The intended use of the CADScor System is to record heart sounds, murmurs and vibration for calculation of a patient specific score, indicating the risk of presence of coronary stenosis, as an aid in cardiac analysis and diagnosis.
Device Story
CADScor System records acoustic heart signals, including murmurs and vibrations; processes signals to calculate patient-specific risk score for coronary stenosis; serves as aid in cardiac analysis and diagnosis. Device intended for prescription use; clinical environment. Healthcare providers use output score to inform clinical decision-making regarding coronary artery disease risk. Benefits include non-invasive assessment of coronary stenosis risk.
Clinical Evidence
Special controls require clinical performance testing representative of the intended use population, including description of patient population and statistical techniques. No specific study results or metrics provided in the document.
Technological Characteristics
Digital stethoscope system comprising docking station, acoustic recording sensor, and single-use patch. Patch includes RFID tag for single-use enforcement. Biocompatibility per ISO 10993-1. Electrical safety per IEC 60601-1 and IEC 60601-1-2. Connectivity: sensor docks for charging/qualification. Algorithm: linear discriminant analysis and logistic regression.
Indications for Use
Indicated for patients suspected of ischemic heart disease to calculate a patient-specific risk score for coronary stenosis as an aid in cardiac analysis and diagnosis.
Regulatory Classification
Identification
A coronary artery disease risk indicator using acoustic heart signals is a device that records heart sounds including murmurs and vibrations to calculate a patient-specific risk of presence of coronary artery disease, as an aid in cardiac analysis and diagnosis.
Special Controls
In combination with the general controls of the FD&C Act. the coronary artery disease risk indicator using acoustic heart signals is subject to the following special controls:
- (1) Clinical performance testing must fulfill the following:
- a. Testing must include a discussion of the patient population and any statistical techniques used for analyzing the data; and
- b. Testing must be representative of the intended use population for the device. Any selection criteria or sample limitations must be fully described and justified.
- (2) Acoustic performance testing must evaluate microphone sensitivity, sound acquisition bandwidth, and amplitude accuracy. The acoustic sensor specifications and mechanism used to capture heart sounds must be described.
- (3) A scientific justification for the validity of the algorithm(s) must be provided. This justification must fulfill the following:
- a. All inputs and outputs of the algorithm must be fully described;
- b. The procedure for segmenting, characterizing and classifying the acoustic signal must be fully described; and
- c. This justification must include verification of the algorithm calculations and validation using an independent data set.
- (4) The patient-contacting components of the device must be demonstrated to be biocompatible.
- (5) Software verification, validation, and hazard analysis must be performed.
- (6) Human factors/usability testing must demonstrate that the user can correctly use the device, including device placement, based solely on reading the directions for use.
- (7) Performance data must demonstrate the electromagnetic compatibility (EMC) and electrical safety of the device.
- (8) Labeling must include the following:
- a. A description of what the device measures and outputs to the user;
- b. Instructions for proper placement of the device:
- c. Instructions on care and cleaning of the device;
- d. Warnings identifying sensor acquisition factors that may impact measurement results and instructions for mitigating these factors; and
- e. The expected performance of the device for all intended use populations and environments.
*Classification.* Class II (special controls). The special controls for this device are:(1) Clinical performance testing must fulfill the following:
(i) Testing must include a discussion of the patient population and any statistical techniques used for analyzing the data; and
(ii) Testing must be representative of the intended use population for the device. Any selection criteria or sample limitations must be fully described and justified.
(2) Acoustic performance testing must evaluate microphone sensitivity, sound acquisition bandwidth, and amplitude accuracy. The acoustic sensor specifications and mechanism used to capture heart sounds must be described.
(3) A scientific justification for the validity of the algorithm(s) must be provided. This justification must fulfill the following:
(i) All inputs and outputs of the algorithm must be fully described;
(ii) The procedure for segmenting, characterizing, and classifying the acoustic signal must be fully described; and
(iii) This justification must include verification of the algorithm calculations and validation using an independent data set.
(4) The patient-contacting components of the device must be demonstrated to be biocompatible.
(5) Software verification, validation, and hazard analysis must be performed.
(6) Human factors/usability testing must demonstrate that the user can correctly use the device, including device placement, based solely on reading the directions for use.
