The CAPILLARYS NEONAT Hb kit is designed for the separation of the normal hemoglobins (F and A) in blood samples from human new-borns, and for the major hemoglobin vanants (S, C, E, D and Bart's), by electrophoresis in alkaline buffer (pH 9.4) with the CAPILLARYS 2 System. The CAPILLARYS NEONAT Hb kit is designed for laboratory use. The CAPILLARYS 2 is an automated analyzer which performs a complete hemoglobin profile for the qualitative analysis of hemoglobins. The assay is performed on the hemolysate of whole blood samples previously collected on filter paper. For In Vitro Diagnostic Use. The Hb AF Control is designed: - for the migration control before starting a new analysis sequence and for the qualitative quality control, for human hemoglobins A and F with the SEBIA CAPILLARYS NEONAT Hb electrophoresis procedure used with the CAPILLARYS 2 system, and, - for the quantitative quality control for detection of the human hemoglobins A, F and A2 with the SEBIA electrophoresis procedures : HYDRAGEL HEMOGLOBIN(E) used with the HYDRASYS system, CAPILLARYS HEMOGLOBIN(E) used with the CAPILLARYS system and MINICAP HEMOGLOBIN(E) used with the MINICAP system. The Hb AF Control is designed for laboratory use. It should be used (with its bar code label for the CAPILLARYS and MINICAP procedures) like a normal human blood. The values obtained must fall within the range provided with each batch of Hb AF Control. For In Vitro Diagnostic Use.
Device Story
Device uses capillary electrophoresis to separate hemoglobin variants in newborn blood samples. Input: whole blood samples on filter paper (Guthrie cards). Process: samples diluted in hemolyzing solution; injected into silica capillaries; high-voltage separation in alkaline buffer (pH 9.4); direct detection at 415 nm. Output: electrophoregrams displayed on CAPILLARYS 2 system screen. Used in clinical laboratories by technicians. Visual evaluation of electrophoregrams identifies hemoglobin patterns. Results aid in diagnosis of hemoglobinopathies. Benefits: automated, fast separation, high resolution compared to manual methods.
Clinical Evidence
No clinical data provided; device relies on bench testing and performance validation of the electrophoresis procedure for hemoglobin separation.
Technological Characteristics
Silica capillaries; alkaline buffer (pH 9.4); 415 nm absorbance detection; automated capillary electrophoresis; continuous loading with sample racks; barcode sample identification. Software-controlled automation of dilution, injection, migration, and detection.
Indications for Use
Indicated for qualitative screening of hemoglobin variants (F, A, S, C, E, D, Bart's) in newborns less than 2 weeks old using whole blood collected on filter paper.
Regulatory Classification
Identification
An abnormal hemoglobin assay is a device consisting of the reagents, apparatus, instrumentation, and controls necessary to isolate and identify abnormal genetically determined hemoglobin types.
Special Controls
*Classification.* Class II (special controls). A control intended for use with an abnormal hemoglobin assay is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 864.9.
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k091283
B. Purpose for Submission:
New Device
C. Measurand:
Hemoglobin variants F, A, S, C, E, D and Bart's
D. Type of Test:
Qualitative, Hemoglobin Electrophoresis
E. Applicant:
Sebia, Inc.
F. Proprietary and Established Names:
CAPILLARYS NEONAT Hb Kit
Hb AF Control
G. Regulatory Information:
1. Regulation section:
21 CFR 864.7415 - Abnormal Hemoglobin Assay
21 CFR 866.7415 - Abnormal Hemoglobin Control
2. Classification:
Class II
3. Product code:
GKA - Abnormal Hemoglobin Quantitation
JCM - Control, Hemoglobin, Abnormal
4. Panel:
Hematology (81)
H. Intended Use:
1. Intended use(s):
CAPILLARYS NEONAT Hb Kit
The CAPILLARYS NEONAT Hb kit is designed for the separation of the normal hemoglobins (F and A) in blood samples from human newborns, and for the detection of the major hemoglobin variants (S, C, E, D and Bart's), by electrophoresis in alkaline buffer (pH 9.4) with the CAPILLARYS 2 system. The CAPILLARYS NEONAT Hb kit is designed for laboratory use.
The CAPILLARYS 2 is an automated analyzer which performs a complete hemoglobin profile for the qualitative analysis of hemoglobins. The assay is performed on the hemolysate of whole blood samples previously collected on filter paper.
