K240797 · Permantis Public Health · QBD · Oct 11, 2024 · Microbiology
Device Facts
Record ID
K240797
Device Name
PPH Saliva Collection Kit
Applicant
Permantis Public Health
Product Code
QBD · Microbiology
Decision Date
Oct 11, 2024
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.2950
Device Class
Class 2
Indications for Use
The PPH Saliva Collection Kit is designed for use in the non-invasive collection, inactivation, and stabilization of viral nucleic acids for in vitro diagnostic testing of saliva samples. The device is intended to inactivate and stabilize human clinical saliva samples from the collection site to the laboratory at room temperature. The device is intended to be used by a health care provider for the collection of saliva samples suspected of containing SARS-CoV-2. The saliva sample is stabilized and suitable for use with legally marketed molecular diagnostic devices.
Device Story
Device consists of plastic bulb pipette, paper cup, and plastic tube containing 0.3 ml stabilization buffer; used by healthcare providers for non-invasive collection of human saliva samples. Operation: patient provides saliva into cup; provider transfers sample to tube using pipette; tube capped and inverted 5-10 times to mix with buffer. Buffer lyses lipid membranes, inactivates enzymes, and stabilizes viral nucleic acids. Stabilized samples transported to laboratory at room temperature; suitable for downstream molecular diagnostic testing. Device provides viral inactivation of SARS-CoV-2, enhancing safety for laboratory personnel. Benefits include simplified, non-invasive sample collection and preservation of viral RNA integrity for up to 7 days at ambient temperature (20-25°C).
Clinical Evidence
No clinical data. Bench testing only. LoD established at 0.25 copies/μL (100% N1 detection, 95% N2 detection). Real-time stability study confirmed sample stability for 7 days at ambient temperature (20-25°C) with Ct change < 1. Inactivation study confirmed complete SARS-CoV-2 inactivation after 90 seconds of exposure to buffer using Vero E6 cell culture plaque assay.
Technological Characteristics
Polypropylene collection tube; 0.3 ml stabilization buffer (Guanidine Thiocyanate, Sarkosyl, Sodium Acetate, pH 5, Nuclease-free Water). Non-sterile, single-use device. Manual operation. No electronic components or software.
Indications for Use
Indicated for use by health care providers to collect, inactivate, and stabilize human saliva samples suspected of containing SARS-CoV-2 for downstream molecular diagnostic testing.
Regulatory Classification
Identification
A microbial nucleic acid storage and stabilization device is a device that consists of a container and reagents intended to stabilize microbial nucleic acids in human specimens for subsequent isolation and purification of nucleic acids for further molecular testing. The device is not intended for preserving morphology or viability of microorganisms.
Special Controls
The special controls for this device are: (1) The intended use for the 21 CFR 809.10 labeling must include a detailed description of microorganisms and types of human specimens intended to be preserved. (2) The 21 CFR 809.10(b) labeling must include: (i) A detailed device description, including all device components. (ii) Performance characteristics from applicable analytical studies, including but not limited to, nucleic acid stability and microorganism inactivation. (iii) A limiting statement that erroneous results may occur when the transport device is not compatible with molecular testing. (iv) A limiting statement that the device has only been validated to preserve the representative microorganisms used in the analytical studies. (3) Design verification and validation must include the following: (i) Overall device design including all device components and all control elements incorporated into the analytical validation procedures. (ii) Thorough description of the microorganisms and methodology used in the validation of the device including, but not limited to, extraction platforms and assays used for the detection of preserved nucleic acids. (iii) The limit of detection (LoD) of the molecular test used to establish microorganism nucleic acid stability.
*Classification.* Class II (special controls). The special controls for this device are:(1) The intended use for the labeling required under § 809.10 of this chapter must include a detailed description of microorganisms and types of human specimens intended to be preserved.
(2) The labeling required under § 809.10(b) of this chapter must include the following:
(i) A detailed device description, including all device components;
(ii) Performance characteristics from applicable analytical studies, including nucleic acid stability and microorganism inactivation;
(iii) A limiting statement that erroneous results may occur when the transport device is not compatible with molecular testing; and
(iv) A limiting statement that the device has only been validated to preserve the representative microorganisms used in the analytical studies.
(3) Design verification and validation must include the following:
(i) Overall device design, including all device components and all control elements incorporated into the analytical validation procedures;
(ii) Thorough description of the microorganisms and methodology used in the validation of the device including, extraction platforms and assays used for the detection of preserved nucleic acids; and
(iii) The limit of detection (LoD) of the molecular test used to establish microorganism nucleic acid stability.
