Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System
DEN250049 · Abbott Diabetes Care · SJD · Aug 25, 2026 · Clinical Chemistry
Device Facts
Record ID
DEN250049
Device Name
Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System
Applicant
Abbott Diabetes Care
Product Code
SJD · Clinical Chemistry
Decision Date
Aug 25, 2026
Decision
DENG
Submission Type
Direct
Regulation
21 CFR 862.1354
Device Class
Class 2
Attributes
Pediatric
Indications for Use
Libre Duo 10 Day is a Continuous Dual Glucose Ketone Monitoring System indicated for the management of diabetes in persons age 2 years and older. It is intended to monitor glucose and ketone (beta-hydroxybutyrate) levels in real-time. The System also provides alarms, detects trends, tracks glucose and ketone patterns, and aids in the detection of episodes of hyperglycemia, hypoglycemia, and hyperketonemia, facilitating both acute and long-term therapy adjustments, and the system replaces blood glucose testing for diabetes treatment decisions, unless otherwise indicated. Interpretation of system readings should be based on the trends and sequential readings over time. When making therapeutic adjustments, ketone output should be used in conjunction with glucose levels, symptoms, and factors that may affect ketone levels such as eating patterns and exercise. The System is also intended to autonomously communicate with digitally connected devices. The System can be used alone or in conjunction with these digitally connected devices for the purpose of managing diabetes.
Device Story
System provides continuous real-time monitoring of glucose and ketone (beta-hydroxybutyrate) levels; intended for diabetes management in patients 2+ years old. Device tracks trends/patterns; generates alarms for glycemic/ketone excursions; replaces fingerstick blood glucose testing for treatment decisions. Operates by autonomously communicating data to digitally connected devices (e.g., automated insulin dosing systems). Used by patients/caregivers in home or clinical settings. Healthcare providers use output to adjust acute/long-term therapy. Benefits include improved glycemic control and early detection of hyperketonemia through continuous data availability.
Clinical Evidence
No clinical data provided in the document. The order establishes special controls requiring robust clinical data demonstrating accuracy across the measuring range, comparison to FDA-accepted laboratory methods, and performance metrics (e.g., MARD, percentage of readings within ±15/20/40% of reference) for both glucose and ketone sensors in adult and pediatric populations.
Technological Characteristics
Integrated continuous glucose ketone monitoring system (iCGK). Features glucose and ketone sensors; autonomous data transmission to digitally connected devices. Requires design verification/validation for sensor accuracy, rate of change performance, and data transmission security. Must demonstrate performance in presence of interfering substances. Includes measures to prevent use beyond claimed sensor wear period.
Indications for Use
Indicated for diabetes management in persons age 2 years and older. Monitors glucose and beta-hydroxybutyrate levels in real-time; detects hyperglycemia, hypoglycemia, and hyperketonemia.
Regulatory Classification
Identification
The Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System is a prescription device indicated for the management of diabetes in persons age 2 years and older. It is intended to monitor glucose and ketone (beta-hydroxybutyrate) levels in real-time. The system provides alarms, detects trends, tracks glucose and ketone patterns, and aids in the detection of episodes of hyperglycemia, hypoglycemia, and hyperketonemia. It replaces blood glucose testing for diabetes treatment decisions and is intended to autonomously communicate with digitally connected devices for the purpose of managing diabetes.
Submission Summary (Full Text)
{0}

August 26, 2026
Abbott Diabetes Care
Katherine Doll Kanne
Regulatory Affairs Manager
1360 S. Loop Rd.
Alameda, California 94502
Re: DEN250049
Trade/Device Name: Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System
Regulation Number: 21 CFR 862.1354
Regulation Name: Integrated continuous glucose ketone monitoring system
Regulatory Class: Class II
Product Code: SJD
Dated: September 26, 2025
Received: September 29, 2025
Dear Katherine Doll Kanne:
This letter corrects our previous classification order, dated August 25, 2026, to correct an inconsistency in labeling special control (7)(i).
The Center for Devices and Radiological Health (CDRH) of the Food and Drug Administration (FDA) has completed its review of your De Novo request for classification of the Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System, a prescription device with the following indications for use:
Libre Duo 10 Day is a Continuous Dual Glucose Ketone Monitoring System indicated for the management of diabetes in persons age 2 years and older. It is intended to monitor glucose and ketone (beta-hydroxybutyrate) levels in real-time.
