| Automatic Sampling | YES | NO |
| Elution Method | Buffers with differing salt<br>concentrations causing an<br>elution gradient | Buffers with differing salt<br>concentrations causing an<br>elution gradient |
| End Point | Colorimetric measurement<br>at 415 nm | Colorimetric measurement<br>at 415 nm |
| Results | Quantitative HbA2 Area % | Quantitative HbA2 Area % |
| Normal Reference Interval | 1.7 - 2.9 % | 2.2 - 3.3 % |
| Imprecision | 2.4 - 3.3 % | 3.25 % |
| Upper Linearity Limit | Up to 12.8 % | Not given |
Image /page/2/Picture/4 description: The image shows a logo with the text "TOSOH" underneath. The logo is a black shape resembling a four-leaf clover with rounded edges. In the center of the clover shape is a white square.
{3}------------------------------------------------
Table 2 Tosoh G7 Automated HPLC Analyzer: Beta-thalassemia Mode HbF VS. Bio-Rad Laboratories VARIANT™ BETA-THALASSEMIA SHORT PROGRAM HbF
| | G7 Automated HPLC Analyzer: Beta-thal Mode | VARIANT™ BETA-THALASSEMIA SHORT PROGRAM |
|-------------------------------|-------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------|
| Intended Use | Quantitative measurement of HbF in whole blood | Quantitative measurement of HbF in whole blood |
| Methodology | High Performance Liquid Chromatography using cation exchange | High Performance Liquid Chromatography using cation exchange |
| Separation Method | Based on differences in electrical charge between column material and hemogoblin molecule | Based on differences in electrical charge between column material and hemoglobin molecules |
| Sample Type | EDTA whole blood | EDTA whole blood |
| Microprocessor Controlled | YES | YES |
| Automatic Sampling | YES | YES |
| Calibration | One Point Dual Analyte Calibration | One Point Dual Analyte Calibration |
| Automated Sample Pretreatment | YES | NO |
| Elution Method | Buffers with differing salt concentrations causing an elution gradient | Buffers with differing salt concentrations causing an elution gradient |
| End Point | Colorimetric measurement at 415 nm | Colorimetric measurement at 415 nm |
| Results | Quantitative HbF Area % | Quantitative HbF Area % |
| Normal Reference Interval | 0.5 - 1.9 | 2.2 - 7.7 % |
| Imprecision (Intra-assay) | 2.2 -7.7 % | Not given |
| Upper Linearity(Reportable) | Up to 35.0 % | Up to 40% |
Image /page/3/Picture/2 description: The image shows a logo with a stylized cross shape in black, with a white square in the center. The cross shape has rounded edges, giving it a soft appearance. Below the logo, the word "TOSOH" is printed in a simple, sans-serif font. The logo appears to be a corporate symbol, possibly for a company or organization.
_
{4}------------------------------------------------
## Table 3 Tosoh G7 Automated HPLC Analyzer: Beta-thalassemia Mode VS. Beckman Paragon® Hemoglobin Electrophoresis
| | G7 Automated HPLC<br>Analyzer: Beta-thal Mode | Hemoglobin<br>Electrophoresis |
|----------------------------------|----------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------|
| Intended Use | Aid in the identification of<br>abnormal human<br>hemoglobins | Electrophoretic separation<br>of human hemoglobins to<br>screen for clinically<br>important hemoglobin<br>variants |
| Methodology | High Performance Liquid<br>Chromatography using<br>cation exchange | Electrophoresis |
| Separation Method | Based on differences in<br>electrical charge between<br>column material and<br>hemoglobin molecule | Based on differences in<br>electrical charge between<br>the media and hemoglobin<br>molecules |
| Sample Type | EDTA whole blood | EDTA whole blood |
| Microprocessor Controlled | YES | NO |
| Automatic Sampling | YES | NO |
| Calibration | Software "windows" for<br>various hemoglobin<br>components are preset | Comparison of unknown<br>with samples of known<br>content |
| Automated Sample<br>Pretreatment | YES | NO |
| Elution Method | Buffers with differing salt<br>concentrations causing an<br>elution gradient | Buffers with differing salt<br>concentrations causing an<br>elution gradient |
| End Point | Colorimetric measurement<br>at 415 nm | Densitometer quantitation<br>or visual interpretation of<br>patterns obtained |
| Results | Presumptive identification<br>of certain hemoglobin<br>variants as "A", "F", "S", "C",<br>and "D" or "unknown" | Qualitative presumptive<br>identification of hemoglobin<br>variants "A", "F", "S", "C" or<br>"unknown" |
| Normal Reference Interval | Compared to "normal"<br>pattern | Compared to "normal"<br>pattern |
Image /page/4/Picture/2 description: The image shows a logo with the text "TOSOH" below it. The logo is a black shape resembling a four-leaf clover with rounded edges. In the center of the clover shape, there is a white square. The text "TOSOH" is in a simple, sans-serif font.
