The sponsor used data from two peer-reviewed publications to support the expansion of the device's indications for use to include pediatric patients. The studies evaluated the performance of the T2Candida 1.1 Panel in pediatric clinical samples compared to blood culture results.
T2Candida® 1.1 Panel and T2Dx® Instrument is a qualitative T2 Magnetic Resonance (T2MR®) assy for the direct detection of Candida species in K₂EDTA human whole blood specimens from patients with symptoms of, or medical conditions predisposing the patient to, invasive fungal infections. The T2Candida 1.1 Panel identifies five species of Candida and categorizes them into the following three species groups: 1. Candida albicans and/or Candida tropicalis 2. Candida parapsilosis 3. Candida glabrata and/or Candida krusei. The T2Candida 1.1 Panel does not distinguish between C. albicans and C. tropicalis. The T2Candida 1.1 Panel does not distinguish between C. glabrata and C. krusei. The T2Candida 1.1 Panel is indicated for the presumptive diagnosis of candidemia. The T2Candida 1.1 Panel is performed independent of blood culture. Concomitant blood cultures are necessary to recover organisms for susceptibility testing or further identification. The T2Candida positive and negative External Controls (T2Candida QCheck Positive Kit and the T2Dx QCheck Negative Kit) are intended to be used as quality control samples with the T2Candida 1.1 Panel when run on the T2Dx Instrument. These controls are not intended for use with other assays or systems.
Device Story
T2Candida 1.1 Panel is a molecular diagnostic assay for direct detection of Candida species in K2EDTA whole blood. The device uses the T2Dx Instrument to perform automated sample processing, including red blood cell lysis, Candida cell lysis, and PCR amplification. Detection utilizes T2 magnetic resonance (T2MR) technology, where species-specific probes attached to superparamagnetic particles bind to Candida DNA amplicons. The system identifies three Candida groups: C. albicans/C. tropicalis, C. parapsilosis, and C. glabrata/C. krusei. Results are provided to clinicians to support presumptive diagnosis of candidemia, enabling faster clinical decision-making compared to traditional blood culture, which remains necessary for susceptibility testing. The device is intended for use in clinical settings by trained personnel.
Clinical Evidence
Clinical performance supported by two peer-reviewed studies evaluating 246 pediatric samples (ages 23 weeks to 17 years). Sensitivity (PPA) ranged from 50-100% and specificity (NPA) ranged from 97-99% compared to blood culture. Low prevalence of 1.2% observed.
Technological Characteristics
Uses T2 magnetic resonance (T2MR) detection following PCR amplification. Platform: T2Dx Instrument. Sample: 3 mL K2EDTA whole blood. Reagents: Internal control, amplification reagents, and probe-coupled superparamagnetic particles. Qualitative detection of Candida DNA.
Indications for Use
Indicated for presumptive diagnosis of candidemia in patients with symptoms of or medical conditions predisposing to invasive fungal infections. Labeled for use in adult and pediatric patients (excluding neonates).
Regulatory Classification
Identification
A nucleic acid-based device for the amplification, detection, and identification of microbial pathogens directly from whole blood specimens is a qualitative in vitro device intended for the amplification, detection, and identification of microbial-associated nucleic acid sequences from patients with suspected bloodstream infections. This device is intended to aid in the diagnosis of bloodstream infection when used in conjunction with clinical signs and symptoms and other laboratory findings.
Special Controls
A nucleic acid-based device for the amplification, detection and identification of microbial pathogens directly from whole blood specimens must comply with the following special controls:
*Classification.* Class II (special controls). The special controls for this device are:(1) Premarket notification submissions must include detailed device description documentation, including the device components, ancillary reagents required but not provided, and a detailed explanation of the methodology, including primer/probe sequence, design, and rationale for sequence selection.
(2) Premarket notification submissions must include detailed documentation from the following analytical and clinical performance studies: Analytical sensitivity (limit of detection), reactivity, inclusivity, precision, reproducibility, interference, cross reactivity, carryover, and cross contamination.
(3) Premarket notification submissions must include detailed documentation from a clinical study. The study, performed on a study population consistent with the intended use population, must compare the device performance to results obtained from well-accepted reference methods.