(7) Performance data must demonstrate the electromagnetic compatibility and electrical safety of the device.
(8) Labeling must include the following:
(i) A description of what the device measures and outputs to the user;
(ii) Instructions for proper placement of the device;
(iii) Instructions on care and cleaning of the device;
(iv) Warnings identifying sensor acquisition factors that may impact measurement results and instructions for mitigating these factors; and
(v) The expected performance of the device for all intended use populations and environments.
Submission Summary (Full Text)
{0}------------------------------------------------
# DE NOVO CLASSIFICATION REQUEST FOR CADSCOR SYSTEM
#### REGULATORY INFORMATION
FDA identifies this generic type of device as:
Coronary artery disease risk indicator using acoustic heart signals. A coronary artery disease risk indicator using acoustic heart signals is a device that records heart sounds including murmurs and vibrations to calculate a patient-specific risk of presence of coronary artery disease, as an aid in cardiac analysis and diagnosis.
NEW REGULATION NUMBER: 21 CFR 870.1420
CLASSIFICATION: Class II
PRODUCT CODE: OMW
#### BACKGROUND
DEVICE NAME: CADScor System
SUBMISSION NUMBER: DEN190047
DATE DE NOVO RECEIVED: November 4, 2019
#### SPONSOR INFORMATION:
Acarix A/S Mette Munch Ryvangs Alle 81-83 DK-2900 Hellerup Denmark
#### INDICATIONS FOR USE
The CADScor System is indicated as follows:
The intended use of the CADScor System is to record heart sounds, murmurs and vibration for calculation of a patient specific score, indicating the risk of presence of coronary stenosis, as an aid in cardiac analysis and diagnosis.
#### LIMITATIONS
The sale, distribution, and use of the CADScor System are restricted to prescription use in accordance with 21 CFR 801.109.
{1}------------------------------------------------
# PLEASE REFER TO THE LABELING FOR A COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.
#### DEVICE DESCRIPTION
The CADScor System is a digital stethoscope for recording and quantifying acoustic noise from micro-turbulence originating from stenosis of the coronary arteries. Computational processing of a recording obtained from the chest surface of a patient is used to determine a coronary artery disease (CAD) risk score and associated risk classification.
Three components make up the CADScor System: the Docking station, the Acoustic Recording Sensor and the Patch. The docking station is responsible for charging and qualifying the sensor. These functionalities only happen when the Acoustic Recording Sensor is in direct contact with the docking station. An LED light indicates the status of the sensor. The Acoustic Recording Sensor contains a display, a microphone and an on/off button. The heart sound is recorded through a microphone and once the CAD risk score is calculated, it appears on the display screen. The patch is directly in contact with the patient's chest at the fourth left inter costal space (IC4-L) region. The patch provides a tight seal between the chest surface and the microphone to reduce the external noise that is picked up by the sensor. The patch is for single use only and is discarded after a CAD-score is calculated. A radiofrequency identification (RFID) tag in the patch is used to prevent the patch from being used more than once.
Image /page/1/Picture/4 description: The image shows a gray, rectangular object with a white label on top, sitting on a silver platform. Next to it is a white, circular object with a small handle. The label on the rectangular object appears to have some text on it, but it is not clear enough to read. The silver platform has a slight incline, and the white circular object is slightly out of focus.
Figure 1. The three components of the CADScor System: Dacking station, Acoustic recording station, and Patch
An algorithm is used to calculate a coronary artery disease (CAD) risk score. The algorithm analyzes 8 features of the acoustic recording and three clinical features that are manually inputted into the device by the clinician. The clinical inputs are age, gender and presence of hypertension. The eight acoustic features are put through a linear discriminate analysis and then put through a logistic regression with the clinical features. The risk score and associated categorization color are displayed on the acoustic sensor screen. There are two risk categories: low risk and elevated risk (Figure 2). Clinicians can use the score and categorization to aid in a clinician's determination of whether further testing is needed for a CAD diagnosis.
