The CAPI 3 IMMUNOTYPING kit is designed for the qualitative detection and the characterization of monoclonal proteins (immunotyping) in human urine and serum with the CAPILLARYS 3 TERA instrument, SEBIA, for capillary electrophoresis. It is used in conjunction with the CAPI 3 PROTEIN(E) 6 kit, SEBIA, designed for proteins separation into 6 major fractions in alkaline buffer (pH 9.9). The CAPILLARYS 3 TERA instrument performs all procedural sequences automatically to obtain a protein profile for qualitative analysis. Each urine or serum sample is mixed with individual antisera that are specific against gamma (Ig G), alpha (Ig A) and mu (Ig M) heavy chains, and kappa (free and bound) light chains and lambda (free and bound) light chains, respectively. The proteins, separated in silica capillaries, are directly detected by their absorbance at 200 nm. The electrophoregrams are evaluated visually to detect the presence of specific reactions with the suspect monoclonal proteins. For In Vitro Diagnostic Use.
Device Story
Device performs capillary zone electrophoresis to identify monoclonal proteins in human urine and serum. System uses CAPILLARYS 3 TERA instrument; automated processing of samples mixed with specific antisera (anti-IgG, IgA, IgM, kappa, lambda). Separation occurs in silica capillaries via high-voltage electrical field in alkaline buffer; proteins detected by absorbance at 200 nm. Immunofixation by subtraction principle: specific antisera cause electrophoretic mobility shifts of target peaks, allowing identification of aberrant protein classes. Used in clinical laboratories; operated by trained personnel. Output is visual electrophoregram; healthcare providers evaluate patterns to detect monoclonal components. Benefits include rapid, automated identification of monoclonal proteins, aiding diagnosis of conditions like multiple myeloma or Bence Jones proteinuria.
Clinical Evidence
Bench testing only. Study included 52 urine samples (8 normal, 44 with monoclonal components) comparing CAPI 3 IMMUNOTYPING on CAPILLARYS 3 TERA against predicate CAPILLARYS IMMUNOTYPING on CAPILLARYS 2. Results showed 100% qualitative agreement. Precision studies (repeatability, between-instrument, between-lot) confirmed concordant results. Detection limits for monoclonal components ranged from 0.4 to 3.0 mg/dL. Stability data supported 2-year kit shelf life, 2-month on-board stability, and urine sample storage (1 week at 2-8°C; 1 month at -70/-80°C).
Technological Characteristics
Free solution capillary electrophoresis in silica glass capillaries (ID < 100 um). Alkaline buffer (pH 9.9). High-voltage electrical field separation. Detection via absorbance at 200 nm (deuterium lamp and LED). Automated sample dilution and mixing. RFID-tagged reagents and sample racks. Temperature control via Peltier device. PC interface with touchscreen.
Indications for Use
Indicated for qualitative detection and characterization of monoclonal proteins in human urine and serum samples. Used for patients suspected of having monoclonal gammopathies.
Regulatory Classification
Identification
An immunoglobulins A, G, M, D, and E immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the immunoglobulins A, G, M, D, an E (serum antibodies) in serum. Measurement of these immunoglobulins aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.
Predicate Devices
CAPILLARYS IMMUNOTYPING using the CAPILLARYS 2 (K130500)
CAPI 3 IMMUNOTYPING using the CAPILLARY 3 TERA INSTRUMENT (SERUM MATRIX) (K161928)
Submission Summary (Full Text)
{0}
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K192095
B Applicant
Sebia
C Proprietary and Established Names
CAPI 3 Immunotyping, Capillarys 3 Tera
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CFF | Class II | 21 CFR 866.5510 - Immunoglobulins A, G, M, D, And E Immunological Test System | IM - Immunology |
| DFH | Class II | 21 CFR 866.5550 - Immunoglobulin (light chain specific) immunological test system | IM - Immunology |
| DEH | Class II | 21 CFR 866.5550 - Immunoglobulin (light chain specific) immunological test system | IM - Immunology |
| CEF | Class I | 21 CFR 862.1630 - Protein (fractionation) test system | CH - Clinical Chemistry |
K192095 - Page 1 of 12
{1}
K192095 - Page 2 of 12
## II Submission/Device Overview:
### A Purpose for Submission:
Addition of a new matrix (urine) to a previously cleared device.