(4) Premarket notification submissions must include detailed documentation for device software, including, but not limited to, software applications and hardware-based devices that incorporate software.
(5) The device labeling must include limitations regarding the need for culture confirmation of negative specimens, as appropriate.
(6) A detailed explanation of the interpretation of results and acceptance criteria must be included in the device's 21 CFR 809.10(b)(9) compliant labeling.
(7) Premarket notification submissions must include details on an end user device training program that will be offered while marketing the device, as appropriate.
(8) As part of the risk management activities performed under 21 CFR 820.10(c) design and development, you must document an appropriate end user device training program that will be offered as part of your efforts to mitigate the risk of failure to correctly operate the instrument.
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K234063
B Applicant
T2Biosystems, Inc.
C Proprietary and Established Names
T2Candida 1.1 Panel
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| PII | Class II | 21 CFR 866.3960 - Nucleic Acid-Based Device For The Amplification, Detection, And Identification Of Microbial Pathogens Directly From Whole Blood Specimens | MI - Microbiology |
| NSU | Class II | 21 CFR 862.2570 - Instrumentation for clinical multiplex test systems | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
To amend the T2Candida 1.1 Panel labeling regarding testing with pediatric patients.
B Measurand:
The assay amplifies and detects nucleic acids of the following species:
Candida albicans and/or Candida tropicalis
Candida parapsilosis
Candida krusei and/or Candida glabrata
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
K234063 - Page 2 of 9
C Type of Test:
The T2Candida 1.1 Panel, performed on the T2Dx Instrument, is a molecular diagnostic assay for the detection of the above listed Candida species from whole blood specimens obtained from patients with signs and symptoms of invasive Candida infection.
III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
T2Candida 1.1 Panel and T2Dx Instrument is a qualitative T2 Magnetic Resonance (T2MR) assay for the direct detection of Candida species in K₂EDTA human whole blood specimens from patients with symptoms of, or medical conditions predisposing the patient to, invasive fungal infections.
The T2Candida 1.1 Panel identifies five species of Candida and categorizes them into the following three species groups:
1. Candida albicans and/or Candida tropicalis
2. Candida parapsilosis
3. Candida glabrata and/or Candida krusei
The T2Candida 1.1 Panel does not distinguish between C. albicans and C. tropicalis. The T2Candida 1.1 Panel does not distinguish between C. glabrata and C. krusei.
The T2Candida 1.1 Panel is indicated for the presumptive diagnosis of candidemia. The T2Candida 1.1 Panel is performed independent of blood culture. Concomitant blood cultures are necessary to recover organisms for susceptibility testing or further identification, and for organisms not detected by the T2Candida 1.1 Panel.
The T2Candida positive and negative External Controls (T2Candida QCheck Positive Kit and the T2Dx QCheck Negative Kit) are intended to be used as quality control samples with the T2Candida 1.1 Panel when run on the T2Dx Instrument. These controls are not intended for use with other assays or systems.
C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
For In Vitro Diagnostic Use
Device performance was initially established with samples from adult patients. Panel performance with samples from pediatric patients was supported by additional studies with pediatric subjects. Panel performance with samples from neonates has not been established.
{2}
D Special Instrument Requirements:
The T2Candida 1.1 Panel is performed on the T2Dx Instrument.
IV Device/System Characteristics:
A Device Description:
The T2Candida 1.1 panel is a qualitative molecular diagnostic assay that detects Candida species directly from whole blood. Together with the T2Dx Instrument, the T2Candida 1.1 panel uses whole blood compatible PCR amplification followed by T2 magnetic resonance (T2MR) detection. The T2Dx Instrument was originally evaluated in DEN140019 and is unchanged in this submission.
To initiate testing, at least 3 mL of whole blood specimen is collected into a 4 mL K₂EDTA vacutainer. The sample tube is loaded into the T2Candida Sample Inlet, which is then placed on the T2Candida Base along with the T2Candida Reagent Tray. The Reagent Tray contains the internal control, amplification reagent, enzyme, and the probe-coupled superparamagnetic particles for each Candida target. The assembled pack is then inserted in the T2Dx instrument, which executes all steps after specimen loading.
