The Monica AN24 is an intrapartum maternal-fetal monitor that non-invasively measures and displays fetal heart rate (FHR), uterine activity (UA) and maternal heart rate(MHR). The AN24 aquires and displays the FHR tracing from abdominal surface electrodes that pick up the fetal ECG (fECG) signal. Using the same surface electrodes, the AN24 also acquires and displays the UA tracing from the uterine electromyography (EMG) signal and the MHR tracing from the maternal ECG signal (mECG). The AN24 is indicated for use on women who are at term (>36 completed weeks), in labor, with singleton pregnancies, using surface electrodes on the maternal abdomen. The AN24 maternal-fetal monitor is intended for use by healthcare professionals in a clinical setting.
Device Story
Monica AN24 is a battery-powered, non-invasive electrophysiological monitor for labor and delivery. It uses five surface electrodes placed on the maternal abdomen to capture fetal ECG (fECG), maternal ECG (mECG), and uterine electromyography (EMG) signals. The device processes these electrical signals to continuously extract and display Fetal Heart Rate (FHR), Maternal Heart Rate (MHR), and Uterine Activity (UA). Unlike traditional Doppler ultrasound or tocodynamometer (TOCO) monitors that measure mechanical intervals or pressure, the AN24 detects electrical RR intervals and uterine muscle activity directly. Operated by healthcare professionals in clinical settings, the device provides real-time tracings to assist in assessing fetal well-being and identifying fetal heart rate confusion. The output is displayed in standard clinical formats, aiding clinicians in labor management decisions.
Clinical Evidence
Prospective equivalence study of 60 term, laboring women. Compared Monica AN24 against Philips 50XM (Doppler/TOCO) and SpO2 pulse oximeter (MHR). Primary endpoints: MHR reliability and accuracy. Results: AN24 MHR mean success rate 99.3% vs 87.8% for SpO2. RMS error for MHR was 4.49 BPM (95% CI: 3.46–5.52 BPM), with a correlation of 0.90. Limits of agreement were -11.47 to +11.62 BPM. Study confirmed AN24 is as accurate and reliable as predicate devices.
Technological Characteristics
Battery-powered electrophysiological monitor. Uses 5 surface electrodes for 3-channel acquisition of fECG, mECG, and uterine EMG. Standards: IEC 60601-1 (electrical safety), IEC 60601-1-2 (EMC), IEC 60601-1-2-47 (electrocardiographs), ISO 10993 (biocompatibility), ISO 14385 (QMS). Continuous extraction of FHR, MHR, and UA from electrical signals.
Indications for Use
Indicated for intrapartum monitoring of women at term (>36 weeks gestation) with singleton pregnancies in labor. Used to measure and display fetal heart rate, maternal heart rate, and uterine activity via abdominal surface electrodes.
Regulatory Classification
Identification
An external uterine contraction monitor (i.e., the tokodynamometer) is a device used to monitor the progress of labor. It measures the duration, frequency, and relative pressure of uterine contractions with a transducer strapped to the maternal abdomen. This generic type of device may include an external pressure transducer, support straps, and other patient and equipment supports.
{0}------------------------------------------------

**monca**
Healthcare
## K112390 510(K) Summary
#### Monica AN24
JUL 1 3 2012
Submitters Name:
lan How Monica Healthcare Ltd Biocity Pennyfoot Street · Nottingham NG1 1GF UK
Tel: +44 (0)115 912 4541 Email: ianhow@monicahealthcare.com
Name of Device: Monica AN24
#### Manufactured by:
Monica Healthcare Ltd Biocity Pennyfoot Street Nottingham NG1 1GF വര
Date of Summary: 21st May 2012
Classification Name: 21 CFR 884.270 System Monitoring Perinatal
Predicate Device: Philips 50XM (K954351)
#### Device Description:
The Monica AN24™ is a small, battery-powered device for L&D surveillance of fetal well-being. The AN24™ is designed to passively monitor Fetal Heart Rate (FHR)), maternal heart rate (MHR) and Uterine Activity (UA) during pregnancy and can be used at any time from > 36 completed weeks gestation in laboring patients. The AN24™ is suitable for singleton pregnancies only.