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K240797
B Applicant
Permantis Public Health (PPH)
C Proprietary and Established Names
PPH Saliva Collection Kit
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QBD | Class II | 21 CFR 866.2950 - Microbial Nucleic Acid Storage And Stabilization Device | MI - Microbiology |
## II Submission/Device Overview:
A Purpose for Submission:
To obtain a substantial equivalence determination for the PPH Saliva Collection Kit for collection, transport, and storage of SARS-CoV-2 in saliva specimens to the laboratory for downstream testing.
B Measurand:
Storage and stabilization of nucleic acids from SARS-CoV-2.
C Type of Test:
Microbial nucleic acid storage and stabilization device
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
K240797 - Page 2 of 8
## III Intended Use/Indications for Use:
### A Intended Use(s):
See Indications for Use below.
### B Indication(s) for Use:
The PPH Saliva Collection Kit is designed for use in the non-invasive collection, inactivation, and stabilization of viral nucleic acids for in vitro diagnostic testing of saliva samples. The device is intended to inactivate and stabilize human clinical saliva samples from the collection site to the laboratory at room temperature. The device is intended to be used by a health care provider for the collection of saliva samples suspected of containing SARS-CoV-2. The saliva sample is stabilized and suitable for use with legally marketed molecular diagnostic devices.
### C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
### D Special Instrument Requirements:
None.
## IV Device/System Characteristics:
### A Device Description:
The PPH Saliva Collection Device contains a plastic bulb pipette, paper cup, plastic tube with PPH Saliva collection buffer (0.3 ml). It is designed for use in the non-invasive collection, inactivation, and stabilization of viral nucleic acids for in vitro diagnostic testing of saliva samples.
Saliva is collected into the provided paper cup and then transferred into the tube containing PPH Saliva collection buffer with the bulb pipet. After transfer of the saliva sample, the tube should be approximately half full. The tube with sample is then capped and inverted 5-10 times to allow adequate mixing.
### B Principle of Operation:
The components of the inactivating media for the PPH Saliva Collection Kit are intended to inactivate SARS CoV-2 capsids, disrupt/lyse membranes, denature proteins, inactivate enzymes, and stabilize SARS CoV-2 RNA. The inactivating solution includes following:
- Guanidine Thiocyanate
- Sarkosyl
- Sodium Acetate, pH 5
- Nuclease-free Water
## V Substantial Equivalence Information:
### A Predicate Device Name(s):
Spectrum Saliva Collection Device
{2}
B Predicate 510(k) Number(s):
K223497
C Comparison with Predicate(s):
| Device & Predicate Device(s): | Device: K240797 | Predicate: K223497 |
| --- | --- | --- |
| Device Trade Name | PPH Saliva Collection Device | Spectrum Saliva Collection Device |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | The PPH Saliva Collection Kit is designed for use in the non-invasive collection, inactivation, and stabilization of viral nucleic acids for in vitro diagnostic testing of saliva samples. The device is intended to inactivate and stabilize human clinical saliva samples from the collection site to the laboratory at room temperature. The device is intended to be used by a health care provider for the collection of saliva samples suspected of containing SARS-CoV-2. The saliva sample is stabilized and suitable for use with legally marketed molecular diagnostic devices. | The Spectrum Solutions Saliva Collection Device is designed for use in the non-invasive collection, inactivation, and stabilization of viral nucleic acids for in vitro diagnostic testing of saliva samples. The device is intended to inactivate and stabilize human clinical saliva samples from the collection site to the laboratory at room temperature. The saliva sample is stabilized and suitable for use with legally marketed molecular diagnostic devices. The device is intended to be used by a health care provider for samples suspected of containing SARS-CoV-2. |
| Analyte | Same | RNA from SARS-CoV-2 |
| General Device Characteristic Differences | | |
| Specimen Stability | 7 days at ambient temperature (20-25°C) | 28 days at 20-25°C |
| Shelf life | 9 months at room temperature (15-30°C) | 24 months at room temperature (15-30°C) |
| Buffer | PPH Saliva Collection | Spectrum’s Nucleic |
K240797 - Page 3 of 8
{3}
| | Kit buffer | Acid Stabilization Solution |
| --- | --- | --- |
| Physical container | Plastic polypropylene collection tube | Tube – Polypropylene Funnel |
VI Standards/Guidance Documents Referenced:
Special controls that are applicable to regulation 21 CFR 866.2950.
