Dice score >= 0.9; Mean Absolute Distance <= 2 mm; Hausdorff Distance <= 5 mm
Hemipelvis Dice: 0.95, Femur Dice: 0.97; Hemipelvis MAD: 1.15 mm, Femur MAD: 1.35 mm; Femoral head HD: 2.84 mm, Acetabulum HD: 3.04 mm
—
—
60 images from 60 patients in the US.
>1 (US-board registered radiologists)
3D model generation from statistical shape modelling
Statistical shape models
Dice score >= 0.9; Mean Absolute Distance <= 2 mm; Hausdorff Distance <= 5 mm
Hemipelvis Dice: 0.95, Femur Dice: 0.97; Hemipelvis MAD: 1.25 mm, Femur MAD: 1.49 mm; Femoral head HD: 2.47 mm, Acetabulum HD: 2.93 mm
—
—
60 images from 60 patients in the US.
>1 (US-board registered radiologists)
Implant sizing recommendation
—
At least 80% of recommendations within +/- 2 sizes of ground truth
Stems: 94% (95% CI 0.947 - 0.998); Cups: 98% (95% CI 0.885 - 0.974)
—
—
133 images from 133 patients.
>1 (orthopaedic surgeons)
Indications for Use
Formus Hip is a preoperative surgical planning software. It is intended to assist qualified medical professionals in the preoperative planning of orthopedic surgical procedures.
Device Story
Formus Hip is a standalone, semi-automated SaMD for pre-operative planning of primary total hip arthroplasty. It imports patient CT scans from PACS or other media. Using AI-based segmentation and statistical shape models, it automatically generates 3D models of the femur and hemipelvis without user input. Algorithms fit the femoral stem and acetabular cup to patient anatomy. Surgeons use an interactive GUI to adjust the plan, which can be exported as a PDF report. Used in clinical settings by qualified medical professionals, the device assists in surgical planning; clinical judgment is required. It does not contact the patient or control life-supporting devices.
Clinical Evidence
No clinical data. Bench testing only. Image processing accuracy validated on 60 CT scans (Dice ≥ 0.95, MAD ≤ 1.35mm, HD ≤ 3.04mm). Implant sizing validated on 133 images; 94% of stem recommendations and 98% of cup recommendations were within ±2 sizes of surgeon-determined ground truth.
Technological Characteristics
SaMD; Windows-based with Chrome browser. Uses AI-based automatic image segmentation and statistical shape models of femur/pelvis. Inputs: DICOM CT scans. Outputs: 3D anatomical models, implant sizing recommendations, PDF reports. Connectivity: Networked/PACS. Software level of concern: Moderate.
Indications for Use
Indicated for pre-operative planning of primary total hip arthroplasty in adults (≥ 21 years). Software imports patient CT scans to assist surgeons in planning via an integrated database of hip implant geometries and interactive graphical interface.
Regulatory Classification
Identification
A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.
Special Controls
*Classification.* Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
{0}------------------------------------------------
March 31, 2023
Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" and "ADMINISTRATION" in blue text.
Formus Labs, Ltd % Richie Christian Head of Regulatory and Quality Suite 5, Floor 3, 30 St Benedicts Street Eden Terrace AUCKLAND 1010 NEW ZEALAND
Re: K213272
Trade/Device Name: Formus Hip Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QIH Dated: February 23, 2023 Received: February 23, 2023
Dear Richie Christian:
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. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. 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 may be subject 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 or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part
{1}------------------------------------------------
801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Amir Khan
For
Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
# Indications for Use
510(k) Number (if known) K213272
Device Name Formus Hip
### Indications for Use (Describe)
Formus Hip is a pre-operative planning software for orthopedic surgery. The standalone software application imports patient diagnostic imaging studies (e.g. pre-dimensioned CT scans) from PACS-systems or other conventional medias. The Formus Hip system contains an integrated database of orthopedic hip implant geometries that can be overlayed to assist surgeons in their planning of orthopedic hip surgeries. The software application further enables the healthcare professional to customize their preoperative planning by means of an interactive graphical user interface. Finalized plans can be printed to a PDF report. The qualified healthcare professional can digitally perform the surgical planning and also make it available as a printable report. Clinical judgment and experience with the software are required for its successful use.
| Type of Use (Select one or both, as applicable) |
|-------------------------------------------------|
|-------------------------------------------------|
X Prescription Use (Part 21 CFR 801 Subpart D)
| Over-The-Counter Use (21 CFR 801 Subpart C)
## CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
Image /page/3/Picture/0 description: The image contains the logo for Formus. The logo consists of a stylized spine graphic on the left and the word "formus" in blue font on the right. The spine graphic is made up of a series of dots connected by a curved line.
