K232833 · Indica Labs, Inc. · PSY · May 7, 2024 · Pathology
Device Facts
Record ID
K232833
Device Name
HALO AP Dx
Applicant
Indica Labs, Inc.
Product Code
PSY · Pathology
Decision Date
May 7, 2024
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 864.3700
Device Class
Class 2
Attributes
Software as a Medical Device
Indications for Use
HALO AP Dx is a software only device intended as an aid to the pathologist to review, interpret and manage digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue for the purposes of pathology primary diagnosis. HALO AP Dx is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens. It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the quality of the images obtained and, where necessary, use conventional light microscopy review when making a diagnostic decision. HALO AP Dx is intended for use with the Hamamatsu NanoZoomer S360MD Slide scanner and the JVC Kenwood JD-C240BN01A display.
Device Story
HALO AP Dx is a browser-based software-only device for viewing, managing, and interpreting digital whole slide images (WSI) of FFPE tissue slides. Input consists of digital images acquired via the Hamamatsu NanoZoomer S360MD scanner. The software ingests these images and stores metadata to optimize viewing performance. Pathologists use the device in a clinical setting to zoom, pan, annotate, measure, and perform side-by-side comparisons of images displayed on a JVC Kenwood JD-C240BN01A monitor. The device facilitates the diagnostic workflow by providing a digital interface for image review; final diagnosis is documented in external systems like an LIS. It benefits patients by enabling digital primary diagnosis, potentially increasing efficiency and accessibility of pathology review.
Clinical Evidence
No clinical data. Bench testing only. Pixel-wise comparison of 315 image-pairs (35 slides, 3 ROIs, 3 magnifications) across HALO AP Dx and the predicate system demonstrated identical image reproduction. The 95th percentile of CIEDE2000 color differences was < 3 ΔE₀₀ (mean 1.52). Measurement accuracy for length and area was verified using a calibration slide. Summative human factors testing confirmed safe and effective use by pathologists and histotechnicians.
Technological Characteristics
Software-only device; browser-based (Chrome/Edge). Operates on Windows Server 2022/Ubuntu 22.04. Interoperable with Hamamatsu NanoZoomer S360MD scanner and JVC Kenwood JD-C240BN01A display. Uses CIEDE2000 color difference metric for image fidelity. Supports standard annotation, measurement, and synchronization tools. Complies with IEC 62304 (software lifecycle), ISO 14971 (risk management), and IEC 62366-1 (usability).
Indications for Use
Indicated for use by pathologists to review, interpret, and manage digital whole slide images of FFPE surgical pathology slides for primary diagnosis. Not for use with frozen section, cytology, or non-FFPE hematopathology specimens.
Regulatory Classification
Identification
The whole slide imaging system is an automated digital slide creation, viewing, and management system intended as an aid to the pathologist to review and interpret digital images of surgical pathology slides. The system generates digital images that would otherwise be appropriate for manual visualization by conventional light microscopy.
Special Controls
A whole slide imaging system must comply with the following special controls: (1) Premarket notification submissions must include the following information: (i) The indications for use must specify the tissue specimen that is intended to be used with the whole slide imaging system and the components of the system. (ii) A detailed description of the device and bench testing results at the component level, including for the following, as appropriate: (A) Slide feeder; (B) Light source; (C) Imaging optics: (D)Mechanical scanner movement; (E) Digital imaging sensor; (F) Image processing software; (G)Image composition techniques; (H)Image file formats; (I) Image review manipulation software; (J) Computer environment; (K)Display system. (iii)Detailed bench testing and results at the system level, including for the following, as appropriate: (A)Color reproducibility; (B) Spatial resolution; (C) Focusing test; (D) Whole slide tissue coverage; (E) Stitching error: (F) Turnaround time. (iv) Detailed information demonstrating the performance characteristics of the device, including, as appropriate: (A)Precision to evaluate intra-system and inter-system precision using a comprehensive set of clinical specimens with defined, clinically relevant histologic features from various organ systems and diseases. Multiple whole slide imaging systems, multiple sites, and multiple readers must be included. (B) Reproducibility data to evaluate inter-site variability using a comprehensive set of clinical specimens with defined, clinically relevant histologic features from various organ systems and diseases. Multiple whole slide imaging systems, multiple sites, and multiple readers must be included. (C) Data from a clinical study to demonstrate that viewing, reviewing, and diagnosing digital images of surgical pathology slides prepared from tissue slides using the whole slide imaging system is non-inferior to using an optical microscope. The study should evaluate the difference in major discordance rates between manual digital (MD) and manual optical (MO) modalities when compared to the reference (e.g., main sign-out diagnosis). (D) A detailed human factors engineering process must be used to evaluate the whole slide imaging system user interface(s). (2) Labeling compliant with 21 CFR 809.10(b) must include the following: The intended use statement must include the information described in paragraph (i) (1)(i) of this section, as applicable, and a statement that reads, "It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images obtained using this device." (ii) A description of the technical studies and the summary of results, including those that relate to paragraph (1)(ii) and (1)(iii) of this section, as appropriate. (iii) A description of the performance studies and the summary of results, including those that relate to paragraph (1)(iv) of this section, as appropriate. (iv) A limiting statement that specifies that pathologists should exercise professional judgment in each clinical situation and examine the glass slides by conventional microscopy if there is doubt about the ability to accurately render an interpretation using this device alone.
