K123274 · Gen-Probe Prodesse, Inc. · PCH · Jan 16, 2013 · Microbiology
Device Facts
Record ID
K123274
Device Name
PROGASTRO SSCS ASSAY
Applicant
Gen-Probe Prodesse, Inc.
Product Code
PCH · Microbiology
Decision Date
Jan 16, 2013
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.3990
Device Class
Class 2
Attributes
Real-World Evidence, Pediatric
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K123274 · Jan 16, 2013
PROGASTRO SSCS ASSAY
Gen-Probe Prodesse, Inc.
Retrospective clinical stool samples; Routine clinical laboratory records (culture and broth enrichment/EIA results)
Retrospective clinical samples were used to supplement the prospective clinical trial data to establish the performance (positive and negative percent agreement) of the ProGastro SSCS Assay compared to standard-of-care reference methods.
Retrospective study; Clinical performance; Stool specimens; Routine clinical care
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Retrospective clinical performance evaluation; Study Period: 2007 - 2011
Symptomatic patients suspected of gastrointestinal infection; Sample Size: 105; Number of Sites: 2
Culture and/or Broth Enrichment/EIA
Positive and negative percent agreement
Indications for Use
The Prodesse® ProGastro SSCS Assay is a multiplex real time PCR in vitro diagnostic test for the qualitative detection and differentiation of Salmonella, Shigella, and Campylobacter (C. jejuni and C. coli only, undifferentiated) nucleic acids and Shiga Toxin 1 (stxl) and Shiga Toxin 2 (stx2) genes. Shiga toxin producing E. coli (STEC) typically harbor one or both genes that encode for Shiga Toxins 1 and 2. Nucleic acids are isolated and purified from preserved stool specimens obtained from symptomatic patients exhibiting signs and symptoms of gastroenteritis. This test is intended for use, in conjunction with clinical presentation and epidemiological risk factors, as an aid in the differential diagnosis of Salmonella, Shigella, Campylobacter jejuni/Campylobacter coli, and STEC infections in humans. The results of this test should not be used as the sole basis for diagnosis, treatment, or other patient management decisions. Positive results do not rule out co-infection with other organisms that are not detected by this test, and may not be the sole or definitive cause of patient illness. Negative ProGastro SSCS Assay results in the setting of clinical illness compatible with gastroenteritis may be due to infection by pathogens that are not detected by this test or non-infectious causes such as ulcerative colitis, irritable bowel syndrome, or Crohn's disease.
Device Story
ProGastro SSCS Assay is a multiplex real-time PCR in vitro diagnostic test; detects/differentiates Salmonella, Shigella, Campylobacter (C. jejuni/C. coli), and STEC (stx1/stx2) genes. Input: nucleic acids isolated/purified from preserved stool specimens using bioMérieux NucliSENS easyMAG. Process: purified nucleic acids added to SSC and STEC supermixes containing target-specific primers/probes; amplification performed on Cepheid SmartCycler II. Principle: Taqman reagent chemistry; 5'-3' exonuclease activity of Taq polymerase cleaves dual-labeled probes, separating reporter dye from quencher to generate fluorescent signal. Output: real-time fluorescent intensity monitored per cycle; indicates presence of target DNA. Used in clinical laboratories by trained personnel. Results aid clinicians in differential diagnosis alongside clinical presentation/epidemiological factors; not for sole diagnostic use. Benefits: rapid, multiplexed identification of common gastrointestinal pathogens.
Clinical Evidence
Prospective (n=1139) and retrospective (n=105) clinical studies compared ProGastro SSCS Assay to culture (Campylobacter, Salmonella, Shigella) or broth enrichment/EIA (STEC). Prospective sensitivity: 100% (Campylobacter), 95.2% (Salmonella), 100% (Shigella), 100% (STEC). Specificity: 98.8% (Campylobacter), 99.1% (Salmonella), 99.5% (Shigella), 99.2% (STEC). Discrepant results resolved via bi-directional sequencing. Reproducibility and precision studies confirmed consistent performance across sites/operators.
Indicated for symptomatic patients of all ages exhibiting signs/symptoms of gastroenteritis to aid in differential diagnosis of Salmonella, Shigella, Campylobacter (C. jejuni/C. coli), and STEC (stx1/stx2) infections.
Regulatory Classification
Identification
A gastrointestinal microorganism multiplex nucleic acid-based assay is a qualitative in vitro diagnostic device intended to simultaneously detect and identify multiple gastrointestinal microbial nucleic acids extracted from human stool specimens. The device detects specific nucleic acid sequences for organism identification as well as for determining the presence of toxin genes. The detection and identification of a specific gastrointestinal microbial nucleic acid from individuals exhibiting signs and symptoms of gastrointestinal infection aids in the diagnosis of gastrointestinal infection when used in conjunction with clinical evaluation and other laboratory findings. A gastrointestinal microorganism multiplex nucleic acid-based assay also aids in the detection and identification of acute gastroenteritis in the context of outbreaks.