#### SUBMITTER 1.
Formus Labs Ltd. Suite 5, Floor 3, 30 St Benedicts Street Eden Terrace Auckland 1010 New Zealand
| Contact Person: | Richie Christian, Head of Regulatory and Quality |
|-----------------|--------------------------------------------------|
| Email: | richie@formuslabs.com |
Last Updated: 31 March 2023
- 2. DEVICE
| Name of Device: | Formus Hip |
|----------------------|------------------------------------------------|
| Classification Name: | Medical image management and processing system |
| Common Name: | Orthopedic Pre-operative Planning Software |
| Regulation: | 21 CFR §892.2050 |
| Regulatory Class: | II |
| Product Code: | QIH |
#### 3. PREDICATE DEVICE
PeekMed (K182464) This predicate has not been subject to a design-related recall.
#### DEVICE DESCRIPTION 4.
Formus Hip is a semi-automated Software as a Medical Device (SaMD) that allows pre-operative planning of primary total hip arthroplasty in real time using the Zimmer Biomet Taperloc G7 system. Using a series of algorithms, the software creates a 3D model and relevant measurements derived from the patient's pre-dimensioned CT scan. Formus Hip generates a 3D model without any user input. Additional algorithms fit the femoral stem and acetabular cup based on the patient anatomy. The software allows the user to adjust the plan interactively to achieve the desired clinical targets.
Formus Hip uses an Al-based automatic image segmentation algorithm trained on CT scans of male and female subjects with typical and atypical bony anatomy between the ages of 21 and 94. Formus Hip also uses statistical shape models of the femur and pelvis trained on segmented 3D models of male and female subjects with typical and atypical bony anatomy between the ages of 18 and 89.
The training datasets are independent from testing and validation datasets. Training data and internal testing data are tracked in a single record file under version control where they are labelled as either training or testing. Code used for training and testing is read from this record file so that a data point is never mixed between the training and testing datasets. Validation data was sourced from different geographies and stored in locations separate from training and internal testing data to ensure independence.
#### INTENDED USE 5.
Formus Hip is a preoperative surgical planning software. It is intended to assist qualified medical professionals in the preoperative planning of orthopedic surgical procedures.
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image shows the logo for Formus. The logo consists of a stylized spine on the left and the word "formus" in blue on the right. The spine is made up of a series of dots that are connected by a curved line.
#### INDICATIONS FOR USE 6.
Formus Hip is a pre-operative planning software for orthopedic surgery. The standalone software application imports patient diagnostic imaging studies (e.g. pre-dimensioned CT scans) from PACSsystems or other conventional medias. The Formus Hip system contains an integrated database of orthopedic hip implant geometries that can be overlayed to assist surgeons in their planning of orthopedic hip surgeries. The software application further enables the healthcare professional to customize their preoperative planning by means of an interactive graphical user interface. Finalized plans can be printed to a PDF report. The qualified healthcare professional can digitally perform the surgical planning and also make it available as a printable report. Clinical judgment and experience with the software are required for its successful use.
#### 7. COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE PREDICATE
The table below provides a comparison of the technological characteristics of Formus Hip and the legally marketed predicate device (PeekMed, K182464).