Hb AF Control
The Hb AF Control is designed for the migration control before starting a new analysis sequence and for the qualitative quality control, for human hemoglobins A and F with the SEBIA CAPILLARYS NEONAT Hb electrophoresis procedure used with the CAPILLARYS 2 system, and for the quantitative quality control detection of human hemoglobins A, F, and A2 with the SEBIA electrophoresis procedures: HYDRAGEL HEMOGLBIN(E) used with the HYDRASYS system, CAPILLARYS HEMOGLBIN(E)
{1}
used with the CAPILLARYS system and MINICAP HEMOGLOBIN(E) used with the MINICAP system.
The Hb AF Control is designed for laboratory use. It should be used (with its bar code label for the CAPILLARYS and MINICAP procedures) like a normal human blood. The values obtained must fall within the range provided with each batch of Hb AF Control.
For In Vitro Diagnostic Use.
2. Indication(s) for use:
Same as Intended Use
3. Special conditions for use statement(s):
For Prescriptive Use Only
4. Special instrument requirements:
For use with the CAPILLARYS 2 System
I. Device Description:
The CAPILLARYS NEONAT Hb kit consists of five components; (1) CAPILLARYS NEONAT Hb buffer contains alkaline buffer (pH 9.4), supplied in 700 mL vials, (2) Hemolyzing Solution, supplied in 70 mL vials, (3) Washing Solution, supplied in 75 mL vials, (4) Dilution segments, supplied in pack of 110, (5) Filters, three per kit.
The CAPILLARYS NEONAT Hb kit is used in conjunction with the Sebia CAPILLARYS 2 system where silica capillaries are utilized for analyzing. The hemoglobin, separated in capillaries, is directly detected at an absorbance wave length of 415 nm, resulting in electrophoregrams. The electrophoregrams are evaluated visually for pattern abnormalities. Two procedures are available for the operator: the CAPILLARYS NEONAT Hb procedure and, the CAPILLARYS NEONAT Hb FAST procedure. The CAPILLARYS NEONAT Hb FAST procedure is characterized by enhanced analyses throughput, and it must be performed only with a CAPILLARYS 2 System adapted to this procedure and with the specific NEONAT Hb sample racks.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Perkin Elmer RESOLVE® Hemoglobin Kit
BIO-RAD VARIANT™ nbs Sickle Cell Program Kit
2. Predicate K number(s):
K050709
K051072
3. Comparison with predicate:
{2}
| Similarities | | | |
| --- | --- | --- | --- |
| Item | CAPILLARYS NEONAT Hb Kit | Perkin Elmer RESOLVE® Hemoglobin Kit | BIO-RAD VARIANT™ nbs Sickle Cell Program Kit |
| Intended Use | The CAPILLARYS NEONAT Hb kit is designed for the separation of the normal hemoglobins (F and A) in blood samples from human newborns, and for the detection of the major hemoglobin variants (S, C, E, 0 and Bart's), by electrophoresis in alkaline buffer (pH 9.4) with the CAPILLARYS 2 system. The CAPILLARYS NEONAT Hb kit is designed for laboratory use. The CAPILLARYS 2 is an automated analyzer which performs a complete hemoglobin profile for the qualitative analysis of hemoglobins. The assay is performed on the hemolysate of whole blood samples previously collected on filter paper. For In Vitro Diagnostic Use. | The RESOLVE® Hemoglobin Kit is designed to separate whole blood and cord blood samples for detection of normal and variant hemoglobins by isoelectric focusing. The kit is designed to be run on a flat-bed electrofocusing unit such as the Multiphor II Electrofocusing Unit. The assay is intended for use as an aid in the diagnosis of neonatal and adult hemoglobinopathies. | Bio-Rad VARIANT™ nbs Sickle Cell Program Kit is intended as a qualitative screen for the presence of hemoglobins F, A, S, D, C, and E in elutes of neonatal blood collected on filter paper by high-performance liquid chromatography (HPLC). Bio-Rad VARIANT™ nbs Sickle Cell Program Kit is intended for Professional Use Only. Bio-Rad VARIANT™ nbs Sickle Cell Program Kit is for use only with the Bio-Rad VARIANT™ nbs Newborn Screening System. |
| Sample type | Blood samples from human newborn less than 2 weeks old | Same | Same |
| Absorbance wavelength | 415 nm | | Same |
| Sample Identification | YES | | YES |
| Sample Introduction | Continuous loading with sample racks | | Sequential injection |
| Differences | | | |
| --- | --- | --- | --- |
| Item | CAPILLARYS NEONAT Hb Kit | Perkin Elmer RESOLVE® Hemoglobin Kit | BIO-RAD VARIANT™ nbs Sickle Cell Program Kit |
| Instrument | CAPILLARYS 2 | Multiphor II Electrofocusing Unit | Bio-Rad VARIANT™ nbs Newborn Screening System. |
| Separation System | Capillary Electrophoresis | Isoelectric Focusing | HPLC |
| Absorbance | 415 nm | 540 nm (stained gels) | |
{3}
| Differences | | | |
| --- | --- | --- | --- |
| Item | CAPILLARYS NEONAT
Hb Kit | Perkin Elmer
RESOLVE®
Hemoglobin Kit | BIO-RAD VARIANT™
nbs Sickle Cell Program
Kit |
| wavelength | | | |
| Sample
Identification | YES | NO | |
| Sample
Introduction | Continuous loading with
sample racks | Manual dispense into the
wells. | |
## K. Standard/Guidance Document Referenced (if applicable):
CLSI LA4-A5, Blood Collection on Filter Paper for Newborn Screening Programs; Approved Standard - Fifth Edition, 2007.