Special Controls
*Classification.* Class II (special controls). The special controls are set forth in FDA's guideline document entitled: “Class II Special Controls Guideline: Gastrointestinal Microorganism Multiplex Nucleic Acid-Based Assays for Detection and Identification of Microorganisms and Toxin Genes from Human Stool Specimens.” For availability of the guideline document, see § 866.1(e).
{0}------------------------------------------------
123274
Page 1 of 11
01/15/2013
Gen-Probe Prodesse, Inc. ProGastro Assay 510(k) Submission
### Attachment D 510(k) SUMMARY
### CONTACT
Karen Harrington, PhD Manager, Clinical Affairs Gen-Probe Prodesse. Inc. 20925 Crossroads Circle Waukesha, WI 53186
### NAME OF DEVICE
Trade Name: Regulation Number: Product Code:
ProGastro SSCS Assay 21 CFR 866.3990 PCH and PCI
### PREDICATE DEVICE
K121454 Luminex GPP Test
#### INTENDED USE
The Prodesse® ProGastro SSCS Assav is a multiplex real time PCR in vitro diagnostic test for the qualitative detection and differentiation of Salmonella, Shigella, and Campylobacter (C. jejimi and C. coli only, undifferentiated) nucleic acids and Shiga Toxin 1 (stxl) and Shiga Toxin 2 (stx2) genes. Shiga toxin producing E. coli (STEC) typically harbor one or both genes that encode for Shiga Toxins I and 2. Nucleic acids are isolated and purified from preserved stool specimens obtained from symptomatic patients exhibiting signs and symptoms of gastroenteritis. This test is intended for use, in conjunction with clinical presentation and epidemiological risk factors, as an aid in the differential diagnosis of Salmonella, Shigella, Campylobacter jejuni/Campylobacter coli, and STEC infections in humans.
The results of this test should not be used as the sole basis for diagnosis, treatment, or other patient management decisions. Positive results do not rule out co-infection with other organisms that are are not detected by this test, and may not be the sole or definitive cause of patient illness. Negative ProGastro SSCS Assay results in the setting of clinical illness compatible with gastroenteritis may be due to infection by pathogens that are not detected by this test or non-infectious causes such as ulcerative colitis, irritable bowel syndrome, or Crohn's disease.
#### PRODUCT DESCRIPTION
The ProGastro SSCS Assay enables detection and differentiation of Salmonella, Shigella, Campylobacter (C. jejuni and C. coli only, undifferentiated) and an Internal Control in the SSC Mix and Shiga Toxin Producing E. coli (STEC, stx1 and stx2 differentiated) and an Internal Control in the STEC Mix.
An overview of the procedure is as follows:
- 1. Collect raw stool specimens from symptomatic patients and place into Cary Blair Transport Medium or ParaPak C&S (C&S) Transport Medium .
- 2. Add the Gastro RNA/DNA Internal Control (GIC) to every sample to monitor for inhibitors present in the specimens.
- 3. Perform isolation and purification of nucleic acids using a NucliSENS easyMAG System and the
Gen-Probe Prodesse, Inc.
JAN 1 6 2013
{1}------------------------------------------------
Automated Magnetic Extraction Reagents (bioMérieux).
- 4. Add purified nucleic acids to the SSC Mix included in the ProGastro SSCS Assay Kit. The SSC Mix contains target-specific oligonucleotide primers and probes for detection of Salmonella, Shigella, and Campylobacter (C. jejuni and C. coli only). The primers and probes are complementary to highly conserved regions of genetic sequences for these organisms. The probes are dual-labeled with a reporter dye and a quencher (see table below).
- 5. Add purified nucleic acids to the STEC Mix included in the ProGastro SSCS Assay Kit. The STEC Mix contains target-specific oligonucleotide primers and probes for detection of Shiga Toxin 1 and 2 genes (stxl and stx2). The primers and probes are complementary to highly conserved regions of these genes. The probes are dual-labeled with a reporter dye and a quencher (see table below).
- 6. Perform amplification of DNA in a Cepheid SmartCycler II instrument. In this process, the probe anneals specifically to the template followed by primer extension and amplification. The ProGastro SSCS Assay is based on Tagman reagent chemistry, which utilizes the 5' - 3' exonuclease activity of Taq polymerase to cleave the probe thus separating the reporter dye from the quencher. This generates an increase in fluorescent signal upon excitation from a light source. With each cycle, additional reporter dye molecules are cleaved from their respective probes, further increasing fluorescent signal. The amount of fluorescence at any given cycle is dependent on the amount of amplification products present at that time. Fluorescent intensity is monitored during each PCR cycle by the real-time instrument.