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
N/A
2. Linearity:
N/A
3. Analytical Specificity/Interference:
N/A
4. Assay Reportable Range:
N/A
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
**Shelf-life Stability:** The shelf life for the PPH Saliva Collection Kit is nine (9) months at room temperature (15-30°C) after the date of manufacture. The shelf-life stability of the PPH Saliva Collection Kit was established in a real-time stability study that evaluated several time points (T = 0, 1, 3, 6, 9, and 12 months) for both temperature extremes. In this study, shelf-life stability also included evaluation of physical stability (appearance), color, volume loss, and pH stability during the period of storage. At each time point, the appearance of the product was inspected visually as a clear liquid without precipitation and with no observed volume loss, change in buffer PH, or color change when stored under the specified storage conditions.
**Sterilization:** The PPH Saliva Collection Kits are not sold as sterile nor are they intended to be sterilized by the user. These vials are single use devices that do not require cleaning or sterilization by the operator.
6. Detection Limit:
A limit of detection (LoD) study was conducted to determine the lowest concentration.
K240797 - Page 4 of 8
{4}
that contains measurable nucleic acids that can be repeatedly detected in samples collected in the PPH Saliva Collection Kit with greater than $95\%$ accuracy. RNA extraction was performed using magnetic bead purification on a Thermo Fisher Kingfisher Apex Purification system. Viral RNA was subsequently amplified using the Triplex CII-SARS-CoV-2 rRT-PCR for SARS-CoV-2 detection assay (RUCGL.SCV2.2 assay). The primers and probes used in this assay allow simultaneous measurements of SARS-CoV-2 nucleocapsid RNA (N1 and/or N2), and human Ribonuclease P (RP) transcripts. RT-qPCR was performed with RP primers as positive control to detect the human RNase P gene.
A preliminary LoD was established by evaluating three replicates of several serial dilutions of saliva spiked with SARS-CoV-2 and collected in the PPH Saliva Collection device. These samples were evaluated on the RUCGL.SCV2.2 assay for SARS-CoV-2 detection. For this assay, Ct values $< 40$ were considered positive for SARS-CoV-2.
Results from the preliminary LoD study are summarized in Table 1 below.
Table 1. Preliminary LoD Estimation Results
| Copies/μL | N1 Detection Rate | N1 Mean Ct | N2 Detection Rate | N2 Mean Ct |
| --- | --- | --- | --- | --- |
| 8 | 3/3 | 31.03 | 3/3 | 30.92 |
| 4 | 3/3 | 32.13 | 3/3 | 31.97 |
| 2 | 3/3 | 33.06 | 3/3 | 32.62 |
| 1 | 3/3 | 34.37 | 3/3 | 33.90 |
| 0.5 | 3/3 | 35.23 | 3/3 | 35.20 |
| 0.25 | 3/3 | 37.85 | 2/3 | - |
| 0.125 | 3/3 | 39.53 | 2/3 | - |
| 0.06125 | 2/3 | - | 1/3 | - |
| 0 | 0/3 | - | 0/3 | - |
The estimated LoD based on the preliminary results was identified as 0.125 copies/μL.
To further confirm this preliminary LoD assessment, four concentrations of SARS-CoV-2 (0, 0.0625, 0.125, and 0.25 copies/μL) in saliva were evaluated in 20 replicates using the PPH Saliva Collection Kit. Results from the LoD confirmation study are summarized in Table 2 below.
Table 2. Confirmatory LoD Study Results
| Copies/μL | N1 Detection Rate | N1 Mean Ct | N2 Detection Rate | N2 Mean Ct |
| --- | --- | --- | --- | --- |
| 0.25 | 20/20 | 35.99 | 19/20 | 37.57 |
| 0.125 | 17/20 | - | 4/20 | - |
| 0.06125 | 18/20 | - | 5/20 | - |
| 0 | 0/20 | - | - | - |
K240797 - Page 5 of 8
{5}
In summary, the results of the LoD study indicate an LoD of 0.25 copies/μL with observed detection of 100% (20/20) for the N1 target and 95% (19/20) for N2 replicate.