The System also provides alarms, detects trends, tracks glucose and ketone patterns, and aids in the detection of episodes of hyperglycemia, hypoglycemia, and hyperketonemia, facilitating both acute and long-term therapy adjustments, and the system replaces blood glucose testing for diabetes treatment decisions, unless otherwise indicated. Interpretation of system readings should be based on the trends and sequential readings over time. When making therapeutic adjustments, ketone output should be used in conjunction with glucose levels, symptoms, and factors that may affect ketone levels such as eating patterns and exercise.
The System is also intended to autonomously communicate with digitally connected devices. The System can be used alone or in conjunction with these digitally connected devices for the purpose of managing diabetes.
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
{1}
DEN250049 - Katherine Doll Kanne
Page 2
FDA concludes that this device should be classified into Class II. This order, therefore, classifies the Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System, and substantially equivalent devices of this generic type, into Class II under the generic name integrated continuous glucose ketone monitoring system.
FDA identifies this generic type of device as:
**Integrated continuous glucose ketone monitoring system.** An integrated continuous glucose ketone monitoring system (iCGK) is intended to automatically measure glucose and/or ketones in bodily fluids continuously or frequently for a specified period of time. iCGK systems are designed to reliably and securely transmit glucose and/or ketone measurement data to digitally connected devices, including automated insulin dosing systems, and are intended to be used alone or in conjunction with these digitally connected medical devices for the purpose of managing a disease or condition related to glycemic control or ketone fluctuation.
Section 513(f)(2) of the Food, Drug and Cosmetic Act (the FD&C Act) was amended by section 607 of the Food and Drug Administration Safety and Innovation Act (FDASIA) on July 9, 2012. This law provides two options for De Novo classification. First, any person who receives a "not substantially equivalent" (NSE) determination in response to a 510(k) for a device that has not been previously classified under the Act may request FDA to make a risk-based classification of the device under section 513(a)(1) of the Act. On December 13, 2016, the 21st Century Cures Act removed a requirement that a De Novo request be submitted within 30 days of receiving an NSE determination. Alternatively, any person who determines that there is no legally marketed device upon which to base a determination of substantial equivalence may request FDA to make a risk-based classification of the device under section 513(a)(1) of the Act without first submitting a 510(k). FDA shall, within 120 days of receiving such a request, classify the device. This classification shall be the initial classification of the device. Within 30 days after the issuance of an order classifying the device, FDA must publish a notice in the Federal Register announcing the classification.
On September 29, 2025, FDA received your De Novo requesting classification of the Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System. The request was submitted under section 513(f)(2) of the FD&C Act. In order to classify the Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System into class I or II, it is necessary that the proposed class have sufficient regulatory controls to provide reasonable assurance of the safety and effectiveness of the device for its intended use. After review of the information submitted in the De Novo request, FDA has determined that, for the previously stated indications for use, the Libre Duo 10 Day Continuous Dual Glucose Ketone Monitoring System can be classified in class II with the establishment of special controls for class II. FDA believes that class II (special) controls provide reasonable assurance of the safety and effectiveness of the device type. The identified risks and mitigation measures associated with the device type are summarized in the following table:
| Risks to Health | Mitigation Measures |
| --- | --- |
| Clinical action based on falsely high or falsely low inaccurate glucose values or inaccurate alerts may lead to inappropriate treatment decisions. | Certain design verification and validation, including documentation of certain studies. Certain labeling information, including certain limiting statements and performance characteristics. |
{2}
DEN250049 - Katherine Doll Kanne
Page 3
| Risks to Health | Mitigation Measures |
| --- | --- |
| Clinical action based on falsely high or falsely low inaccurate ketone values, inaccurate ketone trends, or inaccurate alerts may lead to inappropriate treatment decisions. | Certain design verification and validation, including documentation of certain studies. Certain labeling information, including certain limiting statements and performance characteristics. |
| User misunderstanding of device outputs, contraindications, warnings, precautions, or limitations leading to inappropriate user actions that adversely impact diabetes management. | Certain design verification and validation, including documentation of certain studies. Certain labeling information, including certain limiting statements and performance characteristics. |
| The inability to make appropriate treatment decisions when glucose or ketone values are unavailable due to sensor signal drop-out or loss of communication with digitally connected devices. | Certain design verification and validation, including documentation of certain studies. Certain labeling information, including certain limiting statements and performance characteristics. |
In combination with the general controls of the FD&C Act, the integrated continuous glucose ketone monitoring system is subject to the following special controls:
(1) Design verification and validation must include the following:
(i) Robust clinical data from a clinical study demonstrating the accuracy of the device in the intended use population and throughout the measuring range of the device for each analyte.