| CAD-score ≤20 | CAD-score >20 |
|---------------|---------------|
| Low risk | Elevated risk |
| | | | | Figure 2. CAD score categorization | |
|--|--|--|--|------------------------------------|--|
|--|--|--|--|------------------------------------|--|
{2}------------------------------------------------
## SUMMARY OF NONCLINICAL/BENCH STUDIES
## BIOCOMPATIBILITY/MATERIALS
Biocompatibility testing was performed according to FDA Guidance "Use of International Standard ISO 10993-1, Biological evaluation of medical devices- Part 1: Evaluation and testing within a risk management process." The sponsor tested cytotoxicity, skin sensitization and skin irritation of the patch. The patch is intended to be on the patient for no longer than 45 minutes; therefore, the sponsor tested according to the guidelines for short-term, intact skin contact.
| Test | Purpose | Method | Acceptance Criteria | Results | |
|---------------|--------------------------------------------------------|-------------|------------------------------------------|---------|--|
| Cytotoxicity | To identify any<br>cytotoxic effects to the<br>patient | ISO 10993-1 | No evidence of<br>toxicity or cell lysis | PASS | |
| Sensitization | To identify tissue<br>reactions from the patch | ISO 10993-1 | No evidence of<br>tissue reaction | PASS | |
| Irritation | To identify tissue<br>irritation | ISO 10993-1 | No evidence of<br>tissue irritation | PASS | |
## ELECTROMAGNETIC COMPATIBILITY & ELECTRICAL SAFETY
The CADScor System conforms to the FDA-recognized standards for basic safety and essential performance of Medical Electrical Equipment. These standards include:
- IEC 60601-1-2:2014- Medical Electrical Equipment, Part 1-2: General . requirements for safety- Collateral Standard: Electromagnetic compatibility-Requirements and tests
- IEC 60601-1:2006 + A1:2013- Medical Electrical Equipment, Part 1: General . requirements for basic safety and essential performance
## SOFTWARE
Software documentation was provided in accordance with the FDA Guidance Document, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices," (issued May 11, 2005) for a Moderate Level of Concern (LOC). A Moderate LOC is deemed appropriate as malfunction of the device software or a latent design flaw in the device software may lead to an erroneous diagnosis or a delay in the delivery of appropriate medical care, which would likely result in minor injury but would likely not result in serious injury or death due to the availability of patient history, and vital signs to aid in the clinician's diagnosis.
{3}------------------------------------------------
Verification and validation testing were performed to confirm that the device software met the software requirements.
Algorithm unit testing was performed to demonstrate that the device software met the software requirements. This testing was performed using privately collected patient data. Additional details are provided in the "Summary of Clinical Information" section.
## PERFORMANCE TESTING - BENCH
Acoustic Performance Testing
Acoustic Performance testing was performed to determine that both the heart and ambient noise microphones function as expected and can correctly record the frequencies that are clinically meaningful for this device.
| Test | Purpose | Method | Acceptance Criteria | Results |
|-----------------------------------|---------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------|---------|
| Free Field Acoustic<br>Testing | Ensure the<br>manufactured parts of<br>the CADScor systems<br>are performing<br>according to test<br>specifications | (b) samples were<br>measured at (b)(4)<br>up to<br>(b)(4) Hz using a<br>loud speaker as a<br>source transmitter | Heart and ambient<br>microphone<br>sensitive within 5dB<br>throughout the<br>range of frequencies<br>tested | PASS |
| Microphone Sensitivity<br>Testing | Test microphone<br>sensitivity before and<br>after production | Set-up: Functional<br>generator for output<br>control, loud<br>speaker and B&K<br>(b)(4) sound level<br>meter with receiving<br>microphone | Sensitivity of the<br>heart and ambient<br>microphones are<br>stable at 5, 10, 20,<br>140 Hz before and<br>after the plotting<br>process | PASS |
| Acoustic Verification<br>Testing | Ensure the<br>manufactured CADScor<br>Sensor functionality<br>and performance | The calibration<br>frequency of (b)<br>(b)(4)<br>(b)(4) and (b)(4) Hz<br>were tested to<br>determine if the<br>sensor and ambient<br>noise detectors<br>respond.<br>Additionally, broad<br>band white noise<br>source signal was<br>tested. | The sensor and<br>ambient noise<br>detectors respond<br>uniformly to all<br>seven frequencies. | PASS |
## Mechanical Testing
| Test | Purpose | Method | Acceptance Criteria | Results |
|--------------------------------------------|--------------------------------------------------------------------------|------------------------------------|--------------------------------------------------------|---------|
| Mechanical Testing-<br>Design Verification | Verify the specified<br>geometric proportions<br>and mechanical lifetime | Force Tests.<br>Dimensions of each | Manufactured to<br>correct dimension<br>specifications | PASS |
{4}------------------------------------------------
| | for the following<br>components of the<br>CADScor system:<br>mechanical couplers,<br>electrical contacts,<br>sensor push button and<br>dimensions and weight | component of the<br>device | Force to remove<br>sensor from docking<br>station is 5N.<br>Qualification<br>successful before<br>and after 1000<br>insertions of the<br>sensor onto the<br>docking station | |
|--|--------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--|
|--|--------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--|
# USABILITY TESTING
Usability Testing was provided in accordance with the FDA Guidance Document, "Applying Human Factors and Usability Engineering to Medical Devices- Guidance for Industry and Food and Drug Administration Staff" (issued February 02, 2016).