*Classification.* Class II (special controls). The special controls for this device are:(1) Premarket notification submissions must include the following information:
(i) The indications for use must specify the tissue specimen that is intended to be used with the whole slide imaging system and the components of the system.
(ii) A detailed description of the device and bench testing results at the component level, including for the following, as appropriate:
(A) Slide feeder;
(B) Light source;
(C) Imaging optics;
(D) Mechanical scanner movement;
(E) Digital imaging sensor;
(F) Image processing software;
(G) Image composition techniques;
(H) Image file formats;
(I) Image review manipulation software;
(J) Computer environment; and
(K) Display system.
(iii) Detailed bench testing and results at the system level, including for the following, as appropriate:
(A) Color reproducibility;
(B) Spatial resolution;
(C) Focusing test;
(D) Whole slide tissue coverage;
(E) Stitching error; and
(F) Turnaround time.
(iv) Detailed information demonstrating the performance characteristics of the device, including, as appropriate:
(A) Precision to evaluate intra-system and inter-system precision using a comprehensive set of clinical specimens with defined, clinically relevant histologic features from various organ systems and diseases. Multiple whole slide imaging systems, multiple sites, and multiple readers must be included.
(B) Reproducibility data to evaluate inter-site variability using a comprehensive set of clinical specimens with defined, clinically relevant histologic features from various organ systems and diseases. Multiple whole slide imaging systems, multiple sites, and multiple readers must be included.
(C) Data from a clinical study to demonstrate that viewing, reviewing, and diagnosing digital images of surgical pathology slides prepared from tissue slides using the whole slide imaging system is non-inferior to using an optical microscope. The study should evaluate the difference in major discordance rates between manual digital (MD) and manual optical (MO) modalities when compared to the reference (
*e.g.,* main sign-out diagnosis).(D) A detailed human factor engineering process must be used to evaluate the whole slide imaging system user interface(s).
(2) Labeling compliant with 21 CFR 809.10(b) must include the following:
(i) The intended use statement must include the information described in paragraph (b)(1)(i) of this section, as applicable, and a statement that reads, “It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images obtained using this device.”
(ii) A description of the technical studies and the summary of results, including those that relate to paragraphs (b)(1)(ii) and (iii) of this section, as appropriate.
(iii) A description of the performance studies and the summary of results, including those that relate to paragraph (b)(1)(iv) of this section, as appropriate.
(iv) A limiting statement that specifies that pathologists should exercise professional judgment in each clinical situation and examine the glass slides by conventional microscopy if there is doubt about the ability to accurately render an interpretation using this device alone.
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
## I Background Information:
A 510(k) Number
K232833
B Applicant
Indica Labs, Inc.
C Proprietary and Established Names
HALO AP Dx
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QKQ | Class II | 21 CFR 864.3700 - Whole Slide Imaging System | PA - Pathology |
## II Submission/Device Overview:
A Purpose for Submission:
New device
B Type of Test:
Software only device
## III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
For In Vitro Diagnostic Use
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
HALO AP Dx is a software only device intended as an aid to the pathologist to review, interpret and manage digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue for the purposes of pathology primary diagnosis. HALO AP Dx is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens.