### B Measurand:
Monoclonal Immunoglobulins (IgG, IgA, IgM, Kappa, Lambda)
### C Type of Test:
Capillary Zone Electrophoresis
## III Intended Use/Indications for Use:
### A Intended Use(s):
See Indications for Use below.
### B Indication(s) for Use:
The CAPI 3 IMMUNOTYPING kit is designed for the qualitative detection and the characterization of monoclonal proteins (immunotyping) in human urine and serum with the CAPILLARYS 3 TERA instrument, SEBIA, for capillary electrophoresis. It is used in conjunction with the CAPI 3 PROTEIN(E) 6 kit, SEBIA, designed for proteins separation into 6 major fractions in alkaline buffer (pH 9.9). The CAPILLARYS 3 TERA instrument performs all procedural sequences automatically to obtain a protein profile for qualitative analysis. Each urine or serum sample is mixed with individual antisera that are specific against gamma (Ig G), alpha (Ig A) and mu (Ig M) heavy chains, and kappa (free and bound) light chains and lambda (free and bound) light chains, respectively. The proteins, separated in silica capillaries, are directly detected by their absorbance at 200 nm. The electrophoregrams are evaluated visually to detect the presence of specific reactions with the suspect monoclonal proteins. For In Vitro Diagnostic Use.
### C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
### D Special Instrument Requirements:
CAPILLARYS 3 TERA instrument
{2}
K192095 - Page 3 of 12
# IV Device/System Characteristics:
# A Device Description:
The CAPI 3 IMMUNOTYPING kit includes the following components:
Sample diluent
- Pierceable cap for the Sample diluent vial
- Rack with electrophoresis (ELP) solution and antiserum tubes
ELP solution
- Mammalian immunoglobulins antihuman gamma heavy chains
- Mammalian immunoglobulins antihuman alpha heavy chains
- Mammalian immunoglobulins antihuman mu heavy chains
- Mammalian immunoglobulins antihuman kappa (free and bound) light chains
- Mammalian immunoglobulins antihuman lambda (free and bound) light chains
# B Principle of Operation:
The CAPILLARYS 3 TERA instrument uses the principle of capillary electrophoresis in a liquid medium. With this technique, charged molecules are separated by their electrophoretic mobility in an alkaline buffer with a specific pH. Protein separation is performed in a high voltage electrical field. The separated proteins are directly detected using absorbance at $200\mathrm{nm}$ at the cathodic end of the capillary. Separation occurs according to the electrolyte $\mathsf{pH}$ and is driven by electroosmotic flow. The CAPILLARYS 3 TERA instrument has silica capillaries functioning in parallel allowing 12 simultaneous analyses.
With the CAPI 3 IMMUNOTYPING procedure, the immunotyping using specific antibodies is performed to identify abnormal fractions in serum or urine protein profiles through a process called Immunofixation by Subtraction (Immunotyping). Here, the addition of immunoglobulin class specific antisera to the patient sample causes a shift in the electrophoretic mobility of the specific peaks, allowing the identification of the class of the aberrant peak.