IDE C subjects belonging to a user group of medical doctors/physicians with valid medical authorization, subjects belonging to a user group of registered nurses with valid authorization and @ @04) subjects belonging to a user group of service technicians (non-clinical user group) participated in the usability testing. The testing was performed in a simulated- use environment using a sequence of tasks including but not limited to correct patch positioning of the device on the patient's chest. entering clinical features and other inputs correctly, and reading the display text and symbols/icons.
## SUMMARY OF CLINICAL INFORMATION
A prospective, multicenter, randomized clinical study was conducted to support the safety and effectiveness of the CADScor System for the proposed indication for use. Subjects were over the age of years and were suspected of ischemic heart disease. To determine the subject's diagnosis, which was compared to the result of the CADScor System, the patient underwent coronary computed tomography angiography (CCTA). Subjects who are diagnosed via CCTA to have CAD are defined to have at least one significant stenosis, which has a minimum 11% diameter reduction (DS) of a coronary vessel. Subjects who are classified as Non-CAD are defined as having CT calcium score of zero and no CT stenosis. The primary objective of this study is to determine specificity and sensitivity of the CAD-score in patients with lowintermediate risk for ischemic heart disease.
The device was tested on 100 patients, who were independent from the algorithm training set. The patient population had a 10.7% prevalence of coronary artery disease. The results show that the sensitivity, specificity and area under the curve for the testing group are 87.5%, 37.5% and 71.5%, respectively, for the threshold score of 20. The positive value (PPV) and negative predictive value (NPV) were reported to be 14.4% and 96.2%, respectively, With the NPV of 96.2%, the Agency has determined that this device could be beneficial for clinicians to use as a "rule-out" device for patients over the age of thears who are presenting with symptoms of ischemic heart disease.
{5}------------------------------------------------
# Pediatric Extrapolation
In this De Novo request, existing clinical data were not leveraged to support the use of the device in a pediatric patient population.
## LABELING
The labeling of the device satisfies the special controls listed below:
- A description of what the device measures and outputs to the user; .
- Instructions for proper placement of the device; .
- Instructions on care and cleaning of the device; .
- . Warnings identifying sensor acquisition factors that may impact measurement results and instructions for mitigating these factors
- . The expected performance of the device for all intended use populations and environments.
# RISKS TO HEALTH
The table below identifies the risks to health that may be associated with use of the coronary artery disease risk indicator using acoustic heart signals and the measures necessary to mitigate these risks.