Two milliliters of blood specimen are automatically transferred to the T2Dx Instrument where the red blood cells are lysed, Candida cells are concentrated and lysed, and Candida DNA is amplified. Amplification products are detected by T2MR detection using species-specific probes which are attached to the superparamagnetic particles. The assay provides an identification of Candida albicans and/or Candida tropicalis, Candida parapsilosis, and Candida glabrata and/or Candida krusei. The test does not distinguish between C. albicans and C. tropicalis. The test does not distinguish between C. glabrata and C. krusei. Results are provided within 5 hours of the initial blood draw.
B Principle of Operation:
The T2Candida Panel and T2Dx Instrument rely on PCR amplification of conserved sequences to detect Candida species. The assay includes a single pair of pan-Candida primers that hybridize to conserved sequences within the 5.8S and 26S ribosomal RNA operon of Candida species and amplify the intervening transcribed spacer 2 sequence (ITS2) from nucleic acid released from the lysed Candida cells contained in the specimen. The primers are mixed in a ratio such that an asymmetric product produces a predominantly single stranded nucleic acid after amplification. The primers are designed to also amplify the internal control. Species-specific and internal control-specific probes provide the specificity of the assay.
The instrument detects the amplified PCR product directly in the whole blood matrix by amplicon-induced agglomeration of superparamagnetic particles attached to the species-specific and internal control-specific probes. The detection method measures the spin-spin relaxation signals of water molecules. For these measurements, the T2Dx Instrument utilizes a small permanent magnet and a specialized radio frequency coil to measure the T2MR signal from the water molecules. T2MR measures the disorder of the nuclear spins of the water molecules
K234063 - Page 3 of 9
{3}
contained in the sample and this disorder is directly proportional to the superparamagnetic particle clustering state. The T2Dx Instrument reports a positive or negative result for each detection channel: C. albicans/C. tropicalis (A/T), C. parapsilosis (P), C. krusei/C. glabrata (K/G) and internal control (IC).
# V Substantial Equivalence Information:
A Predicate Device Name(s):
T2Candida 1.1 Panel
B Predicate 510(k) Number(s):
K173536
C Comparison with Predicate(s):
| Device & Predicate Device(s): | Device: T2Candida 1.1 Panel K234063 | Predicate: T2Candida 1.1 Panel K173536 |
| --- | --- | --- |
| Device Trade Name | T2Candida 1.1 Panel | T2Candida 1.1 Panel |
| General Device Characteristic Similarities | | |
| | Device: K234063 | Predicate: K173536 |
| Intended Use/Indications For Use | T2Candida 1.1 Panel and T2Dx Instrument is a qualitative T2 Magnetic Resonance (T2MR) assay for the direct detection of Candida species in K2EDTA human whole blood specimens from patients with symptoms of, or medical conditions predisposing the patient to, invasive fungal infections. The T2Candida 1.1 Panel identifies five species of Candida and categorizes them into the following three species groups: 1. Candida albicans and/or Candida tropicalis 2. Candida parapsilosis 3. Candida glabrata and/or Candida krusei The T2Candida 1.1 Panel does not distinguish between C. albicans and C. tropicalis. The T2Candida 1.1 Panel does not distinguish between C. glabrata and C. krusei. The T2Candida 1.1 Panel is indicated for the presumptive diagnosis of candidemia. The T2Candida 1.1 Panel is performed | Same |
K234063 - Page 4 of 9
{4}
VI Standards/Guidance Documents Referenced:
ISO 15223-1 Fourth Edition 2021-07: Medical devices - Symbols to be used with information to be supplied by the manufacturer - Part 1: General requirements.