C Instrument Description Information:
| Modes of Operation | Yes | No |
| --- | --- | --- |
| Does the applicant's device contain the ability to transmit data to a computer, webserver, or mobile device? | ☑ | ☐ |
| Does the applicant's device transmit data to a computer, webserver, or mobile device using wireless transmission? | ☐ | ☑ |
| Software | | |
| FDA has reviewed applicant's Hazard Analysis and software development processes for this line of product types. | ☑ | ☐ |
{3}
V Substantial Equivalence Information:
A Predicate Device Name(s):
Capillary Immunotyping, Capillary 2 Instrument, IT/IF Control, Capillary 2 Flex Piercing Instrument
CAPI 3 Immunotyping, Capillary 3 Tera, IT/IF Control
B Predicate 510(k) Number(s):
K130500
K161928
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K192095 | K130500 | K161928 |
| --- | --- | --- | --- |
| Device Trade Name | IMMUNOTYPING, CAPILLARYS 3 TERA, IT/IF Control | CAPILLARYS IMMUNOTYPING and IT/IF Control using the CAPILLARYS 2 Instrument and CAPILLARYS 2 FLEX-PIERCING Instrument | CAPI 3 IMMUNOTYPING, CAPILLARYS 3 TERA, IT/IF Control |
| General Device Characteristic Similarities | | | |
| Intended Use/Indications For Use | The CAPI 3 IMMUNOTYPING kit is designed for the qualitative detection and the characterization of monoclonal proteins (immunotyping) in human urine and serum with the CAPILLARYS 3 TERA instrument, SEBIA, for capillary electrophoresis. It is used in conjunction with the CAPI 3 PROTEIN(E) 6 kit, SEBIA, designed for proteins separation into 6 major fractions in alkaline buffer (pH 9.9). The CAPILLARYS 3 TERA instrument performs all procedural sequences automatically | The CAPILLARYS IMMUNOTYPING kit is designed for the detection and characterization of monoclonal proteins (immunotyping) in human urine and serum with the CAPILLARYS, the CAPILLARYS 2 and the CAPILLARYS 2 FLEX-PIERCING, SEBIA, for capillary electrophoresis. It is used in conjunction with the SEBIA CAPILLARYS PROTEIN(E) 6 kit, designed for protein separation into 6 major fractions in alkaline buffer (pH 10.0). The CAPILLARYS, | The CAPI 3 IMMUNOTYPING kit is designed for the qualitative detection and characterization of monoclonal proteins (immunotyping) in human serum with the CAPILLARYS 3 TERA instrument, SEBIA, for capillary electrophoresis. It is used in conjunction with CAPI 3 PROTEIN(E) 6 kit, SEBIA, designed for protein separation into 6 major fractions in alkaline buffer (pH 9.9). The CAPILLARYS 3 TERA instrument performs all procedural sequences automatically to obtain a protein |
K192095 - Page 4 of 12
{4}
K192095 - Page 5 of 12
| | to obtain a protein profile for qualitative analysis. Each urine or serum sample is mixed with individual antisera that are specific against gamma (Ig G), alpha (Ig A) and mu (Ig M) heavy chains, and kappa (free and bound) light chains and lambda (free and bound) light chains, respectively.
The proteins, separated in silica capillaries, are directly detected by their absorbance at 200 nm.
The electropherograms are evaluated visually to detect the presence of specific reactions with the suspect monoclonal proteins.
For In Vitro Diagnostic Use. | CAPILLARYS 2 and the CAPILLARYS 2 FLEX-PIERCING perform all procedural sequences automatically to obtain a protein profile for qualitative analysis. Each urine or serum sample is mixed with individual antisera that are specific against gamma (Ig G), alpha (Ig A) and mu (Ig M) heavy chains, and kappa (free and bound) light chains and lambda (free and bound) light chains, respectively.
The proteins, separated in silica capillaries, are directly detected by their absorbance at 200 nm.
The electropherograms are evaluated visually to detect the presence of specific reactions with the suspect monoclonal proteins.
For In Vitro Diagnostic Use. | profile for qualitative analysis. Each serum sample is mixed with individual antisera that are specific against gamma (Ig G), alpha (Ig A) and mu (Ig M) heavy chains, and kappa (free and bound) light chains and lambda (free and bound) light chains, respectively.
The proteins, separated in silica capillaries, are directly detected by their absorbance at 200 nm.