It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the quality of the images obtained and, where necessary, use conventional light microscopy review when making a diagnostic decision. HALO AP Dx is intended for use with the Hamamatsu NanoZoomer S360MD Slide scanner and the JVC Kenwood JD-C240BN01A display.
## C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
## IV Device/System Characteristics:
## A Device Description:
HALO AP Dx, version 2.1 is a browser-based software-only device intended to aid pathology professionals in viewing, manipulating, management, and interpretation of digital pathology whole slide images (WSI) of glass slides obtained from the Hamamatsu Photonics K.K. NanoZoomer S360MD scanner and viewed on the JVC Kenwood JD-C240BN01A display.
HALO AP Dx is operated as follows:
1. Image acquisition is performed using the predicate device, NanoZoomer S360MD Slide scanner according to its Instructions for Use. The operator performs quality control of the digital slides per the instructions of the NanoZoomer and lab specifications to determine if re-scans are necessary.
2. Once image acquisition is complete, the unaltered image is saved in an external image storage location. HALO AP Dx ingests the image and a copy of image metadata is stored in the subject device's database to improve viewing response times.
3. Scanned images are reviewed by scanning personnel such as histotechnicians to confirm image quality and initiate any re-scans before making it available to the pathologist.
4. The reading pathologist selects a patient case from a selected worklist within HALO AP Dx whereby the subject device fetches the associated images from external image storage.
5. The reading pathologist uses the subject device to view the images and can perform the following actions, as needed:
a. Zoom and pan the image.
b. Measure distances and areas in the image.
c. Annotate images.
d. View multiple images side by side in a synchronized fashion.
6. The above steps are repeated as necessary.
After viewing all images belonging to a particular case (patient), the pathologist will make a diagnosis which is documented in another system, such as a Laboratory Information System (LIS).
K232833 - Page 2 of 9
{2}
The interoperable components of HALO AP Dx and other system specifications are provided in tables 1 - 4 below.
Table 1. Interoperable Components for Use with HALO AP Dx
| Components | Manufacturer | Model |
| --- | --- | --- |
| Scanner | Hamamatsu | NanoZoomer S360MD Slide scanner |
| Display | JVC | JD-C240BN01A |
Table 2. Client System Requirements
| Workstation Component | Specifications |
| --- | --- |
| Processor | Intel Core i7 CPU |
| Memory | 16 GB or more |
| Network connectivity | 100 Mbps (1 Gbps recommended) connection |
| Keyboard/ Mouse / Trackpad | Standard Keyboard and Mouse Input Devices |
| Operating system | Windows 10 |
| Supported browsers | Google Chrome version 116 and above Microsoft Edge version 116 and above |
| Antivirus software | The following anti-virus software has been validated for use: - Microsoft Windows Defender - Trend Micro - Webroot |
Table 3. Server System Requirements
| Server | Operating System | Memory | Processor |
| --- | --- | --- | --- |
| Component Server, Processing Node Server, File Monitor Server | Windows Server 2022 Only x64 (64 bit) operating systems are supported | 16 GB or more | 8 cores or more |
| NGINX Reverse Proxy | Ubuntu 22.04 Only x64 (64 bit) operating systems are supported | 2 GB or more | 2 cores or more |
| MySQL Server | Windows Server 2022 or Ubuntu 22.04 Only x64 (64 bit) operating systems are supported | 16 GB or more | 4 cores or more |
K232833 - Page 3 of 9
{3}
Table 4. Server Configurations
| Component | Specifications |
| --- | --- |
| Network connectivity | 1 Gbps (10 Gbps recommended) LAN connection between services |
| Antivirus software | The following anti-virus software has been validated for use with Windows server: - Microsoft Windows Defender - Trend Micro - Webroot |
B Instrument Description Information:
1. Instrument Name:
HALO AP Dx
2. Specimen Identification:
HALO AP Dx uses digital pathology images obtained from the Hamamatsu S360 MD scanner of Hematoxylin and Eosin (H&E) stained glass slides. The reading pathologist selects a case (patient) from a worklist (within the device or external to the device) whereby the subject device fetches the associated images from the external image storage. The scanned images are identified based on the previously assigned specimen identifier such as the laboratory specimen accession number.