## L. Test Principle:
Hemoglobin is complex molecule composed of two pairs of polypeptide chains. Each chain is linked to the heme, a tetrapyrrotic nucleus (porphyrins) which chelates an iron atom. The heme part is common in all hemoglobins and their variants. The type of hemoglobin is determined by the protein part called globin. Polypeptides chains $\alpha$, $\beta$, $\delta$, and $\gamma$ constitute the normal human hemoglobins:
- hemoglobin A = $\alpha$ 2 $\beta$ 2
- hemoglobin A2 = $\alpha$ 2 $\delta$ 2
- fetal hemoglobin F = $\alpha$ 2 $\gamma$ 2
The $\alpha$-chain is common to these three hemoglobins.
The hemoglobin spatial structure and other molecular properties depend on the nature and the sequence of the amino acids constituting the chains. Substitution of amino acids by mutation is responsible for formation of hemoglobin variants which have different surface charge and consequently, different electrophoretic mobilities, which also depend on the pH and ionic strength of the buffer. The resulting qualitative abnormalities are called hemoglobinopathies. Decreased synthesis of one of the hemoglobin chains leads to qualitative abnormalities called thalassemias.
Hemoglobin electrophoresis is a well established technique routinely used in clinical laboratories for screening samples for hemoglobin abnormalities. The CAPILLARYS 2 System has been developed to provide complete automation of this testing with fast separation and good resolution. In many respects, the methodology can be considered as an intermediary type of technique between classical zone electrophoresis and liquid chromatography.
The CAPILLARYS 2 System uses the principle of capillary electrophoresis in free solution. With this technique, charged molecules are separated by their electrophoretic mobility in an alkaline buffer with a specific pH. Separation also occurs according to the electrolyte pH and electroosmotic flow. The CAPILLARYS 2 System has capillaries functioning in parallel allowing eight simultaneous analyses for hemoglobin quantification. A sample dilution with hemolyzing solution is prepared and injected by aspiration at the anodic end of the capillary. A high voltage protein separation is then performed and direct detection of the hemoglobins is made at $415\mathrm{nm}$ at the cathodic end of the capillary. Before each run, the capillaries are
{4}
washed with a Wash Solution and prepared for the next analysis with buffer. The hemoglobins, separated in silica capillaries, are directly and specifically detected at an absorbance wave length of 415 nm which is specific to hemoglobins. The resulting electrophoregrams are evaluated visually for pattern abnormalities.
By using alkaline pH buffer, normal and abnormal (or variant) hemoglobins are detected in the following order, from cathode to anode: C, A2/0-Arab, F-Ouled Rabah, E, S, D, G-Philadelphia, Korle-Bu, F, degraded F, A, degraded A and Bart's. Variants generated by the mutation of the γ-chain may appear in different zones of the electrophoretic pattern. The carbonic anhydrase is not visualized on the hemoglobin electrophoretic patterns with capillary electrophoresis.