| Supermix | Analyte | Gene Targeted | Probe Fluorophore | Absorbance Peak | Emission Peak | Instrument Channel |
|----------------------------|--------------------------------------------------|--------------------------------------|-------------------------|-----------------|---------------|--------------------|
| SSC Mix | Campylobacter<br>(C. jejuni and C.<br>coli only) | C. jejuni<br>glyA<br>C. coli<br>cadF | FAM | 495 nm | 520 nm | FAM |
| SSC Mix | Salmonella spp. | orgC | CAL Fluor<br>Orange 560 | 538 nm | 559 nm | TET |
| SSC Mix | Shigella spp. | ipaH | CAL Fluor<br>Red 610 | 590 nm | 610 nm | Texas Red |
| STEC Mix | Shiga Toxin 1 | stx1 | CAL Fluor<br>Orange 560 | 538 nm | 559 nm | TET |
| STEC Mix | Shiga Toxin 2 | stx2 | FAM | 495 nm | 520 nm | FAM |
| SSC Mix<br>and STEC<br>Mix | Internal Control | NA | Quasar 670 | 647 nm | 670 nm | Cy5 |
{2}------------------------------------------------
## SUBSTANTIAL EQUIVALENCE
| Similarities | | |
|---------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Element | Prodesse ProGastro SSCS (k123274) | Luminex xTAG GPP (k121454) |
| Organisms<br>Detected | Salmonella spp., Shigella spp.,<br>Campylobacter ( <i>C. jejuni</i> and <i>C. coli</i> ),<br>and STEC ( <i>stx1</i> and <i>stx2</i> genes) | Same<br>(See below for differences) |
| Analyte | DNA | Same<br>(See below for differences) |
| Technological<br>Principles | Multiplex nucleic acid | Same<br>(See below for differences) |
| Specimen<br>Types | Stool specimens | Same |
| User Complexity | High | Same |
| Sample<br>Preparation<br>Method | Up front sample processing is required<br>to extract nucleic acids | Same |
| Controls | Internal control in each sample.<br>External control processed with each<br>batch of samples. | Same |
| Differences | | |
| Element | Prodesse ProGastro SSCS (k123274) | Luminex xTAG GPP (k121454) |
| Organisms<br>Detected | (See above for similarities) | Can also detect and distinguish <i>C. lari</i> .<br>In addition, can detect and distinguish<br><i>Clostridium difficile</i> toxin A/B,<br><i>Cryptosporidium</i> ( <i>C. parvum</i> and <i>C.</i><br><i>hominis</i> only), <i>Escherichia coli</i> ( <i>E.</i><br><i>coli</i> ) O157, Enterotoxigenic <i>E. coli</i><br>(ETEC) LT/ST, <i>Giardia</i> ( <i>G. lamblia</i><br>only), Norovirus GI/GII, and<br>Rotavirus A. |
| Analyte | DNA | RNA/DNA |
| Technological<br>Principles | Real time multiplex PCR based on the<br>Taqman reagent chemistry | Multiplex RT-PCR and bead<br>hybridization followed by<br>Fluorescence-activated sorting of<br>labeled beads coupled to streptavidin-<br>conjugated biotinylated products |
| Instrumentation | Cepheid SmartCycler II | PCR Thermocycler and Luminex<br>100/200 system |
{3}------------------------------------------------
### Clinical Performance
### Prospective Study
The clinical performance of the ProGastro SSCS Assay was established during prospective studies at four U.S. clinical laboratories. Leftover stool samples were collected during July 2011 - November 2011 and May 2012 - July 2012 and tested during November 2011 thru August 2012. All specimens used in the study meeting the inclusion criteria represented excess remnants of stool specimens that were prospectively collected from symptomatic individuals suspected of gastrointestimal infection, and were submitted for routine care or analysis by each site, and that otherwise would have been discarded.
Demographic details for the patient population included in the prospective study are summarized in the following table.
| Sex | Number of Samples SSC Mix | Number of Samples STEC Mix |
|---------------|---------------------------|----------------------------|
| Male | 615/1214 (50.6%) | 615/1214 (50.6%) |
| Female | 581/1214 (47.9%) | 581/1214 (47.9%) |
| Unknown | 18/1214 (1.5%) | 18/1214 (1.5%) |
| Age (yrs) | | |
| ≤ 5 years | 378/1214 (31.1%) | 378/1214 (31.1%) |
| 6 - 18 years | 296/1214 (24.4%) | 296/1214 (24.4%) |
| 19 - 64 years | 357/1214 (29.4%) | 357/1214 (29.4%) |
| ≥ 65 years | 164/1214 (13.5%) | 164/1214 (13.5%) |
| Unknown | 19/1214 (1.6%) | 19/1214 (1.6%) |
Performance of the ProGastro SSCS Assay was assessed and compared to the reference method of culture (Campylobacter, Salmonella, and Shigella) or broth enrichment followed by FDA cleared EIA test (Shiga Toxin producing E. coli). Samples positive for STEC by broth/EIA and/or the ProGastro SSCS Assay underwent PCR followed by bi-directional sequencing to confirm the presence of the stx 1 and/or stx2 genes. Two PCR/sequencing assays were used that each targeted different regions of the stxl or stx2 gene than the ProGastro SSCS Assay. "True" STEC positives were considered as any sample that tested positive for STEC by the broth/ElA method, and "True" STEC negatives were considered as any sample that tested negative for STEC by the broth/EIA method. "True" stx2 positives were considered as any sample that tested positive for STEC by the broth/E/A method and by PCR/sequencing. Bi-directional sequencing data was required to meet pre-defined quality acceptance criteria for both the forward and the reverse sequences that matched stx1 or stx2 sequences deposited in the National Center for Biotechnology Information (NCBI) GenBank database (www.ncbi.nlm.nih.gov), respectively, with acceptable E-values. The E-Value from NCBI BLAST Alignment indicates the statistical significance of a given pair-wise alignment and reflects the size of the database and the scoring system used. The lower the E-Value, the more significant the hit is. A sequence alignment that has an E-Value of le-3 means that this similarity has a 1 in 1000 chance of occurring by chance alone. (http://www.ncbi.nlm.nih.gov/books/bv.fcgi?rid=handbook.section.614).