| Identified Risks to Health | Mitigation Measures |
|------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Adverse tissue reaction | Biocompatibility evaluation,<br>Labeling, and<br>Usability testing |
| Skin burn/irritation | Electrical safety testing, and<br>Electromagnetic compatibility testing |
| False positive leading to<br>unnecessary medical<br>procedures | Software verification, validation, and hazard analysis;<br>Usability testing;<br>Acoustic performance testing<br>Clinical performance testing; and<br>Labeling |
| False negative leading to failure<br>to detect coronary artery<br>disease | Software verification, validation, and hazard analysis;<br>Usability testing;<br>Acoustic performance testing;<br>Clinical performance testing; and<br>Labeling |
| Delay in calculation due to<br>device failure resulting in a<br>delay of treatment | Software verification, validation, and hazard analysis; |
| | Clinical performance testing; |
| | Usability testing;<br>Acoustic performance testing; and<br>Labeling |
{6}------------------------------------------------
## SPECIAL CONTROLS
In combination with the general controls of the FD&C Act. the coronary artery disease risk indicator using acoustic heart signals is subject to the following special controls:
- (1) Clinical performance testing must fulfill the following:
- a. Testing must include a discussion of the patient population and any statistical techniques used for analyzing the data; and
- b. Testing must be representative of the intended use population for the device. Any selection criteria or sample limitations must be fully described and justified.
- (2) Acoustic performance testing must evaluate microphone sensitivity, sound acquisition bandwidth, and amplitude accuracy. The acoustic sensor specifications and mechanism used to capture heart sounds must be described.
- (3) A scientific justification for the validity of the algorithm(s) must be provided. This justification must fulfill the following:
- a. All inputs and outputs of the algorithm must be fully described;
- b. The procedure for segmenting, characterizing and classifying the acoustic signal must be fully described; and
- c. This justification must include verification of the algorithm calculations and validation using an independent data set.
- (4) The patient-contacting components of the device must be demonstrated to be biocompatible.
- (5) Software verification, validation, and hazard analysis must be performed.
- (6) Human factors/usability testing must demonstrate that the user can correctly use the device, including device placement, based solely on reading the directions for use.
- (7) Performance data must demonstrate the electromagnetic compatibility (EMC) and electrical safety of the device.
- (8) Labeling must include the following:
- a. A description of what the device measures and outputs to the user;
- b. Instructions for proper placement of the device:
- c. Instructions on care and cleaning of the device;
- d. Warnings identifying sensor acquisition factors that may impact measurement results and instructions for mitigating these factors; and
- e. The expected performance of the device for all intended use populations and environments.
## BENEFIT-RISK DETERMINATION
The risks associated with use of the device are based on data collected in a clinical study described above. One risk to a patient is myocardial infarction. This poses a risk to patients when they receive a false negative result where they are classified as "low risk" but may have needed to go through further testing to determine that their symptoms are from CAD. The probability of this occurring is low because the negative predictive value (NPV) is 96.2%. Additionally, the clinician is not intended to use this device as a sole diagnostic decision maker and are instructed in the labeling to recommend to patients categorized in the low risk group to seek medical attention if their symptoms persist or worsen.
{7}------------------------------------------------
A risk to a patient categorized in the "elevated risk" group can be excessive testing but are found to be "low risk" after further testing. With a relatively low specificity, it is expected that a false positive result could lead to unnecessary testing. However, without this device, it is likely that the entire patient population would undergo other tests, i.e. stress tests.
Additionally, tissue irritation could occur from the patch: however, the probability of this occurring is very low because no adverse events occurred during the biocompatibility testing. and labeling instructs the clinician to not leave the patient's chest for longer than 45 minutes.
The probable benefits of the device are also based on data collected in a clinical study as described above. By using the CADScor system to evaluate the patient's risk of Coronary Artery Disease, a "low risk" score can help the clinician identify patients who are at low risk of CAD and avoid unnecessary additional testing, which come with their own respective risks. Additionally, this device can be used in the clinician's office to provide results in a timely manner. The probability of correctly identifying a patient who is low risk for CAD is high based on the NPV of 96.2%.
#### Patient Perspectives
This submission did not include specific information on patient perspectives for this device.
#### Benefit/Risk Conclusion
In conclusion, given the available information above, for the following indication statement:
The intended use of the CADScor System is to record heart sounds, murmurs and vibration for calculation of a patient specific score, indicating the risk of presence of coronary stenosis, as an aid in cardiac analysis and diagnosis.
The probable benefits outweigh the probable risks for the CADScor System. The device provides benefits and the risks can be mitigated by the use of general controls and the identified special controls.
#### CONCLUSION
The De Novo request for the CADScor System is granted and the device is classified as follows:
Product Code: OMW Device Type: Coronary artery disease risk indicator using acoustic heart signals Regulation Number: 21 CFR 870.1420 Class: II
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.