| Device | Subject Device | Predicate Device |
|---------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------|
| | Formus Hip | PeekMed |
| | (K213272) | K182464 |
| Manufacturer | Formus Labs Ltd. | Peek Health, S.A. |
| Product Code | QIH | LLZ |
| Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 |
| Regulation Name | System, Image | System, Image |
| | Processing, Radiological | Processing, Radiological |
| Intended Use | Formus Hip is a preoperative surgical | PeekMed is a preoperative |
| | planning software. It is | planning software for surgery |
| | intended to assist qualified medical | |
| | professionals in the preoperative | |
| | planning of orthopedic surgical | |
| | procedures. | |
| Indications for Use | Formus Hip is a pre-operative planning | PeekMed is a software system |
| | software for orthopedic surgery. The | designed to help surgeons' |
| | standalone software application imports | specialists carry out the preoperative |
| | patient diagnostic imaging studies (e.g. | planning in a prompt and efficient |
| | pre-dimensioned CT scans) from | manner for several surgical |
| | PACS-systems or other conventional | procedures, based on their patients' |
| | medias. The Formus Hip system | imaging studies. The software imports |
| | contains an integrated database of | diagnostics imaging studies such as x- |
| | orthopedic hip implant geometries that | rays, CT or magnetic resonance image |
| | can be overlayed to assist surgeons in | (MRI). The import process can retrieve |
| | their planning of orthopedic hip | files from a CD ROM, a local folder or |
| | surgeries. The software application | the PACS. In parallel, there is a |
| | further enables the healthcare | database of digital representations |
| | professional to customize their | related to prosthetic materials supplied |
| | preoperative planning by means of an | by their producing companies. |
| | interactive graphical user interface. | PeekMed allows health professional to |
| | Finalized plans can be printed to a PDF | digitally perform the surgical planning |
| | report. The qualified healthcare | without adding any additional steps to |
| | professional can digitally perform the | that process. This software system |
| | surgical planning and also make it | requires no imaging study acquisition |
| | available as a printable report. Clinical | specification (no protocol). Experience |
| | judgment and experience with the | in usage and a clinical assessment are |
| | software are required for its successful | necessary for a proper use of the |
| | use. | software. |
| Device | Subject Device<br>Formus Hip<br>(K213272) | Predicate Device<br>PeekMed<br>K182464 |
| Patient Population | Adults (≥ 21 years) | Adults and pediatrics |
| End Users | Qualified medical professionals | Surgeons |
| Computer | Personal computer or workstation | Personal computer or workstation |
| Operating System | Windows with a Chrome browser | Windows or OS X |
| Radiological Image<br>Format | DICOM | DICOM |
| Device Availability | Can be accessed from the Chrome<br>internet browser launched from a<br>standalone PC or workstation with<br>internet access. | It can be set to start from a workstation<br>or standalone for planning procedure |
| Image Source | Receive digital images from various<br>sources (including PACS system) | Receive digital images from various<br>sources (including PACS system) |
| Data Processing | The software processes pre-<br>dimensioned CT imaging to produce<br>digital representations of the patient<br>anatomy to which digital<br>representations of prosthetic<br>components are overlapped. | The software processes data in<br>order to provide an overlap and<br>dimensioning of digital representation<br>of the prosthetic material |
| Digital Overlap of<br>Prosthetic Material | Allows the overlap of the digital<br>representation of prosthetic<br>components | Allows the overlap of models and the<br>intersection of the models |
| Interactive Model<br>Positioning | Yes | Yes |
| Interactive Model<br>Dimensioning | Yes | Yes |
| Model Rotation | Yes | Yes |
| Support for Digital<br>Prosthetic materials<br>Provided by the<br>Manufacturers | Yes | Yes |
| Anatomical<br>Landmarks | Yes | Yes |
| Medical<br>Subspecialities | Hip | Hip, Knee, Spine, Upper Limb, Foot-<br>and-Ankle, Trauma |
| Pre-specified<br>Procedures | Total Hip Arthroplasty | Total Hip Arthroplasty<br>(Additional joint replacements and<br>associated procedures specific to<br>product intended for expanded<br>indications) |
| Pre-surgical<br>Planning | Yes | Yes |
| Contact with the<br>Patient | No | No |
| Control of Life<br>Supporting Devices | No | No |
| Human Intervention<br>for Image<br>Interpretation | Yes | Yes |
| Ability to Add<br>Additional Modules | Yes | Yes |
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the logo for Formus. The logo consists of a stylized spine graphic on the left and the word "formus" in blue on the right. The spine graphic is made up of a series of black circles connected by a blue line. The word "formus" is written in a sans-serif font.
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image shows the logo for Formus. The logo consists of a stylized spine on the left and the word "formus" in blue on the right. The spine is made up of a series of circles connected by a curved line.
#### NON-CLINICAL PERFORMANCE DATA 8.
Software verification and validation was performed per Formus Labs' design and development processes which confirmed that the product specifications have been met. Formus Hip is classified as a "moderate" level of concern since a failure or latent flaw could indirectly result in minor injury to the patient.