Premarket Assessment of Pediatric Medical Devices: Guidance for Industry and Food and Drug Administration Staff (March 24, 2014)
| | independent of blood culture. Concomitant blood cultures are necessary to recover organisms for susceptibility testing or further identification. The T2Candida positive and negative External Controls (T2Candida QCheck Positive Kit and the T2Dx QCheck Negative Kit) are intended to be used as quality control samples with the T2Candida 1.1 Panel when run on the T2Dx Instrument. These controls are not intended for use with other assays or systems. | |
| --- | --- | --- |
| Sample Type | Whole blood collected in a blood collection tube with EDTA anticoagulant | Same |
| Sample Volume | ≥3 mL in a 4 mL K_{2}EDTA tube | Same |
| Test Platform | T2Dx Instrument | Same |
| Test Principle | Nucleic acid amplification followed by T2 magnetic resonance detection | Same |
| Test Cartridge | T2Candida test cartridge, sample inlet, and disposables | Same |
| Reagent Trays | T2Candida test reagents specific for the detection of Candida | Same |
| Targets | T2Candida Panel tests for five different species of Candida commonly associated with candidemia: Candida albicans and/or Candida tropicalis, Candida parapsilosis, Candida glabrata and/or Candida krusei | Same |
| General Device Characteristic Differences | | |
| | Device: K234063 | Predicate: K173536 |
| Patient Population and Exclusions | Labeled for adult and pediatric patients (excluding neonates) | Labeled for adult patients |
K234063 - Page 5 of 9
{5}
VII Performance Characteristics (if/when applicable):
# A Analytical Performance:
Most analytical performance metrics of the T2Candida 1.1 Panel were previously established in DEN140019 and K173536 and remain applicable under the expanded use with pediatric subjects. The sample matrix (human blood), device design, and sample workflow remain unchanged. In this submission, additional analytical studies were conducted as deemed necessary to ensure safety and effectiveness in this specific patient population. This approach is in accordance with the Premarket Assessment of Pediatric Medical Devices Guidance (2014).
# 1. Precision/Reproducibility:
Device precision/reproducibility was assessed and deemed acceptable in DEN140019. Refer to the DEN140019 Decision Summary for additional details.
# 2. Linearity:
Not applicable.
# 3. Analytical Specificity/Interference:
# Analytical Specificity
Cross-reactivity was previously assessed with 80 non-target, clinically relevant or environmental organisms in DEN140019 and select species were found to be cross-reactive (see DEN140019 Decision Summary).
Additional cross-reactivity testing was performed in this submission using five organisms clinically relevant to pediatric populations: Streptococcus agalactiae, Listeria monocytogenes, Haemophilus influenzae, Streptococcus mitis, and Neisseria meningitidis.
Isolates were tested in triplicate at a concentration of $10^{6}$ CFU/mL. Any organism that demonstrated cross-reactivity or gave an invalid result was further evaluated with additional replicates from two additional sample preparations at the same concentration and was tested at lower, more clinically relevant concentrations of organisms in blood (100-1000 CFU/mL).
Cross-reactivity was defined as an increase in the T2 signal above the established cutoff for the Candida detection channel when tested at clinically relevant concentrations. Cross-reactivity required both amplification of the organism with the pan-Candida primers and subsequent detection with any of the capture probes. Of the five organisms tested, two demonstrated cross-reactivity at $10^{6}$ CFU/mL (S. agalactiae, H. influenzae). Cross-reactivity was not observed when the organisms were re-tested at 1000 CFU/mL. The remaining three organisms did not demonstrate cross-reactivity (Table 1). The data are acceptable.
Table 1. T2Candida cross-reactivity results
| Species | Concentration (CFU/mL) | Positive Results per Detection Panel | | | |
| --- | --- | --- | --- | --- | --- |
| | | A/T | P | K/G | Internal Control |
| N. meningitidis | 10^6 CFU/mL | 0/3 | 0/3 | 0/3 | Valid (3/3) |
K234063 - Page 6 of 9
{6}
| Species | Concentration (CFU/mL) | Positive Results per Detection Panel | | | |
| --- | --- | --- | --- | --- | --- |
| | | A/T | P | K/G | Internal Control |
| S. mitis | 10^6 CFU/mL | 0/3 | 0/3 | 0/3 | Valid (3/3) |
| L. monocytogenes | 10^6 CFU/mL | 0/3 | 0/3 | 0/3 | Valid (3/3) |
| S. agalactiae | 10^6 CFU/mL | 0/3 | 0/3 | 1/3 | Valid (3/3) |
| | 10^6 CFU/mL* | 0/6 | 0/6 | 1/6 | Valid (6/6) |
| | 1000 CFU/mL | 0/3 | 0/3 | 0/3 | Valid (3/3) |
| | 100 CFU/mL | 0/3 | 0/3 | 0/3 | Valid (3/3) |
| | 33 CFU/mL | 0/3 | 0/3 | 0/3 | Valid (3/3) |
| H. influenzae | 10^6 CFU/mL | 0/3 | 0/3 | 2/3 | Valid (3/3) |
| | 1000 CFU/mL | 0/3 | 0/3 | 0/3 | Valid (3/3) |
| | 100 CFU/mL | 0/3 | 0/3 | 1/3 | Valid (3/3) |
| | 100 CFU/mL* | 0/6 | 0/6 | 0/6 | Valid (6/6) |
| | 33 CFU/mL | 0/3 | 0/3 | 0/3 | Valid (3/3) |
A/T = C. albicans / C. tropicalis; P = C. parapsilosis; K/G = C. krusei / C. glabrata
*For any cross-reactive result, two additional unique sample preparations were tested at the same concentration. Results were not considered cross-reactive if only one replicate demonstrated cross-reactivity.