The electropherograms are evaluated visually to detect the presence of specific reactions with the suspect monoclonal proteins.
For In Vitro Diagnostic Use. |
| --- | --- | --- | --- |
| Quality Control | The IT/IF Control | The IT/IF Control is designed to quality control the qualitative detection and characterization of human monoclonal immunoglobulins (Ig G, Ig A, Ig M, Kappa and Lambda) with the electrophoresis methods:
- Immunotyping performed using capillary electrophoresis on SEBIA CAPILLARYS 2 and CAPILLARYS 2 FLEX | The IT/IF Control is designed to quality control the qualitative detection and characterization of human monoclonal immunoglobulins (IgG, IgA, IgM, Kappa and Lambda) with the electrophoresis methods:
- Immunotyping performed using capillary electrophoresis on SEBIA CAPILLARYS 2, CAPILLARYS 2 FLEX-PIERCING and CAPILLARYS 3 TERA instruments and on SEBIA MINICAP |
{5}
K192095 - Page 6 of 12
| | | PIERCING instruments and on SEBIA MINICAP instrument, - Immunofixation methods: SEBIA HYDRAGEL IF, HYDRAGEL IF Penta, HYDRAGEL BENCE JONES (Standard mask and Dynamic mask) performed using the HYDRASYS and HYDRASYS 2 instruments and the K20 electrophoresis chamber. The IT / IF Control is designed for laboratory use. It should be used (with its barcode label for MINICAP procedure) like a human serum sample. The electrophoretic pattern obtained is specific for each batch of IT/IF control. For In Vitro Diagnostic Use. | instrument, - Immunofixation methods: SEBIA HYDRAGEL IF, HYDRAGEL IF Penta, HYDRAGEL BENCE JONES (Standard mask and Dynamic mask) performed using the HYDRASYS and HYDRASYS 2 instruments and the K20 electrophoresis chamber. The IT/IF Control is designed for laboratory use. It should be used (with its barcode label for CAPILLARYS and MINICAP procedure) like a human serum sample. The electrophoretic pattern obtained is specific for each batch of IT/IF control. For In Vitro Diagnostic Use. |
| --- | --- | --- | --- |
| Separation system | Free solution capillary electrophoresis (FSCE): protein separation in an alkaline buffer (pH 9.9) according to their charge, to the electrolyte pH and electroosmotic flow. Provides fast separation and good resolution. Electrophoregrams show separated fractions according to their charge. | Same | Same |
| Sample Type | Serum and Urine | Same | Serum |
| Results | Qualitative | Same | Same |
| Reagent | Mammalian | Same | Same |
{6}
| | immunoglobulins anti-human gamma heavy chains, mammalian immunoglobulins antihuman alpha heavy chains, mammalian immunoglobulins antihuman mu heavy chains, mammalian immunoglobulins anti-human kappa (free and bound) light chains, mammalian immunoglobulins antihuman lambda (free and bound) light chains | | |
| --- | --- | --- | --- |
| Sample Type | Serum and Urine | Same | Serum |
| Results | Qualitative | Same | Same |
| Reagent | Mammalian immunoglobulins anti-human gamma heavy chains, mammalian immunoglobulins antihuman alpha heavy chains, mammalian immunoglobulins antihuman mu heavy chains, mammalian immunoglobulins anti-human kappa (free and bound) light chains, mammalian immunoglobulins antihuman lambda (free and bound) light chains | Same | Same |
| Temperature Control | Peltier device | Same | Same |
| Software for data processing | SEBIA PHORESIS software | Same | Same |
| General Device Characteristic Differences | | | |
| Reagent format | CAPI 3 Immunotyping Kit: Sample diluent Rack with ELP solution tube and antiserum tube | CAPILLARYS IMMUNOTYPING Kit: Antisera segment containing ELP solution | One vial (lyophilized; 1.0 mL) |
| Instrument | SEBIA CAPILLARYS | SEBIA CAPILLARYS 2 | Same |
K192095 - Page 7 of 12
{7}
| | 3 TERA | FLEX-PIERCING
SEBIA CAPILLARYS 2 | |