Discrepant results between the ProGastro SSCS Assav and the reference methods were also evaluated using analytically validated PCR/sequencing assays and results are footnoted in the performance tables below.
{4}------------------------------------------------
A total of 1214 patients were initially enrolled in the prospective clinical trial. Prospective stool specimens were initially included in the prospective clinical trial. Sixty-one (61) patient/specimens were excluded from the performance calculations due to deviations from the clinical study protocol. Fourteen (14) specimens were excluded for the SSC Mix and 14 were excluded for the STEC Mix from the prospective clinical study data analysis because they remained "Unresolved" after repeat testing with the respective ProGastro SSCS Assay Mix. Unresolved results occur when the sample is negative for all target detections and the Internal Control, indicating potentially PCR-inhibited samples, This resulted in a total of 1139 eligible prospective specimens to be included in the prospective clinical study data analysis.
| | <i>Culture</i> | | | | |
|-------------------------------------|----------------|----------|-------|------|-----------------------------------------------|
| | Positive | Negative | Total | | |
| <i>ProGastro<br/>SSCS<br/>Assay</i> | Positive | 20 | 13a | 33 | Sensitivity 100.0%<br>(83.9% - 100.0%) 95% CI |
| | Negative | 0 | 1106 | 1106 | Specificity 98.8%<br>(98.0% - 99.3%) 95% CI |
| | Total | 20 | 1119 | 1139 | |
Campylobacter (C. jejuni / C. coli) Comparison Results
a Six (6) samples were positive for Campylobacter (C. coli or C. jejuni) by bi-directional sequence analysis.
### Salmonella Comparison Results
| | Culture | | | |
|----------------------------|----------|----------|-------|---------------------------------------------|
| | Positive | Negative | Total | |
| ProGastro<br>SSCS<br>Assay | 20 | 10a | 30 | Sensitivity 95.2%<br>(77.3% - 99.2%) 95% CI |
| | 1b | 1108 | 1109 | Specificity 99.1%<br>(98.4% - 99.5%) 95% CI |
| Total | 21 | 1118 | 1139 | |
a Ten (10) samples were positive for Salmonella by bi-directional sequence analysis.
Sample was positive for Salmonella by bi-directional sequence analysis.
### Shigella Comparison Results
| | Culture | | | | |
|----------------------------|----------|----------|-------|------|-----------------------------------------------|
| | Positive | Negative | Total | | |
| ProGastro<br>SSCS<br>Assay | Positive | 15 | 6a | 21 | Sensitivity 100.0%<br>(79.6% - 100.0%) 95% CI |
| | Negative | 0 | 1118 | 1118 | Specificity 99.5%<br>(98.8% - 99.8%) 95% CI |
| | Total | 15 | 1124 | 1139 | |
a Six (6) samples were positive for Shigella by bi-directional sequence analysis.
{5}------------------------------------------------
### STEC Comparison Results
| | Broth Enrichment/EIA | | | | |
|----------------------------|----------------------|----------|-------|-------------|-----------------------------------------------|
| | Positive | Negative | Total | | |
| ProGastro<br>SSCS<br>Assay | Positive | 9a | 9b | <b>18</b> | Sensitivity 100.0%<br>(70.1% - 100.0%) 95% CI |
| | Negative | 0 | 1121 | <b>1121</b> | Specificity 99.2%<br>(98.5% - 99.6%) 95% CI |
| | Total | 9 | 1130 | 1139 | |
a Six (6) samples positive for stx1, one (1) sample positive for stx2, and two (2) samples positive for stx1 and stx2 by bi-directional sequence analysis.
b Six (6) samples positive for stx1 and three (3) samples positive for stx2 by bi-directional sequence analysis.
### stx1 Comparison Results
| | Broth Enrichment/EIA and<br>sequencing for stx1 | | | | |
|-------------------------|-------------------------------------------------|----------|-------|----|-----------------------------------------------------------------|
| | Positive | Negative | Total | | |
| ProGastro<br>SSCS Assay | Positive | 8 | 6a | 14 | Positive Percent Agreement<br>100.0%<br>(67.6% - 100.0%) 95% CI |
| | Negative | 0 | 4 | 4 | Negative Percent Agreement 40.0%<br>(16.8% - 68.7%) 95% CI |
| | Total | 8 | 10 | 18 | |
4 Six (6) samples negative by broth/EIA, five (5) were positive for stx/by bi-directional sequencing, but were negative by Broth Enrichment/EIA.