{5}------------------------------------------------
## Comparative Analysis
## Comparative Analysis Quantitative HbA2
Patient specimens were analyzed using the Tosoh G7 Automated HPLC Analyzer: Beta-thalassemia Mode and another commercially available quantitative HbA2 assay utilizing a micro-chromatographic methodology (Helena Laboratories' Beta-Thal HbA2 Quik Column™. Approximately onehalf the samples had HbA2 within the normal reference interval. The remainder showed elevated results. The comparison yielded the following correlation statistics when the two methods were compared using linear regression analysis:
| Slope: | 0.9318 |
|--------------------------|------------|
| Y-Intercept: | -1.08 |
| Correlation Coefficient: | 0.9318 |
| Range of Samples (%): | 1.6 – 7.4% |
| n: | 75 |
#### Comparative Analysis Quantitative HbF
Patient specimens were analyzed with the Tosoh G7 Automated HPLC Analyzer: Beta-thalassemia Mode and another commercially available quantitative HbF assay utilizing HPLC (Bio-Rad Laboratories VARIANT BETA-THALASSEMIA SHORT PROGRAM. The comparison yielded the following correlation statistics between these two methods.
| Slope: | 0.778 |
|--------------------------|------------|
| Y-Intercept: | 1.15 |
| Correlation Coefficient: | 0.9906 |
| Range of Samples (%): | 0.5 – 67.6 |
| n: | 57 |
Image /page/5/Picture/7 description: The image shows the word "TOSOH" in a sans-serif font below a black abstract shape. The shape resembles a four-leaf clover with rounded edges, and it has a white square in the center. The black shape is symmetrical and appears to be a stylized logo.
{6}------------------------------------------------
# Qualitative Comparison of Hemoglobins in Clinical Samples
Whole blood from patients suspected of having hemoglobinopathies were tested on the G7 Automated HPLC Analyzer: Beta-thalassemia Mode and the Beckman Laboratories Paragon® Hemoglobin Electrophoresis. Results from these qualitative comparisons are listed below.
| G7 Presumptive Result | Electrophoresis Result | Number of Analyses |
|---------------------------------------------|------------------------|--------------------|
| HbA/HbS* | HbA/HbS* | 37 |
| HbA/HbS*/HbA2* | HbA/HbS*/HbA2* | 1 |
| HbF*/HbS* | HbF*/HbS* | 1 |
| HbS*/HbC* | HbS*/HbC* | 2 |
| HbA/HbC* | HbA/HbC* | 11 |
| HbA/HbC*/HbF* | HbA/HbC*/HbF* | 1 |
| HbA/HbS*/HbF* | HbA/HbS*/HbF* | 1 |
| HbA/HbD* | HbA/HbD* | 7 |
| HbA/HbD*/HbF* | HbA/HbD*/HbF* | 1 |
| HbA/Hb Unknown | HbA/HbE* | 5 |
| HbA/unknown coeluting<br>with HbA2* (47.2%) | HbA/unknown | 1 |
| HbA/HbF*/Unknown fast* | HbA/HbF*/Hb Barts* | 1 |
| HbA/Hb Unknown* | HbA/Hb unknown* | 1 |
| HbA/HbA2*/HbF* | HbA/HbA2*/HbF* | 3 |
| HbA/HbA2*/HbF | HbA/HbA2*/HbF | 9 |
| HbF*/HbA/HbA2 | HbF*/HbA/HbA2 | 7 |
| HbF*/HbA/HbA2* | HbF/HbA/HbA2* | 6 |
| HbA/Hb Unknown* | HbA/HbG* | 5 |
| Normal HbA/HbF/HbA2 | Normal HbA/HbF/HbA2 | 55 |
| | TOTAL COMPARISONS | 155 |
Precision studies demonstrated intra-assay precision % CVs on HbF of 4.3 - 13.5% and on HbA2 from 1.3 - 2.1 %. Between day precision CV%s of2.2 -- 7.7% on HbF and on HbA2 2.4 -- 3.3 %. Recovery studies performed on HbF and HbA2 showed recoveries ranging from 99.4% - 107.1%.