(ii) The clinical data must include a comparison between the iCGK glucose sensor values and blood glucose values in specimens collected in parallel that are measured on an FDA-accepted laboratory-based glucose measurement method that is precise and accurate, and that is traceable to a higher order (e.g., an internationally recognized reference material and/or method).
(iii) The clinical data must include a comparison between the iCGK ketone sensor values and blood ketone values in specimens collected in parallel that are measured on an FDA-accepted laboratory-based ketone measurement method.
(iv) Clinical study results must demonstrate consistent analytical and clinical performance throughout the sensor wear period.
(v) Clinical study results for the iCGK glucose sensor in the adult population must meet the following performance requirements:
(A) For all iCGK glucose sensor measurements less than 70 milligrams/deciliter (mg/dL), the percentage of iCGK measurements within ±15 mg/dL of the corresponding blood glucose value must be calculated, and the lower one-sided 95 percent confidence bound must exceed 85 percent.
(B) For all iCGK glucose sensor measurements from 70 mg/dL to 180 mg/dL, the percentage of iCGK measurements within ±15 percent of the corresponding blood glucose value must be calculated, and the lower one-sided 95 percent confidence bound must exceed 70 percent.
(C) For all iCGK glucose sensor measurements greater than 180 mg/dL, the percentage of iCGK measurements within ±15 percent of the corresponding blood glucose value
{3}
DEN250049 - Katherine Doll Kanne
Page 4
must be calculated, and the lower one-sided 95 percent confidence bound must exceed 80 percent.
(D) For all iCGK glucose sensor measurements less than 70 mg/dL, the percentage of iCGK measurements within ±40 mg/dL of the corresponding blood glucose value must be calculated, and the lower one-sided 95 percent confidence bound must exceed 98 percent.
(E) For all iCGK glucose sensor measurements from 70 mg/dL to 180 mg/dL, the percentage of iCGK measurements within ±40 percent of the corresponding blood glucose value must be calculated, and the lower one-sided 95 percent confidence bound must exceed 99 percent.
(F) For all iCGK glucose sensor measurements greater than 180 mg/dL, the percentage of iCGK measurements within ±40 percent of the corresponding blood glucose value must be calculated, and the lower one-sided 95 percent confidence bound must exceed 99 percent.
(G) Throughout the device measuring range, the percentage of iCGK glucose sensor measurements within ±20 percent of the corresponding blood glucose value must be calculated, and the lower one-sided 95 percent confidence bound must exceed 87 percent.
(H) When iCGK glucose sensor values are less than 70 mg/dL, no corresponding blood glucose value shall read above 180 mg/dL.
(I) When iCGK glucose sensor values are greater than 180 mg/dL, no corresponding blood glucose value shall read less than 70 mg/dL.
(J) There shall be no more than 1 percent of iCGK glucose sensor measurements that indicate a positive glucose rate of change greater than 1 mg/dL per minute (/min) when the corresponding true negative glucose rate of change is less than -2 mg/dL/min as determined by the corresponding blood glucose measurements.
(K) There shall be no more than 1 percent of iCGK glucose sensor measurements that indicate a negative glucose rate of change less than -1 mg/dL/min when the corresponding true positive glucose rate of change is greater than 2 mg/dL/min as determined by the corresponding blood glucose measurements.
(vi) Clinical study results for the iCGK ketone sensor in the adult population must meet the following performance requirements:
(A) The iCGK ketone sensor accuracy and rate of change performance shall be adequate to ensure clinically acceptable agreement, as determined by FDA.
(B) When iCGK ketone sensor values are less than 0.6 mmol/L, no corresponding blood ketone value shall be above 3.0 mmol/L.
(C) When iCGK ketone sensor values are greater than 3.0 mmol/L, no corresponding blood ketone value shall be less than 0.6 mmol/L.
(vii) Data demonstrating similar accuracy and rate of change performance of the iCGK in the pediatric population as compared to that in the adult population, or alternatively a clinical and/or technical justification for why pediatric data are not needed, must be provided and determined by FDA to be acceptable and appropriate.