| --- | --- | --- | --- |
| Analysis throughput | 21 analyses / 2 hours | 16 analyses / 2 hours | Same |
| Interface | PC interface + touch screen | PC interface | Same |
| Detection system | Deuterium lamp and LED | Deuterium lamp | Same |
| Firmware | Included into the instrument | Included into the
PHORESIS software | Same |
| Number of separation units | 12 parallel capillaries | 8 parallel capillaries | Same |
| Sample tubes | uncapped tubes or capped tubes depending on the procedure | Same | Same |
| Sample identification | Bar code reading on sample tubes and RFID labels on sample racks | Bar code reading on both sample racks and tubes | Same |
| Reagent identification | Yes (RFID labels on reagent vials) | No | Same |
| Introduction of the samples into the automatic system | Primary maximal capacity of 120 tubes (i.e. 15 sample racks), uninterrupted throughput on sample racks (8 positions available). | Primary capacity of 13 tubes for IT technique (i.e. 13 sample racks), uninterrupted throughput on sample racks. Only position 1 on the sample rack contains sample tube. | Same |
| Reagent bay: main compartment | Up to four analysis buffers or hemolysing solutions (identified by RFID labels); one waste container, one container for the wash solution | CAPILLARYS 2 : Contains one vial of water, wash solution and buffer container.
CAPILLARYS 2 FLEX-PIERCING : Contains one vial of water, wash solution, hemolyzing solution (for Hb and Hb A1c techniques) and buffer container. | Same |
| Reagent bay: secondary compartment | Up to 3 vials and 1 rack with immunotyping reagents (all RFID tagged) in temperature-controlled environment (< 15 °C); one RFID labeled vial and three tubes (for maintenance | N/A | Same |
K192095 - Page 8 of 12
{8}
K192095 - Page 9 of 12
VI Standards/Guidance Documents Referenced:
Not applicable
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
All results met the manufacturer’s pre-specified acceptance criteria.
Repeatability
Four different urine samples with monoclonal proteins including Bence Jones proteins were run using the CAPI 3 IMMUNOTYPING URINE procedure on all capillaries of the same CAPILLARYS 3 TERA instrument using one lot of CAPI 3 IMMUNOTYPING kit. The four samples included IgG-kappa, Lambda Free, IgM-kappa + kappa free, and IgA-Lambda + lambda free. Each sample was analyzed with each reagent in duplicate (ELP solution, Anti-Ig G, Anti-Ig A, Anti-Ig M, Anti-Kappa and Anti-Lambda using the 12 capillaries. In this study all dilution programs were tested. For each tested reagent, all samples gave concordant results within run and between capillaries.
Between-Instrument and Between-Lot Precision
Three different urine samples with monoclonal proteins including Bence Jones proteins were run using the CAPI 3 IMMUNOTYPING URINE procedure on three CAPILLARYS 3 TERA instruments and with three lots of CAPI 3 IMMUNOTYPING kit. The samples included one sample with two kappa free light chains, one sample with IgG-kappa immunoglobulin and one sample with Lambda free light chain. Each sample was analyzed on 18 runs over five working days (2 runs/day x 3 lots x 3 instruments = 18). In this study, all dilution programs were tested. All samples gave concordant results for all runs on the three CAPILLARYS 3 TERA instruments and with the three lots of CAPI 3 IMMUNOTYPING kit.
2. Linearity:
Not applicable, this is a qualitative test.
3. Analytical Specificity/Interference:
This clearance is for the addition of urine to the acceptable matrices for a previously cleared device, where specificity/interference was demonstrated in the original clearance (see K130500).
4. Assay Reportable Range:
Not applicable, this is a qualitative test.