Image /page/6/Picture/4 description: The image shows the logo for TOSOH. The logo consists of a stylized four-leaf clover shape in black, with a white square in the center. Below the logo, the word "TOSOH" is printed in a simple sans-serif font.
{7}------------------------------------------------
### Conclusion:
Considering the excellent correlation between the Tosoh G7 Automated HPLC Analyzer: Betathalassemia Mode and the other predicate devices listed above, it can be concluded that the G7 Automated HPLC Analyzer: Beta-thalassemia Mode is substantially equivalent to the other predicate devices which have been 510(K) cleared. Based on the establishment of substantial equivalence, the safety and effectiveness of the Tosoh G7 Automated HPLC Analyzer: Betathalassemia Mode is confirmed.
Image /page/7/Picture/2 description: The image shows the word "TOSOH" in all capital letters. Above the word is a black abstract shape with a white square in the center. The shape appears to be a stylized plus sign with rounded edges.
{8}------------------------------------------------
## DEPARTMENT OF HEALTH & HUMAN SERVICES
Image /page/8/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a circular seal with the text "DEPARTMENT OF HEALTH & HUMAN SERVICES • USA" around the perimeter. Inside the circle is a stylized image of an eagle or bird-like figure with three curved lines representing its wings or body.
# MAY 1 4 2002
Food and Drug Administration 2098 Gaither Road Rockville MD 20850
Ms. Lois Nakayama Manager, Ouality Assurance TOSOH Medics, Inc. 347 Oyster Point Boulevard, Suite 201 South San Francisco, California 94080
k020489 Re:
Trade/Device Name: G7 Automated HPLC Analyzer: Beta-thalassemia Mode Regulation Number: 21 CFR § 864.7400 Regulation Name: Hemoglobin A2 quantitation Regulatory Class: II Product Code: JPD Dated: April 29, 2002 Received: May 1, 2002
Dear Ms. Nakayama:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to such additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
{9}------------------------------------------------
Page 2
This letter will allow you to begin marketing your device as described in your 510(k) premarket notification. The FDA finding of substantial equivalence of your device to a legally marketed predicate device results in a classification for your device and thus, permits your device to proceed to the market.
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801 and additionally 809.10 for in vitro diagnostic devices), please contact the Office of Compliance at (301) 594-4588. Additionally, for questions on the promotion and advertising of your device, please contact the Office of Compliance at (301) 594-4639. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR 807.97). Other general information on your responsibilities under the Act may be obtained from the Division of Small Manufacturers International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 443-6597 or at its internet address "http://www.fda.gov/cdrb/dsma/dsmamain.html".
Sincerely vours.
Steven Butman
Steven I. Gutman, M.D., M.B.A. Director Division of Clinical Laboratory Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{10}------------------------------------------------
Image /page/10/Picture/0 description: The image shows the logo for Tosoh Medics, Inc. The logo consists of a black four-leaf clover-like shape with a white square in the center, followed by the text "TOSOH MEDICS, INC." to the right. Below the clover is the word "TOSOH" with a horizontal line underneath.
## PREMARKET NOTIFICATION
## INDICATION FOR USE STATEMENT
# G7 Automated HPLC Analyzer: Beta-thalassemia Mode
The G7 Automated HPLC Analyzer: Beta-thalassemia Mode is intended for IN VITRO DIAGNOSTIC USE ONLY for the separation and area percent determinations of hemoglobins A2 and F and as an aid in the detection and presumptive identification of abnormal hemoglobins in whole blood using ionexchange high performance liquid chromatography (HPLC).
The G7 Automated HPLC Analyzer: Beta-thalassemia Mode reagents and software are intended only for use on the Tosoh G7 Automated HPLC Analyzer.
Josephine Bautista.
(Division Sign-Off)
Division of Clinical Laboratory Devices
510(k) Number K020489
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.