(viii) Data must demonstrate that throughout the claimed sensor life, the device does not allow clinically significant gaps in sensor data availability that would prevent any digitally connected devices from achieving their intended use.
{4}
DEN250049 - Katherine Doll Kanne
Page 5
(2) Design verification and validation must include a detailed strategy to ensure secure and reliable means of iCGK data transmission to provide real-time glucose and ketone readings at clinically meaningful time intervals to devices intended to receive the glucose and ketone data.
(3) Design verification and validation must include adequate controls established during manufacturing and at product release to ensure the released product meets the required performance specifications.
(4) The device must demonstrate clinically acceptable performance in the presence of clinically relevant levels of potential interfering substances that are reasonably present in the intended use population, including but not limited to endogenous substances and metabolites, foods, dietary supplements, and medications.
(5) The device must include appropriate measures to ensure that disposable sensors cannot be used beyond its claimed sensor wear period.
(6) Design verification and validation must include results obtained through a usability study that demonstrates that the intended user can use the device safely and obtain the expected glucose and ketone measurement accuracy.
(7) The required labeling must include a separate description of the following sensor performance data observed in the clinical study for each intended use population and analyte, in addition to separate sensor performance data for each different iCGK insertion or use sites (e.g., abdomen, arm, buttock):
(i) A description of the iCGK glucose accuracy in the following blood glucose concentration ranges: less than 54 mg/dL, 54 mg/dL to less than 70 mg/dL, 70 to 180 mg/dL, greater than 180 to 250 mg/dL, and greater than 250 mg/dL.
(ii) A description of the iCGK ketone accuracy in the following blood ketone concentration ranges: less than 0.6 mmol/L, 0.6 to 1.5 mmol/L, greater than 1.5 to 3.0 mmol/L, and greater than 3.0 mmol/L.
(iii) A description of the accuracy of positive and negative rate of change data.
(iv) A description of the frequency and duration of gaps in sensor data.
(v) A description of the true, false, missed, and correct alert rates and a description of the available glucose and ketone concentration alert settings, if applicable.
(vi) A description of the observed duration of iCGK life for the device.
In addition, this is a prescription device and must comply with 21 CFR 801.109.
Although this letter refers to your product as a device, please be aware that some granted products may instead be combination products. If you have questions on whether your product is a combination product, contact CDRHProductJurisdiction@fda.hhs.gov.
Section 510(m) of the FD&C Act provides that FDA may exempt a class II device from the premarket notification requirements under section 510(k) of the FD&C Act, if FDA determines that premarket notification is not necessary to provide reasonable assurance of the safety and effectiveness of the device type. FDA has determined premarket notification is necessary to provide reasonable assurance of the safety and effectiveness of the device type and, therefore, the device is not exempt from the premarket notification requirements of the FD&C Act. Thus, persons who intend to market this device type must submit a premarket notification containing information on the integrated continuous glucose ketone monitoring system they intend to market prior to marketing the device.
{5}
DEN250049 - Katherine Doll Kanne
Page 6
Please be advised that FDA's decision to grant this De Novo request does not mean that FDA has made a determination that your device complies with other requirements of the FD&C Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the FD&C Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801 and 809); medical device reporting (reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and if applicable, the electronic product radiation control provisions (Sections 531-542 of the FD&C Act; 21 CFR 1000-1050).
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System Rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
A notice announcing this classification order will be published in the Federal Register. A copy of this order and supporting documentation are on file in the Dockets Management Branch (HFA-305), Food and Drug Administration, 5630 Fishers Lane, Room 1061, Rockville, MD 20852 and are available for inspection between 9 a.m. and 4 p.m., Monday through Friday.
As a result of this order, you may immediately market your device as described in the De Novo request, subject to the general control provisions of the FD&C Act and the special controls identified in this order.
For comprehensive regulatory information about medical devices and radiation-emitting products, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
{6}
DEN250049 - Katherine Doll Kanne
Page 7
If you have any questions concerning the contents of the letter, please contact McKenna Tennant at 301-837-7377.
Sincerely,
**Marianela Perez-Torres -S**
Marianela Perez-Torres, Ph.D.
Director
Division of Chemistry and
Toxicology Devices
OHT7: Office of In Vitro Diagnostics
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
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.