Dedicated system verification testing including but not limited to automated tests and regression tests has been performed against pre-defined acceptance criteria. Each test met its predefined acceptance criteria for all functions of the software.
Dedicated validation has been performed on image processing accuracy and implant sizing, as below.
### Image Processing Accuracy
Dedicated validation has been performed on 60 images acquired (from 60 patients) in the US to validate accuracy of image processing by comparing automatically generated 3D models of the femur and hemipelvis to the 3D models generated via manual segmentation by a panel of US radiologists. The images were acquired on Philips - Brilliance Big Bore, LightSpeed VCT using Formus Labs' standard CT protocol. The demographic distribution of this dataset is provided below.
- . Gender: Male: 34; Female: 26
- Minimum: 41; Maximum: 88 Age:
- . Ethnicity: Black or African American: 18; Hispanic: 16; White: 16; Not specified: 10
Ground truth was obtained by US-board registered radiologists (truthers) experienced in 3D image segmentation. Each bone surface was manually segmented by two radiologists. A third senior radiologist reviewed each pair of segmentation and selected the most accurate segmentation which was the final manually segmented mesh.
Difference between the automatic (Formus Hip generated) and manual 3D models were quantified using the Sorensen-Dice coefficient (Dice), Mean Absolute Distance (MAD) and Hausdorff Distance (HD). All acceptance criteria were met, as shown in the table below.
| Endpoint | Acceptance Criteria | Results |
|--------------------------------------------------------|-----------------------------------------------------------------------------------|----------------------------------------|
| 3D models from image segmentation | The average Dice score must be equal or greater than 0.9 | Hemipelvis: 0.95<br>Femur: 0.97 |
| | The average MAD must be equal or less than 2 mm | Hemipelvis: 1.15<br>Femur: 1.35 |
| | The average HD must be equal or less than 5 mm in the femoral head and acetabulum | Femoral head: 2.84<br>Acetabulum: 3.04 |
| 3D models of the proximal shaft inner cortical surface | The average MAD must be equal or less than 2 mm | Inner cortical surface: 1.02 |
| | The average HD must be equal or less than 5 mm | Inner cortical surface: 2.80 |
| 3D models generated from statistical shape modelling | The average Dice score must be equal or greater than 0.9 | Hemipelvis: 0.95<br>Femur: 0.97 |
| | The average MAD must be equal or less than 2 mm | Hemipelvis: 1.25<br>Femur: 1.49 |
| | The average HD must be equal or less than 5 mm in the femoral head and acetabulum | Femoral head: 2.47<br>Acetabulum: 2.93 |
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image shows the logo for Formus. The logo consists of a stylized spine on the left and the word "formus" in blue on the right. The spine is made up of a series of black dots connected by a blue line, and the word "formus" is written in a sans-serif font.
Consistency in performance across all subgroups (i.e., sex, age, body mass index, ethnicity, and CT scanner) was assessed to demonstrate generalisability of the device across the intended US patient population.
### Implant Sizing
A validation on implant sizing was performed on 133 images (from 133 patients) in which the implant sizes recommended by Formus Hip were compared to the implant sizes (ground truth) determined by orthopaedic surgeons. The images were acquired via a variety of common clinical CT scanners using Formus Labs' standard CT protocol. The demographic distribution of this dataset is provided below.
- Male: 70; Female: 63 ● Gender:
- . Minimum: 42; Maximum: 87 Age:
Ground truth was obtained by orthopaedic surgeons (truthers) using traditional templating methods. The different in sizes recommended by Formus Hip was compared with ground truth. The performance goal was that at least 80% of cup and stem sizes recommended by Formus Hip were within ±2 sizes of the around truth.
The acceptance criteria were met as the proportion of stems and cups recommended by Formus Hip that were within 2 sizes of ground truth were 94% (95% Cl 0.947 - 0.998) and 98% (95% Cl 0.885 - 0.974), respectively.
#### CLINICAL PERFORMANCE DATA 9.
Substantial equivalence was not based on an assessment of clinical performance data.
### 10. CONCLUSIONS
Formus Hip has the same intended use, indications for use, technological characteristics and principles of operation compared to the predicate device and does not raise different questions of safety or effectiveness.
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.