{9}
K192095 - Page 10 of 12
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
No reference standards and methods available. Controls are internally manufactured by the manufacturer from myeloma serum samples with representative Immunoglobulin G with kappa light chain (IgGK), Immunoglobulin A with kappa light chain (IgAK), and Immunoglobulin M with lambda light chain (IgML) monoclonal proteins and are validated by both Immunofixation Gel Electrophoresis and Capillary Electrophoresis methods.
Stability: The manufacturer provided data to support real-time stability of two years and on-board stability of two months for the CAPI 3 IMMUNOTYPING Kit.
Sample Stability at 2–8°C
Ten urine samples, including normal and pathological urine samples, were analyzed at the beginning of the study (reference) and after one week storage at 2–8°C (test), with the CAPI 3 IMMUNOTYPING URINE procedure performed with the CAPILLARYS 3 TERA instrument. The results obtained comply with the acceptance criteria defined by SEBIA for the CAPI 3 IMMUNOTYPING URINE procedure performed with the CAPILLARYS 3 TERA instrument. Urine samples can be stored for one week between 2 and 8°C.
Stability –70 / –80°C
Eleven urine samples including normal and pathological urine samples were analyzed at the beginning of the study (reference) and after one month storage at –70 / –80°C (test), with the CAPI 3 IMMUNOTYPING URINE procedure performed with the CAPILLARYS 3 TERA instrument. The results obtained comply with the acceptance criteria defined by SEBIA for the CAPI 3 IMMUNOTYPING URINE procedure performed with the CAPILLARYS 3 TERA instrument. Urine samples can be stored for one month between –70 and –80°C.
6. Detection Limit:
Serial dilutions were prepared in normal urine with three pathological urine samples exhibiting monoclonal components and analyzed using the CAPI 3 IMMUNOTYPING URINE procedure. The results are summarized below:
| Sample | Type | Detection Limit mg/dL |
| --- | --- | --- |
| 1 | Lambda Free | 1.0 |
| 2 | Kappa Free | 3.0 |
| 3 | IgG (Lambda) | 0.4 |
| | Lambda | 0.4 |
7. Assay Cut-Off:
Not applicable.
{10}
K192095 - Page 11 of 12
# B Comparison Studies:
1. Method Comparison with Predicate Device:
The method comparison study included 52 urines samples composed of 8 urine samples without monoclonal component and 44 urine samples with monoclonal component including Bence Jones proteins. The samples were tested using the CAPI 3 IMMUNOTYPING URINE procedure performed with the CAPILLARYS 3 TERA instrument (test technique) and the CAPILLARYS IMMUNOTYPING URINE procedure performed with the CAPILLARYS 2 instrument (reference technique). All electropherograms were evaluated visually for the qualitative results. This study demonstrated a 100% agreement between the two techniques.
| Qualitative Results | Number of urine samples | Percent Agreement |
| --- | --- | --- |
| IgG Lambda | 5 | 100% |
| IgG Kappa | 2 | 100% |
| IgG Lambda with Lambda free | 4 | 100% |
| IgG Kappa with Kappa free | 2 | 100% |
| Lambda free | 19 | 100% |
| Kappa free | 8 | 100% |
| IgM Kappa with Kappa free | 2 | 100% |
| IgA Lambda | 1 | 100% |
| IgA Lambda with Lambda free | 1 | 100% |
| Without Monoclonal | 8 | 100% |
| Grand Total | 52 | 100% |
2. Matrix Comparison:
Not applicable, the results in urine are not directly comparable to serum.
C Clinical Studies:
1. Clinical Sensitivity:
Not applicable, clinical studies were not required for the addition of this matrix.
2. Clinical Specificity:
Not applicable, clinical studies were not required for the addition of this matrix.
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
D Clinical Cut-Off:
Not applicable, this is a qualitative test.
E Expected Values/Reference Range:
Absence of monoclonal immunoglobulins in apparently healthy individuals
{11}
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K192095 - Page 12 of 12
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.