Blood samples from few days old newborns and not transfused, do not present any hemoglobin A2, any variant of this hemoglobin, nor hemoglobin H (when present, they are at low concentration in the sample). These blood samples contain hemoglobin fractions associated to the γ chain, e.g., hemoglobin F, eventually some variants of this chain and hemoglobins due to post-traductional modifications, such as hemoglobin F1 (with acetylation of an amino acid in the γ chain) which migrates at the same position of the degraded hemoglobin F.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Reproducibility within-run was determined when four different blood samples, two normal blood samples with Hb F and Hb A and two pathological samples with Hb S, Hb F and Hb A were run twice in eight capillaries using the CAPILLARYS NEONAT Hb Kit procedure (two lots). One CAPILLARYS 2 System was used for analysis with two lots of hemolyzing solution. All electrophoregrams were evaluated visually. All replicates gave concordant results and the patterns corresponded to the hemoglobin type of each tested sample.
Reproducibility between-run and lot-to-lot was determined when eight different blood samples were run using the CAPILLARYS NEONAT Hb Kit procedure with three lots of analysis buffer and hemolyzing solution. The analyzed samples included four normal samples with Hb A level and four samples with abnormal hemoglobins three samples with HbS and one sample with Hb Bart's). These samples were run three times simultaneously with each of three lots of buffer and hemolyzing solution. All electrophoregrams were evaluated visually. All replicates gave concordant results between-runs and lot-to-lot. The patterns corresponded to the hemoglobin type of each tested sample.
SEBIA Hb AF Control (within-run, between-run and lot-to-lot):
The SEBIA Hb AF Control was run using the CAPILLARYS NEONAT Hb Kit procedure (two lots, including the same lot of analysis buffer and two different lots of hemolyzing solution). The sample was run eight times with each of the two lots of kits. All repeats gave concordant results within-run, between-run and lot-to-lot with the two lots of kits representing 16 analysis of the AF Control; no differences were observed among the replicates and the patterns corresponded to the type of the tested, Hb AF Control. All electrophoregrams were evaluated visually.
{5}
b. Linearity/assay reportable range:
Not applicable.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Blood Samples Stability: The stability of blood samples collected on filter paper punches was determined by a concordance study between the test CAPILLARYS NEONAT Hb Kit procedure and the reference HPLC procedure. Fifty-two (52) different blood samples (31 normals and 21 pathological) from newborns were collected and analyzed. The HPLC procedure was performed on 11 to 30 day old blood samples and the analyses of the same samples was performed with the CAPILLARYS NEONAT Hb Kit procedure on 15 to 102 day old samples. The results of this study concluded that blood samples collected on filter paper punches may be stored for up to one (1) month refrigerated (2 to 8°C), and up to 15 days at room temperature (15 to 30°C) before analysis with CAPILLARYS NEONAT Hb procedure.
SEBIA Hb AF Control is obtained from a pool of normal blood samples and from newborn umbilical cord blood samples. Certificate of Analysis (COA) forms were provided both types of samples.
SEBIA Hb AF Control Stability: Reconstituted Hb AF Control storage was determined to be 1 week at 2 - 8 °C and 3 months storage at -20 °C. The stability study was conducted on two lots, run eight times, from 1-6 months, and was compared to a reconstituted Hb AF control stored at -20°C, and a reference Hb AF control.
A realtime stability of the freeze-dried Hb AF Control was determined on one lot, run eight times and stored at 2 - 8 °C, from 1 week to 24 months. This study and accelerated aging determined that the freeze-dried control is stable until the expiration date on the label.
d. Detection limit:
CAPILLARYS NEONAT Hb assay is a qualitative test and no limit of detection has been determined. However, when comparing this test to the reference HPLC in sensitivity study CAPILLARYS NEONAT Hb showed an equivalent performance:
- 1.1% for the Hb S fraction
- 2.3% for the Hb C fraction
- 1.1% for the Hb E fraction
e. Analytical specificity:
An interference study was performed to verify that triglycerides in a blood sample do not interfere in the analysis with CAPILLARYS NEONAT Hb procedure. This study was performed on a normal blood sample with Hb A and Hb F and a pathological sample (with Hb A, F and S). The results obtained indicated that the presence of triglycerides does not interfere in the CAPILLARYS NEONAT Hb analysis until a triglyceride concentration of 28.4 g/L, or 32 μM.
An interference study was performed to verify that bilirubin in a blood sample does not interfere in the analysis with CAPILLARYS NEONAT Hb procedure. This study was performed on a normal blood sample with Hb A and Hb F. The results obtained indicated that the presence of bilirubin does not interfere in the CAPILLARYS NEONAT Hb analysis until a bilirubin concentration of 123 mg/L, or 210 μM.
6
{6}
f. Assay cut-off:
Not applicable.