### stx2 Comparison Results
| | Broth Enrichment/EIA<br>and sequencing for stx2 | | | | |
|-------------------------|-------------------------------------------------|----------|-------|----|-----------------------------------------------------------------|
| | Positive | Negative | Total | | |
| ProGastro<br>SSCS Assay | Positive | 3 | 3a | 6 | Positive Percent Agreement<br>100.0%<br>(43.9% - 100.0%) 95% CI |
| | Negative | 0 | 12 | 12 | Negative Percent Agreement 80.0%<br>(54.8% - 93.0%) 95% CI |
| | Total | 3 | 15 | 18 | |
4 Three (3) samples were positive for stx2 by bi-directional sequence analysis, but were negative by Broth Enrichment/EIA.
{6}------------------------------------------------
The ProGastro SSCS Assay detected one mixed infections in the prospective clinical evaluation. This represents 0.98% of the total positive specimens (1/102). The one mixed infections sample was double infections and was confirmed by the reference methods.
Distinct Co-infection Combinations Detected by the ProGastro SSCS Assay in the Prospective Clinical Trial
| Distinct Co-infection Combinations<br>Detected by ProGastro SSCS Assay | | | | | |
|------------------------------------------------------------------------|---------------|-----------|------------------------|-------------------------------------------|------------------------|
| Analyte 1 | Analyte 2 | Analyte 3 | Total<br>Co-infections | Number of<br>Discrepant<br>Co-infectionsa | Discrepant Analyte(s)a |
| Salmonella | Campylobacter | N/A | 0 | 0 | |
| Salmonella | Shigella | N/A | 0 | 0 | |
| Salmonella | STEC | N/A | 0 | 0 | |
| Campylobacter | Shigella | N/A | 0 | 0 | |
| Campylobacter | STEC | N/A | 1 | 0 | |
| STEC | Shigella | N/A | 0 | 0 | |
| Salmonella | Campylobacter | STEC | 0 | 0 | |
| Total Co-infections | | | 1 | 0 | |
| Total Double Infections | | | 1 | 0 | |
| Total Triple Infections | | | 0 | 0 | |
ª A discrepant co-infection or discrepant analyte was defined as one that was detected by the ProGastro SSCS Assay but not detected by the reference methods.
There were no co-infections that were detected by the reference method and not detected by the ProGastro SSCS Assay.
### Retrospective Study
In addition to the prospective clinical study, two clinical sites also performed testing using retrospective samples that were collected from 2007 - 2011. A total of 105 stool samples were included in the retrospective study. These samples had been previously determined to be positive or negative by culture and/or Broth Enrichment/ElA. The ProGastro SSCS Assay was compared to the same reference method that was employed for the prospective study to determine positive and negative percent agreement.
Demographic details for this patient population are summarized in the table below.
| Sex* | Number of Subjects |
|---------------|--------------------|
| Female | 24/55 (43.6%) |
| Male | 31/55 (56.4%) |
| Age | Number of Subjects |
| ≤ 5 years | 12/105 (11.4%) |
| 6 - 18 years | 24/105 (22.9%) |
| 19 – 64 years | 51/105 (48.6%) |
| ≥ 65 years | 18/105 (17.1%) |
*For all of the 50 specimens tested from one site the gender was unknown
{7}------------------------------------------------
Campylobacter Comparison Results
| | Culture | | | | |
|-------------------------|----------|----------|----------|-------|---------------------------------------------------------------|
| | | Positive | Negative | Total | |
| ProGastro<br>SSCS Assay | Positive | 27 | 5 | 32 | Positive Percent Agreement 96.4%<br>(82.3% - 99.4%) 95% CI |
| | Negative | 1 | 72 | 73 | Negative Percent Agreement<br>93.5%<br>(85.7% - 97.2%) 95% CI |
| | Total | 28 | 77 | 105 | |
### Salmonella Comparison Results
| | | | Culture | | | |
|-------------------------|----------|---|----------|----------|-------|-----------------------------------------------------------------|
| | | | Positive | Negative | Total | |
| ProGastro<br>SSCS Assay | Positive | 3 | 0 | 3 | | Positive Percent Agreement<br>100.0%<br>(43.4% - 100.0%) 95% CI |
| | Negative | 0 | 102 | 102 | | Negative Percent Agreement<br>100.0%<br>(96.4% - 100.0%) 95% CI |
| Total | | 3 | 102 | 105 | | |
### Shigella Comparison Results
| | | Culture | | | |
|-------------------------|----------|----------|----------|-------|-----------------------------------------------------------------|
| | | Positive | Negative | Total | |
| ProGastro<br>SSCS Assay | Positive | 4 | 0 | 4 | Positive Percent Agreement<br>100.0%<br>(51.0% - 100.0%) 95% CI |
| | Negative | 0 | 101 | 101 | Negative Percent Agreement<br>100.0%<br>(96.3% - 100.0%) 95% CI |
| Total | | 4 | 101 | 105 | |
### STEC Comparison Results
| | | | Culture or Broth Enrichment/EIA | | | | |
|----------------------------|----------|-------|---------------------------------|----------|-------|--------------------------------------------------------------|--|
| | | | Positive | Negative | Total | | |
| ProGastro<br>SSCS<br>Assay | Positive | | 19a | 0 | 19 | Positive Percent Agreement 100.0%<br>(83.2% - 100.0%) 95% CI | |
| | Negative | | 0 | 86 | 86 | Negative Percent Agreement 100.0%<br>(95.7% - 100.0%) 95% CI | |