3. Specimen Sampling and Handling:
Specimen sampling and handling are performed upstream and independent of the use of the subject device. Specimen sampling includes biopsy or resection specimens which are processed using histology techniques. The FFPE tissue section is Hematoxylin and Eosin (H&E) stained. Digital images are then obtained from these glass slides using the Hamamatsu S360 MD scanner.
4. Calibration:
Not applicable
5. Quality Control:
The scanning technician should perform quality control of all glass slides following the instructions. Upon scanning, quality control should be performed on all digital slide images following procedures defined by the scanner manufacturer prior to import into HALO AP Dx.
The pathologist should review all images to ensure that all expected slides have been imported by viewing the thumbnails and labels, and manually verifying the tissue specimen, block, and staining information is present. Additional details of the quality control procedures are provided in the device User's Guide and the Implementation Guide.
K232833 - Page 4 of 9
{4}
V Substantial Equivalence Information:
A Predicate Device Name(s):
NanoZoomer S360MD Slide scanner system
B Predicate 510(k) Number(s):
K213883
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K232833 | K213883 |
| --- | --- | --- |
| Device Trade Name | HALO AP Dx | Hamamatsu NanoZoomer S360MD Slide scanner system |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | HALO AP Dx is a software only device intended as an aid to the pathologist to review, interpret and manage digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. HALO AP Dx is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens. It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the quality of the images obtained and, where necessary, use conventional light microscopy review when making a diagnostic decision. HALO AP Dx is intended for use with the Hamamatsu NanoZoomer S360MD Slide scanner and the JVC Kenwood JD-C240BN01A display. | The NanoZoomer S360MD Slide scanner system (“NanoZoomer System”) is an automated digital slide creation, viewing, and management system. The NanoZoomer System is intended for in vitro diagnostic use as an aid to the pathologist to review and interpret digital images of surgical pathology slides prepared from formalin-fixed paraffin embedded (“FFPE”) tissue. The NanoZoomer System is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens. The NanoZoomer System comprises the NanoZoomer S360MD Slide scanner, the NZViewMD Software and the JVC Kenwood JD-C240BN01A display. The NanoZoomer System is for creation and viewing of digital images of scanned glass slides that would otherwise be appropriate for manual visualization by conventional light microscopy. It is the responsibility of a qualified pathologist to employ appropriate |
K232833 - Page 5 of 9
{5}
| Device & Predicate Device(s): | K232833 | K213883 |
| --- | --- | --- |
| | | procedures and safeguards to assure the validity of the interpretation of images obtained using NanoZoomer System. |
| Specimen Type | Same | Surgical pathology slides prepared from FFPE tissue |
| Diagnostic Image File Format | Same | Hamamatsu NDPI File |
| Image Storage | Same | User-supplied network attached storage |
| General Device Characteristic Differences | | |
| Image Manipulation and Review Functions | Functions for continuous panning and zooming, annotations, image adjustments, distance/area measurements, organize workload and view patient data, export images, and display of diagnostic status of images. | Functions for continuous panning and zooming, annotations, distance/area measurements, track visited areas, export images, discrete Z-axis displacement, and display of diagnostic status of images. |
| Type of Software Application | Internet browser-based application | PC-based installed application |
| End User’s Interface | HALO AP Dx | NZViewMD |
VI Standards/Guidance Documents Referenced:
1. Guidance for Industry “Technical Performance Assessment of Digital Pathology Whole Slide Imaging Devices”, April 20, 2016.
2. Guidance for Industry "Applying Human Factors and Usability Engineering to Medical Devices", February 3, 2016.
3. IEC 62304 Edition 1.1 2015-06 CONSOLIDATED VERSION, 13-79. Medical device software – Software life cycle processes.
4. ISO 14971 Third Edition 2019-12, 5-125, Medical devices – Applications of risk management to medical devices.
5. IEC 62366-1 Edition 1.1 2020-06 CONSOLIDATED VERSION, 5-129, Application of usability engineering to medical devices.
6. AAMI TIR 45:2012, 13-36, Guidance on the use of AGILE practices in the development of medical device software.
7. Standards Details / Supplemental Documentation per ISO/IEC 17050-2.
VII Performance Characteristics (if/when applicable):
K232833 - Page 6 of 9
{6}
K232833 - Page 7 of 9
# A Analytical Performance:
1. Precision/Reproducibility:
Not applicable
2. Linearity:
Not applicable
3. Analytical Specificity/Interference:
Not applicable
4. Accuracy (Instrument):
Not applicable
5. Carry-Over:
Not applicable
# B Other Supportive Instrument Performance Characteristics Data:
Technical performance testing was conducted with HALO AP Dx. The subject device was compared to the predicate device's image review manipulation software (IRMS, as defined in FDA guidance document, "Guidance for Industry – Technical Performance Assessment of Digital Pathology Whole Slide Imaging Devices," dated April 20, 2016) using the quantitative pixel-wise comparison method. The basis for the comparison was the CIEDE2000 color difference equation, $\Delta E$.