## 7. Sample Stability:
A real-time sample stability study was conducted to evaluate the stability of samples containing SARS-CoV-2 when stored for up to 8 days at ambient temperature (20-25°C). Inactivated SARS-CoV-2 (Zeptometrix, Cat # NATSARS(COV2)-ST, 1.21×10⁶ copies/μl) was used to prepare contrived samples including 20 low positive samples (2X LoD) and 10 negative samples for each device lot. Briefly, saliva matrix and SARS-CoV-2 were combined at a ratio of 1:1 and then added to each collection tube containing 300 μl of PPH Saliva Collection Kit buffer.
Sample stability was assessed at baseline (day 0), day 7, and day 8 after being placed in PPH Saliva Collection Kit buffer and stored at ambient temperature (20-25°C). The difference in Ct over this time course is less than 1. The largest change in Ct observed was 0.40 at 8 days.
These test results fall within the established acceptance criteria and indicate that samples are stable in the PPH Saliva Collection Kits inactivating media for up to 7 days. Results for sample stability testing are summarized in Table 3 below.
Table 3. Sample Stability Study Results
| Samples Evaluated | Mean Ct & SD | Day 0 | Day 7 | Day 8 |
| --- | --- | --- | --- | --- |
| Low positive (60 samples) | N1 Mean Ct | 35.9 | 36.14 | 36.2 7 |
| | SD | 0.43 | 0.5 | 0.523 |
| | N2 Mean Ct | 35.49 | 35.63 | 35.7 |
| | SD | 0.4 | 0.47 | 0.4 |
| Negative (30 samples) | - | - | - | - |
## SARS-CoV-2 Inactivation
An inactivation study was conducted to verify that the PPH Saliva Collection device inactivates SARS-CoV-2 as efficiently as the predicate device.
**Cytotoxicity:** A cytotoxicity study was performed to first determine at what dilution ratio the PPH Saliva Collection Kit buffer would not be toxic to a cell monolayer.
To determine the cytotoxic effect of the buffer on test cells, Vero E6 cells that were seeded at a concentration of 2500 cells/well in each well of a 96 well plate was exposed to serially diluted PPH Saliva Collection Kit buffer prepared in Vero E6 DMEM culture medium. Viability of the test cells was assessed using the CellTiterGlo assay (Promega #G7570) after 4 days of exposure and normalized to untreated cells. After the incubation period, a concentration of 1:5,000 PPH Saliva Collection Kit buffer was determined not to have a cytopathic effect to the host cells.
K240797 - Page 6 of 8
{6}
Therefore, to conduct the viral inactivation study the PPH Saliva Collection Kit buffer was diluted to 1:5,000 with DMEM media.
## Inactivation Assay:
Viral inactivation was assessed using a stock of SARS-CoV-2 (USA WA1/2020) at 5.65×10⁶ PFU/ml. To determine the amount of contact time required for viral inactivation of SARS-CoV-2 with PPH Saliva Collection Kit buffer, the samples were prepared as follows:
1. Mixed virus stock with saliva at a 1:1 ratio.
2. Mixed virus and saliva with PPH Saliva Collection Kit buffer at a 1:1 ratio.
3. Incubated for 15, 30, 45, 60, 90, 120, 180, or 240 seconds.
4. Diluted virus, saliva and buffer 1:5,000 with Dulbecco’s modified Eagle’s Medium (DMEM), a concentration previously determined not to be cytotoxic.
100 μL of each sample containing ~113 PFU of SARS-CoV-2 was added to a 96-well plate confluent with Vero E6 cells after media was removed. Six replicates were plated for each time point. The controls included and plated in triplicate included only media, Saliva and PPH Saliva Collection Kit buffer (no virus), and Virus only. No PFUs were obtained after 60, 90, 120, 180 and 240 seconds of exposure of the cells to the media in the PPH Saliva Collection Kit buffer. Acceptance criteria were met for no detectable virus (zero positive plaques) after 4 days growth.
These study results support SARS-CoV-2 inactivation after 90 seconds of exposure to PPH Saliva Collection Kit buffer.
## 8. Assay Cut-Off:
N/A
## B Comparison Studies:
1. Method Comparison with Predicate Device:
N/A
2. Matrix Comparison:
N/A
## C Clinical Studies:
1. Clinical Sensitivity:
N/A
K240797 - Page 7 of 8
{7}
2. Clinical Specificity:
N/A
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
N/A
D Clinical Cut-Off:
N/A
E Expected Values/Reference Range:
N/A
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.
K240797 - Page 8 of 8
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.