| | | Total | 19 | 86 | 105 | | |
4 Five (5) samples positive for stx1, 5 samples positive for stx2, and 9 samples positive for stx1 and stx2.
{8}------------------------------------------------
### stx1 Comparison Results
| | Culture or Broth Enrichment/EIA<br>and sequencing for stx1 | | | | |
|----------------------------|------------------------------------------------------------|----------|----------|-------|--------------------------------------------------------------|
| ProGastro<br>SSCS<br>Assay | | Positive | Negative | Total | |
| | Positive | 14 | 0 | 14 | Positive Percent Agreement 100.0%<br>(78.5% - 100.0%) 95% CI |
| | Negative | 0 | 5 | 5 | Negative Percent Agreement 100.0%<br>(56.6% - 100.0%) 95% CI |
| | Total | 14 | 5 | 19 | |
### stx2 Comparison Results
| | | Culture or Broth Enrichment/EIA<br>and sequencing for stx2 | | | |
|----------------------------|----------|------------------------------------------------------------|----------|-------|--------------------------------------------------------------|
| | | Positive | Negative | Total | |
| ProGastro<br>SSCS<br>Assay | Positive | 14 | 0 | 14 | Positive Percent Agreement 100.0%<br>(78.5% - 100.0%) 95% CI |
| | Negative | 0 | 5 | 5 | Negative Percent Agreement 100.0%<br>(56.6% - 100.0%) 95% CI |
| | Total | 14 | 5 | 19 | |
Of the prospective and retrospective specimens run using the SSC Mix Assay, 98.0% (1233/1258) of these specimens were successful on the first attempt. The remaining 25 (25/1258 = 2.0%) gave "Unresolved" results on the first attempt. An "Unresolved" result is generated when the Gastro Internal Control (GIC) fails to be detected in a clinical specimen. A failure of the GIC to be detected can occur if inhibitors are present in a sample or due to technical error (e.g., GIC not added prior to nucleic acid extraction). Of the 25 "Unresolved" specimens on the first attempt with sufficient nucleic acid for retest, 44.0% (11/25) gave a valid result on the second attempt. The remaining 14 were "Unresolved" on the second attempt.
Of the prospective and retrospective specimens run using the STEC Mix Assay, 97.9% (1232/1258) of these specimens were successful on the first attempt. The remaining 26 (26/1258 = 2.1%) gave "Unresolved" results on the first attempt. Of the 26 "Unresolved" specimens on the first attempt with sufficient nucleic acid for retest, 48.0% (12/25) gave a valid result on the second attempt. The remaining 14 were "Unresolved" on the second attempt.
#### Reproducibility
The reproducibility of the ProGastro SSCS Assay was evaluated at three laboratory sites. Reproducibility was assessed using a panel of 15 simulated samples that included medium positive, low positive (near the assav limit of
detection, ≥ 95% positive), and high negative (below the assay limit of detection, ≤ 95% positive) samples for each of the assay targets. The reproducibility panel and controls were run with the ProGastro SSCS Assay (SSC and STEC Mixes) at three sites by each of two operators per site for five days.
{9}------------------------------------------------
### Page 10 of 11 01/15/2013
#### Reproducibility Panel Member Results
| | SSC Mix | | | | | | | | STEC Mix | | | | | | SSC STEC<br>Mix Mix | |
|--------|-----------------------------------------------|-------------------------------|----------------------------------|-----------------------------|--------------------------------|--------------------------------|--------------------------------------|------------------------------|---------------------------------|---------------------------|---------------------------------|---------------------------|---------------------------------|--------------------------------|--------------------------------|--|