## Interference
An interference substances study was conducted as part of DEN140019. Results indicated interference with the signal for Candida species or with the signal for the internal control for the following substances: Feraheme, Magnevist, EDTA, Ablavar, and samples with an interferent simulating lipemia (Intralipid). Refer to the DEN140019 Decision Summary for additional information.
## 4. Assay Reportable Range:
Not applicable.
## 5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
Internal and external controls are unchanged in this submission and were previously validated in DEN140019. Refer to the DEN140019 Decision Summary for additional information.
Sample and reagent stability was previously validated in DEN140019 and K173536:
- Specimen stability at 2-8°C
- Lysis tube and reagent stability/shelf-life (12 months)
- Shipping stability
Use with pediatric populations will not alter the internal/external controls or stability. The data above are acceptable for the T2Candida 1.1 Panel.
## 6. Detection Limit:
The limit of detection for each Candida species was previously determined in DEN140019.
## 7. Assay Cut-Off:
K234063 - Page 7 of 9
{7}
Assay cut-off was previously established in DEN140019.
## B Comparison Studies:
1. **Method Comparison with Predicate Device:**
Not applicable. See Clinical Studies below.
2. **Matrix Comparison:**
Not applicable.
## C Clinical Studies:
Clinical study data from DEN140019 as well as additional data from studies that used the T2Candida 1.1 Panel with pediatric subjects were leveraged to support clinical performance of the device in subjects inclusive of adult and pediatric ages. This approach was based on the principles in the FDA Guidance, *Premarket Assessment of Pediatric Medical Devices*. As the course of the disease (invasive candidemia) is similar in adult and pediatric patients and the sample workflow and technological characteristics of the device remain unchanged, the amended labeling was supported by the existing clinical validation data conducted with adults.
The following principles were considered and deemed acceptably similar between the predicate device, as previously established for adult patients, and the subject device for a broader age-range subject population:
- Biological similarity of the sample (human whole blood)
- Biological similarity of disease in patient sub-populations
- No changes to device technology, design, reagents, or sample workflow
To further support testing in a pediatric population, data were evaluated from two studies from peer-reviewed literature in which the T2Candida 1.1 Panel was used to test samples from pediatric subjects. Detailed enrollment criteria, clinical protocols, patient demographic and clinical information, testing protocols, and detailed line data were provided for assessment. All samples were tested in accordance with the T2Candida 1.1 Panel instructions for use and compared to speciated *Candida* results from blood culture. A total of 246 samples were evaluated from patients aged <1 year to 17 years. Low prevalence (as determined by positive blood culture) was observed (1.2%). For all samples, estimates of sensitivity (PPA) ranged from 50-100% and specificity (NPA) ranged from 97-99%. The totality of data from pediatric and adult subjects support testing with the expanded patient age population.
1. **Clinical Sensitivity:**
Clinical sensitivity was determined in DEN140019 using prospective and contrived samples. Refer to the DEN140019 Decision Summary.
2. **Clinical Specificity:**
K234063 - Page 8 of 9
{8}
Clinical sensitivity was determined in DEN140019 using prospective and contrived samples. Refer to the DEN140019 Decision Summary.
## D Clinical Cut-Off:
The clinical cut-off was previously established in DEN140019.
## E Expected Values/Reference Range:
The expected values/reference range were previously established in DEN140019.
## 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.
K234063 - Page 9 of 9
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.