#### Intended Use:
The Monica AN24 is an intrapartum maternal-fetal monitor that non-invasively measures and displays fetal heart rate (FHR), maternal heart rate (MHR) and uterine activity (UA). The AN24 acquires and displays the FHR & MHR tracing from abdominal surface electrodes that pick up the fetal ECG (fECG) and maternal ECG (mECG) signal. Using the same surface electrodes, the AN24 also acquires and displays the UA tracing from the uterine electromyography (EMG) signal. The AN24 is indicated for use on women who are at term (>36 completed weeks), in labor, with singleton pregnancies, using surface electrodes on the maternal abdomen.
The AN24 maternal-fetal monitor is intended for use by healthcare professionals in a clinical setting.
#### Technology Characteristics:
The Monica AN24 is a small, battery powered electrophysiological monitor (specifically fetal ECG, maternal ECG and uterine EMG). The electrical signals are passively monitored on three channels using five electrodes placed on the pregnant abdomen in specific locations. From these electrical signals the Fetal Heart Rate (FHR), maternal heart rate (MHR) and Uterine Activity (UA) are continuously extracted and displayed in the same standard format as the predicate device.
The detection technology of the Monica AN24 differs from the predicate device which uses Doppler ultrasound to measure Fetal Heart Rate (FHR) and maternal heart rate (MHR), and a tocodynamometer (TOCO) to measure Uterine Activity
{1}------------------------------------------------
Image /page/1/Picture/0 description: The image shows the logo for Monica Healthcare. The logo features the word "monica" in a stylized font, with a figure of a person above the "i". Below the word "monica" is the word "Healthcare". The logo is simple and clean, and it is likely used to represent the company's brand.
(UA). The predicate device detects the mechanical RR interval of the fetal heart whilst the Monica AN24 detects the electrical RR interval. However, from this data both instruments produce the same output i.e. fetal heart rate and maternal heart rate (expressed as number of heart beats per minute).
Uterine activity in the Monica AN24 is derived from the electrohysterogram which is the electric signal of the contracting/moving uterine muscle. The uterine activity in the TOCO predicate is derived from an external strain gauge to measure the abdominal pressure of the contracting/moving uterine muscle. However from this data both instruments produce the same uterine activity output trace.
For the actual detection of FHR, MHR and UA the Monica AN24 does not emit any energy into the patient and hence the above differences in detection technology do not raise any new type of safety and effectiveness questions. In addition for FHR, MHR and uterine activity both the AN24 and predicate device are external, skin contacting devices. Differences in materials in contact with the patient are resolved with biocompatibility testing and compliance with standards.
To ensure clinical effectiveness the clinical performance data was collected as described in the "Clinical Study" section below. This study demonstrates that the Monica AN24 device is at least as accurate and reliable as the predicate device for monitoring both FHR and UA.
In summary, the differences in technology between the AN24 and the e predicate device do not affect safety or effectiveness.
Clinical Study
#### Introduction
This section summarizes the clinical equivalence trial supporting the effectiveness of the Monica AN24. The study enrolled 60 women at term, in labor, at two clinical sites, of which 33 women contributed to the Matrenal Heart Rate (MHR), the key statistics are :
### Study Design
#### Study Objective
The study was designed as a prospective, equivalence study (for FDA approval purposes) for determining the performance of a trans-abdominal fetal ECG/EHG monitor (Monica AN24) when compared with an external Doppler ultrasound/tocodynamometer CTG monitor (Philips 50XM) during the first and second stage of labour. No additional invasive monitoring was performed purely for this study. Additionally, the maternal heart rate was monitored by a pulse oximeter, and it is this data that is used here to demonstrate MHR equivalence.
#### Inclusion Criteria:
The inclusion criteria were: subjects with singleton, term (≥ 37 weeks) pregnancies, giving birth in the hospital, who were able to be simultaneously monitored with Monica AN24 (FHR + UA), Doppler U/S FHR, Scalp ECG FHR, Toco UA, and IUPC UA, and who required internal monitoring (ie scalp ECG and/or IUPC).
#### Exclusion Criteria:
Subjects were excluded if: any transducer could not be optimally placed; if the fetus had a confirmed major malformation or chromosomal abnormality; if the subject had been involved in another clinical trial during this pregnancy; or if in the investigators opinion the subject was in a bad condition or otherwise not capable of taking part.
{2}------------------------------------------------
Image /page/2/Picture/0 description: The image shows a logo for Monica Healthcare. The logo has the word "monica" in a stylized font, with the "i" replaced by a stick figure. Below the word "monica" is the word "Healthcare" in a smaller, simpler font. The logo is black and white.