| | Panel<br>Member ID | <i>C. jejuni</i> Low Positive | <i>C. jejuni</i> Medium Positive | <i>C. coli</i> Low Positive | <i>C. coli</i> Medium Positive | <i>Salmonella</i> Low Positive | <i>Salmonella</i> Medium<br>Positive | <i>Shigella</i> Low Positive | <i>Shigella</i> Medium Positive | STEC (stx 1) Low Positive | STEC (stx 1) Medium<br>Positive | STEC (stx 2) Low Positive | STEC (stx 2) Medium<br>Positive | High Negative (IC Ct<br>Value) | High Negative (IC Ct<br>Value) | |
| | Concentration | 20X*<br>LoD | 100X*<br>LoD | 6X*<br>LoD | 30X*<br>LoD | 2X<br>LoD | 10X<br>LoD | 2X<br>LoD | 10X<br>LoD | 2X<br>LoD | 10X<br>LoD | 2X<br>LoD | 10X<br>LoD | 0.0001X<br>LoD | | |
| | Agreement<br>with Expected<br>Result | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 90/90<br>100% | 90/90<br>100% | |
| Site 1 | Mean Ct Value | 37.6 | 35.2 | 35.9 | 33.5 | 35.9 | 33.2 | 35.8 | 33.2 | 36.1 | 33.4 | 36.7 | 34.5 | 33.6 | 33.2 | |
| | % CV | 3.5 | 3.0 | 3.9 | 3.7 | 1.4 | 1.2 | 1.7 | 1.4 | 2.0 | 1.6 | 1.8 | 1.3 | 3.0 | 1.7 | |
| | Agreement<br>with Expected<br>Result | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 29/30<br>96.7% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 90/90<br>100% | 90/90<br>100% | |
| Site 2 | Mean Ct Value | 37.3 | 34.8 | 35.8 | 33.4 | 36.0 | 33.1 | 35.6 | 33.2 | 36.2 | 33.6 | 36.8 | 34.7 | 33.3 | 33.0 | |
| | % CV | 3.0 | 2.8 | 3.1 | 3.2 | 1.7 | 1.6 | 1.9 | 1.8 | 2.5 | 1.6 | 1.9 | 1.9 | 0.9 | 0.9 | |
| | Agreement<br>with Expected<br>Result | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 30/30<br>100% | 90/90<br>100% | 90/90<br>100% | |
| Site 3 | Mean Ct Value | 37.0 | 34.4 | 35.2 | 32.9 | 35.7 | 32.7 | 35.0 | 32.8 | 35.6 | 33.1 | 36.5 | 34.2 | 32.9 | 32.6 | |
| | % CV | 2.6 | 2.2 | 2.1 | 1.9 | 1.4 | 1.2 | 1.8 | 1.3 | 1.7 | 1.3 | 1.6 | 1.0 | 0.8 | 1.1 | |
| | Total<br>Agreement<br>with Expected<br>Result | 90/90<br>100% | 90/90<br>100% | 90/90<br>100% | 90/90<br>100% | 90/90<br>100% | 90/90<br>100% | 89/90<br>89.9% | 90/90<br>100% | 90/90<br>100% | 90/90<br>100% | 90/90<br>100% | 90/90<br>100% | 270/270<br>100% | 270/270<br>100% | |
| | 95% CI | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 94.0%-<br>99.8% | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 95.9%-<br>100.0% | 98.6%-<br>100.0% | 98.6%-<br>100.0% | |
| | Overall Mean<br>Ct Value | 37.3 | 34.8 | 35.6 | 33.3 | 35.9 | 33.0 | 35.5 | 33.1 | 35.9 | 33.4 | 36.7 | 34.5 | 33.2 | 32.9 | |
| | Overall<br>% CV | 3.1 | 2.8 | 3.2 | 3.1 | 1.6 | 1.5 | 2.0 | 1.6 | 2.2 | 1.6 | 1.8 | 1.5 | 2.1 | 1.5 | |
* Note: The Campylobacter strains were tested at higher concentrations because Campylobacter is sensitive to environmental stressors including freezing where it loses viability. However, the average Ct value for the C. jejuni (ATCC 33291) Low Positives was 37.3, which is very close to the average Ct value of 38.8 for the same C. jejuni strain tested at the estimated LoD level in the Analytical Reactivity Study. The average Ct value for the C. coli (ATCC BAA-371) Low Positives was 35.6, which is very close to the average Ct value of 34.4 for the same C. coli strain tested at the estimated LoD level in the Analytical Reactivity Study. Therefore, the effective DNA concentrations of the C. jejuni (ATCC 33291) and C. codi (ATCC BAA-371) low positive samples tested in the Reproducibility Study are very close to the estimated LoD DNA concentrations for these two strains tested in the Analytical Reactivity Study.
{10}------------------------------------------------
#### Precision
The precision of the ProGastro SSCS Assay was evaluated internally using a panel of 15 simulated samples that included medium positive (near the assay limit of detection, ≥ 95% positive), and high negative (below the assay limit of detection, ≤ 95% positive) samples for each of the assay targets. A panel of 15 contrived samples including the necessary controls was run with the ProGastro SSCS Assay (SSC and STEC Mixes) by each of two operators for twelve days.