# 1. Bench Testing - Pixelwise comparison test
Pixel-wise comparison testing to demonstrate identical image reproduction was conducted to compare WSIs reproduced by HALO AP Dx and Nanozoomer NZViewMD. The devices were tested as operating with the intended components, including the scanner (Hamamatsu NanoZoomer S360MD Slide scanner), image management system (Nanozoomer NZViewMD, HALO AP Dx with Google Chrome, or HALO AP Dx with Microsoft Edge), and display (JVC Kenwood JD-C240BN01A).
The device was tested with multiple slides across multiple regions of interest (ROI) at multiple magnification levels. A total of 35 H&E-stained, FFPE glass slides of normal and tumor tissues from various human anatomical organs were used in the testing. The glass slides were scanned on a Hamamatsu NanoZoomer S360MD Slide scanner system to obtain 35 WSIs. For each of the 35 WSIs, 3 ROIs were selected by qualified personnel to represent various features in the tissue samples. Each ROI was captured at 3 magnification levels (10x, 20x, 40x).
{7}
The screenshots were captured from the intended display and cropped to generate bitmap images (.bmp) that were ready for pixelwise comparison. Three sets of images were collected: (1) NZViewMD, (2) HALO AP Dx using Google Chrome, and (3) HALO AP Dx using Microsoft Edge. Each image set included 315 images that covered all combinations of 35 slides, 3 ROIs, and 3 magnification levels. The testing data, including the overview images of the 35 glass slides with annotations of the ROIs, registration/cropping information, and captured images, were provided in the FDA specific format.
Image set #1 above was used as the reference to compare image set #2 (or #3) to determine whether all the 315 image-pairs were identical. Two images are considered identical if the 95th percentile of the pixelwise differences, computed using the International Commission on Illumination (CIE) color difference metric CIEDE2000 (ΔE₀₀), is less than 3 ΔE₀₀. Testing results showed that the pixelwise differences across all 630 image-pairs were less than 3 ΔE₀₀. The mean 95th percentile ΔE₀₀ value was 1.52 with the lowest value reported as 0.82 and the highest reported as 2.75. Testing results demonstrated that WSIs reproduced by HALO AP Dx are identical to images reproduced by the predicate device.
2. Turnaround Time
Turnaround times for image loading, panning and zooming were tested when using Google Chrome and Microsoft Edge browsers over different magnifications levels and over multiple fields of view (FOVs). Additionally, concurrent, multi-user load testing of the HALO AP Dx Image Server was performed to show that the subject device is responsive under constant utilization over a long period of time. Test results showed these to be adequate for the intended use of the subject device.
3. Measurements – area and distance
Measurement accuracy testing was performed to demonstrate that HALO AP Dx represents length and area measurements accurately across multiple magnification levels. An image of a calibration slide with known object sizes was used to verify the measurement accuracy. A total of 32 annotations were created – 4 annotations (2 horizontal and 2 vertical) at 4 magnification levels in 2 browsers. The intended and reported metrics were recorded for each annotation. The differences between intended and reported measurements were calculated. Test results showed that the subject device performed accurate measurements of length and area across multiple magnification settings with respect to its intended use.
4. Human Factors (Usability) Testing
Usability testing was conducted per FDA’s Guidance on Applying Human Factors and Usability Engineering to Medical Devices (2016). A summative human factors test, designed around critical user tasks and use scenarios using multiple representative users (pathologists and histotechnicians), was conducted. All tasks associated with reviewing and reporting results for cases including confirmation that all slides belonging to specific cases are reviewed before reporting results were included in the study. The HALO AP Dx device has been found to be safe and effective for intended users, users and use environments.
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
K232833 - Page 8 of 9
{8}
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K232833 - Page 9 of 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.