### Study Methodology
The Monica AN24 has been demonstrated to be substantially equivalent to existing predicate devices for monitoring of FHR and UA during labor and delivery (FDA clearance under K101801). However, the AN24 can also produce an MHR trace, which can be clinically useful either for maternal monitoring, or to identify fetal heart rate confusion if it occurs. This study demonstrates the equivalence of the Monica AN24 to a predicate SPO2 pulse oximeter (Philips M1191A) which produces an MHR trace when connected to a series 50 fetal monitor.
The study demonstrates that the alternative monitoring technique (maternal ECG monitoring), as used by the Monica AN24, is equivalent to the predicate. This includes showing that the device itself is capable of making these recordings safely and effectively, that the electrode positioning used for fetal monitoring (ie abdominal electrodes) does not prevent detection of the maternal ECG, and that the presence of the fetal ECG in the signal does not prevent accurate detection of the MHR from the ECG signal.
#### Outcome Measures
Both the Monica AN24 (MHR) and the predicate devices (Sp02) were compared. Monica AN24 was tested against the predicates using null hypotheses of inferiority and alternative hypotheses of non-inferiority, for the measurement of MHR.
#### Results
This section summarizes the results that confirm equivalence between Monica AN24 and the existing predicate device.
Maternal Heart Rate Equivalence:
#### Labor and Delivery:
- Reliability: Success rate:
- o AN24 MHR Mean SR: 99.3%
- o SPO2 MHR Mean SR: 87.8%
- o SR Ratio (AN24/SPO2) Mean: 1.16, Cl: 1.08 1.21
- Lower limit of Cl > 0.8, so equivalence criterion met
(Note: log transform applied to calculate CI due to skew)
- Accuracy: RMS error
- Combined RMS error between AN24 and SPO2 mean: 4.49 BPM, CI: 3.46 - 5.52 BPM
- Correlation between AN24 and SPO2 MHR traces mean: 0.90, CI 0.87 -0.93
- o The 95% limits of agreement are -11.47 bpm to +11.62 bpm. We estimate the maternal heart rate measured by the AN24 to be between 11.47 bpm less than the Sp02 and 11.62bpm greater.
### Statement of Equivalence
The results shown in Section meet the accuracy and reliability criteria for substantial equivalence. This demonstrates that the Monica AN24 is substantially equivalent to an SPO2 pulse oximeter for monitoring maternal heart rate during labor and delivery.
{3}------------------------------------------------
K112390 page 4 of 4
Image /page/3/Picture/1 description: The image shows the logo for Monoca Healthcare. The logo features the word "Monoca" in a stylized font, with a stick figure incorporated into the design. Below the word "Monoca" is the word "Healthcare" in a smaller font.
### Acknowledgements
Monica Healthcare Ltd, UK, would like to thank: the clinical teams at QHC, New York and Temple University, Philadelphia for undertaking this study and the USA mothers who kindly agreed to take part in the study.
#### Non Clinical Test Summary
The Monica AN24 and Accessories comply with voluntary standards. The standards were employed in the following areas:
- Electrical Safety .
- EMC
- Material Safety
- Software Validation
#### Conclusion
The non clinical tests used voluntary standards employed at accredited independent test facilities to demonstrate that the Monica AN24 is as safe and effective in performance to the predicate device, the main standards employed were
- IEC60601-1 electrical safety
- IEC60601-1-2 EMC
- IEC 60601-1-2-47 Performance standard for electrocardiographs
- IEC60601-1-4 Software
- ISO10993 Biocompatibility
- ISO14385 QMS
To demonstrate that the Monica AN24 is as clinically safe and effective as the predicate device, the clinical study described above measured the clinical performance of the Monica AN24 against the predicate device. The Monica AN24 showed that in a clinical setting
The mean AN24 reliability is 99.3% (CI 95% = 98.5%; 100%).
The mean SPO2 reliability is 87.8% (CI 95% = 83.2%; 92.5%).
Reliability is measured by the difference of the success rates of the AN24 MHR and SPO2 MHR for each patient.
The mean MHR RMS error is 4.489 BPM (Cl g5% = 3.416 BPM; 5.562 BPM).