| | SSC Mix | | | | | | | | STEC Mix | | | | SSC<br>Mix | STEC<br>Mix |
|-----------------------------------------------|-------------------------------|----------------------------------|-----------------------------|--------------------------------|--------------------------------|-----------------------------------|------------------------------|---------------------------------|------------------------------------|---------------------------------------|------------------------------------|---------------------------------------|-----------------------------|-----------------------------|
| Panel<br>Member ID | <i>C. jejuni</i> Low Positive | <i>C. jejuni</i> Medium Positive | <i>C. coli</i> Low Positive | <i>C. coli</i> Medium Positive | <i>Salmonella</i> Low Positive | <i>Salmonella</i> Medium Positive | <i>Shigella</i> Low Positive | <i>Shigella</i> Medium Positive | STEC ( <i>stx 1</i> ) Low Positive | STEC ( <i>stx 1</i> ) Medium Positive | STEC ( <i>stx 2</i> ) Low Positive | STEC ( <i>stx 2</i> ) Medium Positive | High Negative (IC Ct Value) | High Negative (IC Ct Value) |
| Concentration | 20X*<br>LoD | 100X*<br>LoD | 6X*<br>LoD | 30X*<br>LoD | 2X<br>LoD | 10X<br>LoD | 2X<br>LoD | 10X<br>LoD | 2X<br>LoD | 10X<br>LoD | 2X<br>LoD | 10X<br>LoD | 0.0001X LoD | 0.0001X LoD |
| Total<br>Agreement<br>with Expected<br>Result | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 72/72<br>100% | 71/72<br>98.6% | 72/72<br>100% |
| Overall Mean<br>Ct Value | 36.7 | 34.2 | 35.0 | 32.7 | 35.6 | 32.7 | 35.1 | 32.7 | 35.6 | 33.0 | 36.5 | 34.2 | 32.9 | 32.5 |
| Overall % CV | 2.6 | 2.4 | 2.1 | 2.3 | 1.5 | 1.1 | 1.6 | 1.3 | 1.8 | 1.3 | 1.8 | 1.2 | 0.9 | 1.0 |
### Precision Panel Member Results
Note: The Campylobacter strains were tested at higher concentrations because Campylobacter is sensitive to environmental stressors including freezing where it loses viability. However, the average Ct value for the C. jejuni (ATCC 33291) Low Positives was 37.3, which is very close to the average Ct value of 38.8 for the same C. jejuni strain tested at the estimated LoD level in the Analytical Reactivity Study. The average Ct value for the C. coli (ATCC BAA-371) Low Positives was 35.6, which is very close to the average Ct value of 34.4 for the same C. coli strain tested at the estimated LoD level in the Analytical Reactivity Study. Therefore, the effective DNA concentrations of the C. jejuni (ATCC 33291) and C. codi (ATCC BAA-371) low positive samples tested in the Precision Study are very close to the estimated LoD DNA concentrations for these two strains tested in the Analytical Reactivity Study.
{11}------------------------------------------------
Image /page/11/Picture/0 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" arranged around the perimeter. Inside the circle is a stylized symbol resembling an abstract human figure with three flowing lines extending from its head.
#### DEPARTMENT OF HEALTH & HUMAN SERVICES
#### Public Health Service
Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-002
Gen-Probe Prodesse, Inc. c/o Karen Harrington, Ph.D. Manager, Clinical Affairs 20925 Crossroads Circle Waukesha, WI 53186
JAN 1 6 2013
Re: k123274
Trade/Device Name: ProGastro SSCS Assay Regulation Number: 21 CFR 866.3990 Regulation Name: Gastrointestinal Microorganism Multiplex Nucleic Acid-Based Assay Regulatory Class: Class II Product Code: PCH, PCI, OOI Dated: October 17. 2012 Received: October 19, 2012
Dear Dr. Harrington:
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 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); medical device reporting (reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set
{12}------------------------------------------------
Page 2 -- Karen Harrington
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.
If you desire specific advice for your device on our labeling regulation (21 CFR Parts 801 and 809), please contact the Office of In Vitro Diagnostics and Radiological Health at (301) 796-5450. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.
You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address http://www.fda.gov/cdrh/industry/support/index.html.
Sincerely yours,
Uwe Scherf for
Sally A. Hojvat, M.Sc., Ph.D. Director Division of Microbiology Devices Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health
Enclosure
{13}------------------------------------------------
# Indication for Use
510(k) Number: k123274
Device Name: ProGastro SSCS Assay
Indication For Use:
The Prodesse® ProGastro SSCS Assay is a multiplex real time PCR in vitro diagnostic test for the qualitative detection and differentiation of Salmonella, Shigella, and Campylobacter (C. jejuni and C. coli only, undifferentiated) nucleic acids and Shiga Toxin 1 (stxl) and Shiga Toxin 2 (stx2) genes. Shiga toxin producing E. coli (STEC) typically harbor one or both genes that encode for Shiga Toxins 1 and 2. Nucleic acids are isolated and purified from preserved stool specimens obtained from symptomatic patients exhibiting signs and symptoms of gastroenteritis. This test is intended for use, in conjunction with clinical presentation and epidemiological risk factors, as an aid in the differential diagnosis of Salmonella, Shigella, Campylobacter jejuni/Campylobacter coli, and STEC infections in humans.
The results of this test should not be used as the sole basis for diagnosis, treatment, or other patient management decisions. Positive results do not rule out co-infection with other organisms that are not detected by this test, and may not be the sole or definitive cause of patient illness. Negative ProGastro SSCS Assay results in the setting of clinical illness compatible with gastroenteritis may be due to infection by pathogens that are not detected by this test or non-infectious causes such as ulcerative colitis, irritable bowel syndrome, or Crohn's disease.
Prescription Use X (21 CFR Part 801 Subpart D) And/Or
Over the Counter Use _ (21 CFR Part 801 Subpart C)
(PLEASE DO NOT WRITE BELOW THIS LINE; CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of In Vitro Diagnostics and Radiological Health (OIR)
R. H. Hitz
ion Sign-Off Office of In Vitro Diagnostics and Radiological Health k 23274
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.