2. Comparison studies:
a. Method comparison with predicate device:
Comparison studies were performed at one internal site and three external sites.
Internal Site:
One hundred and twenty (120) different blood samples (50 normal blood samples and 70 pathological blood samples with hemoglobin variants, (hemoglobins S, C, E and Bart's) were analyzed with the CAPILLARYS NEONAT Hb procedure and with a reference procedure, including iso-electrofocusing on polyacrylamide gels for all samples and a second analysis with HPLC system for samples exhibiting abnormal hemoglobins. All abnormal hemoglobins detected with the CAPILLARYS NEONAT Hb procedure were in 100 % agreement with the comparative HPLC system. There was no case observed of false positive.
External Sites: Studies were performed in two sites located in Europe (United Kingdom and Spain) and one located in the USA. The diagnosis was based on a routine HPLC.
In the United Kingdom, 126 different blood samples (49 normal samples and 77 pathological samples with abnormal hemoglobins) were analyzed. In Spain, 131 different blood samples (37 normal samples and 94 pathological samples) were analyzed. In the USA, 50 different blood samples (16 normal samples and 34 pathological samples) were analyzed. In these three external studies, all normal samples had normal hemoglobins Hb A and Hb F and all pathological samples had abnormal hemoglobins, Hb S, C, D, E and Bart's. All samples were analyzed with the CAPILLARYS NEONAT Hb procedure and a commercially available HPLC system. They were treated strictly according to the operating procedures recommended by the manufacturers of the analysis systems and following the same guidelines in regards to sample integrity. All abnormal hemoglobins detected with CAPILLARYS NEONAT Hb procedure were in agreement with the comparative HPLC system, hospital results and clinical diagnosis. There was no case reported as false positive (i.e., detection of abnormal hemoglobin where no such abnormality existed) as well as no case reported as false negative. There was 100% agreement between the two methods.
b. Matrix comparison:
Not applicable
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
Not applicable
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Not applicable.
{7}
8
N. Instrument Name:
Sebia, CAPILLARYS 2
O. System Descriptions:
1. Modes of Operation:
Open tube batch mode with the following sequence of automated steps:
- Bar code reading of sample racks
- Samples are diluted in hemolyzing solution and the sample probe is rinsed after each sample
- Capillary washing
- Samples are incubated with the hemolyzing solution for 7 minutes
- Dilution sample is injected into capillaries
- Migration is carried out under constant voltage for about 7 minutes
- Hemoglobins are detected directly by reading at 415 nm and an electrophoretic profile appears on the screen of the system
Two procedures are available with the CAPILLAYS 2 system: NEONAT Hb and NEONAT Hb FAST. Each type of analysis has pre-programmed setting and cycles, and the progress of the analyses is permanently displayed on a screen. The difference is that the NEONAT Hb FAST procedure allows the instrument to run two segments in parallel. This procedure also has specific NEONAT Hb sample racks for blood sample analysis. The throughput is 50 analyses per/hour instead of 28 analyses per/ hour with the NEONAT Hb procedure.
2. Software:
The "PHORESIS" operating system software is designed to work with the instrumentation, CAPILLARYS 2. The CAPILLARYS 2 instrumentation directed by the software is a fully automated in the performance of the sample identification by barcode labeling, dilution, testing, and calculation of results.
FDA has reviewed applicant's Hazard Analysis and software development processes for this line of product types:
Yes ☐ X or No ☐
3. Specimen Identification:
Bar Code reader
4. Specimen Sampling and Handling:
The analysis is performed on whole blood samples from newborns less than two weeks old, collected on Guthrie cards (such as Whatman cards for neonatal sample collection) and dried for a minimum of 4 hours at room temperature (15°-30°C). Guthrie cards with dried collected samples are stored at 2 - 8°C, away from light and humidity.
A dilution segment is placed on the segment holder and 50 μL of distilled or deionized water is applied into each of the eight wells of the dilution segment. Filter paper punches with dried blood samples are placed into the wells for analysis.
5. Calibration:
Not applicable
6. Quality Control:
It is necessary to run two analysis sequences with the Hb AF Control (SEBIA) after having changed the analysis buffer vial (even if the lot numbers is unchanged) or the technique, after a capillary cleaning sequence or after capillaries activation, and before starting a new analysis. It is also advised to include into each run of samples, an assayed
{8}
control blood (i.e. containing hemoglobins A, F, C, and S, Hb AFSC Control, SEBIA).
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above.
None
Q. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
R. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
9
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.