Note that this RMS error is comparable to values given by the manufacturers of SPO2 sensors for MHR accuracy in the presence of movement (GE/Masimo sensor, pulse rate error (±1 S.D.) of ±3 BPM with no motion, or ±5 BPM with motion (4)).
The mean Pearson correlation coefficient (secondary statistics) is 0.9 (Cl 95% = 0.877; 0.924).
The higher limit of the 95% CI of the MHR RMS error is 5.381 BPM, lower than the 7BPM equivalence threshold and accuracy equivalence is demonstrated.
The 95% limits of agreement are -11.47 bpm to +11.62 bpm. We estimate the maternal heart rate measured by the AN24 to be between 11.47 bpm less than the Sp02 and 11.62bpm greater.
The conclusions drawn from the nonclinical tests and clinical study demonstrate that the Monica AN24 is as safe, as effective and performs as safely and effectively as the legally marketed predicate device.
{4}------------------------------------------------
# DEPARTMENT OF HEALTH & HUMAN SERVICES
Image /page/4/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a stylized caduceus symbol, which is a staff with two snakes coiled around it, and the text "DEPARTMENT OF HEALTH & HUMAN SERVICES USA" arranged in a circular fashion around the symbol. The logo is black and white.
#### Public Health Service
Food and Drug Administration 10903 New Hampshire Avenue Document Control Room -WO66-G609 Silver Spring, MD 20993-0002
Mr. Ian How Regulatory Affairs Manager Monica Healthcare Ltd. Biocity, Pennyfoot Street NOTTINGHAM NG1 1GF UNITED KINGDOM
# JUL 1 3 2012
K112390 Re:
> Trade/Device Name: AN24 Regulation Number: 21 CFR§ 884.2720 Regulation Name: External uterine contraction monitor and accessories Regulatory Class: II Product Code: OSP Dated: July 3, 2012 Received: July 5, 2012
# Dear Mr. How:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it your device to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act that I Dri has made a aond regulations administered by other Federal agencies. You must or uny I varial studies the requirements, including, but not limited to: registration and listing Comply with an the Not 1 to 1 to (21 CFR Part 801); medical device reporting (reporting of medical
{5}------------------------------------------------
device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please of go to http://www.fda.gov/AboutFDA/CentersOffices/CDRH/CDRHOffices/ucm115809.htm for the Center for Devices and Radiological Health's (CDRH's) Office of Compliance. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to
http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.
You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address http://www.fda.gov/MedicalDevices/Resourcesfor You/Industry/default.htm.
Sincerely yours,
Sincerely yours,
Benjamin K. Evanko
Benjamin R. Fisher, Ph.D. Director Division of Reproductive, Gastro-Renal, and Urological Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image shows the logo for Monica Healthcare. The logo features the word "Monica" in bold, sans-serif font, with a stylized image of a pregnant woman forming the "i" in "Monica". Below the name is the word "Healthcare" in a smaller, lighter font.
# Indications for Use Statement
510(k) Number (if known):
Device Name: AN24
Indications for Use
The Monica AN24 is an intrapartum maternal-fetal monitor that non-invasively measures and displays f rich heart rate (FHR), uterine activity (UA) and maternal heart rate(MHR). The AN24 aquires and displays the FHR tracing from abdominal surface electrodes that pick up the fetal ECG (fECG) signal. Using the same surface electrodes, the AN24 also acquires and displays the UA tracing from the Using the banded of CMG) signal and the MHR tracing from the maternal ECG signal (mECG). The AN24 is indicated for use on women who are at term (>36 completed weeks), in labor, with singleton pregnancies, using surface electrodes on the maternal abdomen.
on groght.1000, abing of as intended for use by healthcare professionals in a clinical setting.
The AN24 maternal-fetal monitor is intended for use by healthcare professionals in a clinical setting.
Prescription Use (Part 21 CFR 801 Subpart D) AND/OR
Over-The-Counter Use (21 CFR 801 Subpart C)
(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of Device Evaluation (ODE)
Heim
(Division Sign-Off)
Division of Reproductive, Gastro-Renal, and
Page 1 of 1
(Division Sign-Off)
Division of Reproductive, Gastro-Renal, and
Urological Devices
510(k) Number K112390
Monica healthcare Ltd AN 24 510(K) Submission Rev 2 April 2010 Rev 1 Submission K081435
Section 1 Total Pages = 16
Page | 9
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.