Retrospective analysis of hospitalized patients (Loma Linda University); Retrospective analysis of healthy volunteers (Masimo laboratory study)
Retrospective data was used to calculate ORi values, demonstrate the non-linear relationship between ORi and PaO2, and support the clinical performance validation of the device as an adjunct to SpO2.
Retrospective study; Standard of care; Clinical performance validation; Hospitalized patients
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Loma Linda University Study; Retrospective study
126 hospitalized subjects undergoing elective surgery; Sample Size: 126 subjects (1251 data pairs); Number of Sites: 1
Not applicable for this study
ORi value calculation and correlation with PaO2
Masimo Clinical Lab Study; Retrospective study
52 healthy volunteers; Sample Size: 52 subjects (939 data pairs); Number of Sites: 1
Not applicable for this study
ORi value calculation and correlation with PaO2
Indications for Use
The ORi feature is intended to be used in patients undergoing surgery as an adjunct to SpO2 for increased monitoring resolution of elevated hemoglobin oxygen saturation levels (e.g., due to the administration of supplemental oxygen). The ORi feature is indicated for the monitoring of hemoglobin oxygen saturation levels in patients 18 years and older (adults and transitional adolescents) on supplemental oxygen during no-motion conditions perioperatively in hospital environments.
Device Story
ORi is an adjunct pulse oximetry feature providing monitoring resolution for elevated hemoglobin oxygen saturation (hyperoxia) in surgical patients. It uses a multi-wavelength optical sensor applied to a capillary site (e.g., fingertip) to measure light absorption profiles of oxyhemoglobin and deoxyhemoglobin. The device processes these inputs to generate a numeric index (0 to 1 scale) representing blood oxygen levels. It is used in hospital operating rooms, integrated into monitors like Rad-97, Radical-7, and Root. The output is displayed alongside SpO2 values; it provides a high-limit alarm at 0.7. Clinicians use the trend of ORi values to titrate supplemental oxygen delivery. It does not replace arterial blood gas analysis, which remains the gold standard. The device benefits patients by providing visibility into the transition from normoxia to hyperoxia, aiding in the management of oxygenation during anesthesia.
Clinical Evidence
Evidence includes two retrospective studies (52 healthy volunteers, 126 surgical patients) and one prospective study (28 surgical patients). Total 206 subjects, 2330 data pairs (ORi, SaO2). Primary endpoint: accuracy of ORi in detecting PaO2 changes (100-250 mmHg). Results: Pooled data demonstrated AUC > 0.8 for PaO2 range 100-250 mmHg. No adverse events reported. Studies confirm non-linear relationship between ORi and PaO2 with intra/inter-subject variability.
Technological Characteristics
Multi-wavelength optical sensor; uses red and infrared light absorption principles similar to pulse oximetry with additional wavelengths for hyperoxia resolution. Numerical output (0-1 scale). Integrated into Masimo monitoring systems (Radical-7, Root). Software-based processing. Biocompatible patient-contacting components.
Indications for Use
Indicated for monitoring hemoglobin oxygen saturation levels in adults and transitional adolescents (18+ years) receiving supplemental oxygen during no-motion perioperative conditions in hospital settings.
Regulatory Classification
Identification
A hyperoxia monitoring device adjunct to pulse oximetry is a device that monitors elevated hemoglobin oxygen saturation levels as an adjunct to arterial oxygen saturation monitoring. The ORi feature is intended to be used in patients undergoing surgery as an adjunct to SpO2 for increased monitoring resolution of elevated hemoglobin oxygen saturation levels (e.g., due to the administration of supplemental oxygen) in patients 18 years and older on supplemental oxygen during no-motion conditions perioperatively in hospital environments.
Special Controls
(1) Clinical performance testing under anticipated conditions of use must evaluate the accuracy of hyperoxia monitoring by the device and evaluate all adverse events.
(2) Human factors/usability testing must demonstrate that the user can correctly use the device, based solely on reading the instructions for use.
(3) Performance data must demonstrate the electromagnetic compatibility (EMC) and electrical safety of the device.
(4) The patient-contacting components of the device must be demonstrated to be biocompatible.
(5) Performance testing must validate the reprocessing instructions for the device. including demonstration of device performance after repeated cleaning and disinfection.
(6) Software verification, validation, and hazard analysis must be performed. Performance testing must demonstrate compatibility with pulse oximeter devices labeled to be compatible with the device.
(7) Labeling must include:
- (i) Cleaning and disinfection instructions:
- A summary of the clinical performance testing with the device: (ii)
- (iii) A warning against over-reliance on device output without using arterial blood gas values for confirmation; and
- (iv) Instructions to monitor oxygen delivery and patient clinical/cardiovascular status when device output changes.
Submission Summary (Full Text)
{0}------------------------------------------------
## DE NOVO CLASSIFICATION REQUEST FOR ORI
#### REGULATORY INFORMATION
FDA identifies this generic type of device as:
Hyperoxia monitoring device adjunct to pulse oximetry. A hyperoxia monitoring device adjunct to pulse oximetry is a device that monitors elevated hemoglobin oxygen saturation levels as an adjunct to arterial oxygen saturation monitoring.
NEW REGULATION NUMBER: 21 CFR 870.2720
CLASSIFICATION: Class II
PRODUCT CODE: OWE
#### BACKGROUND
DEVICE NAME: ORi
SUBMISSION NUMBER: DEN200076
DATE DE NOVO RECEIVED: December 21, 2020
#### SPONSOR INFORMATION:
Masimo Corporation 52 Discovery Irvine, CA 92618
#### INDICATIONS FOR USE
The ORi feature is intended to be used in patients undergoing surgery as an adjunct to SpO2 for increased monitoring resolution of elevated hemoglobin oxygen saturation levels (e.g., due to the administration of supplemental oxygen).
The ORi feature is indicated for the monitoring of hemoglobin oxygen saturation levels in patients 18 years and older (adults and transitional adolescents) on supplemental oxygen during no-motion conditions perioperatively in hospital environments.
#### LIMITATIONS
The sale, distribution, and use of the ORi are restricted to prescription use in accordance with 21 CFR 801.109.
{1}------------------------------------------------
The device is not intended to be used as a stand-alone diagnostic device.
The device output does not reduce the operator's responsibility for informed clinical judgement and best clinical procedure.
The ORi feature is an adjunct to SpO2 only to be used in titration of supplemental oxygen in patients over age 18 undergoing surgery.
Arterial blood gas analysis remains the gold standard in diagnosis of hypoxemia.
PLEASE REFER TO THE LABELING FOR A COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.
## DEVICE DESCRIPTION
ORi is a device that provides an adjunct oximeter function that extends the monitoring resolution of hemoglobin oxygen saturation at elevated oxygen levels (e.g., due to the administration of supplemental oxygen). The feature is intended to be used in conjunction with SpO2 monitoring provided by a pulse oximeter. The ORi feature utilizes the similar principles of operation as pulse oximetry, utilizing hemoglobin wavelength absorption characteristics to determine relative blood oxygen saturation. Whereas SpO2 monitoring provides visibility to blood oxygen saturation in the transition from normoxia to hypoxia on the hemoglobin oxygen disassociation curve, ORi provides visibility to the transition from normoxia to hyperoxia.
## Principle of Operation
The ORi feature is an index that relies on the same principles of operation used in pulse oximetry to increase the resolution of the monitoring of hemoglobin oxygen saturation under elevated blood oxygen levels. Like pulse oximetry (SpO2 monitoring), OR i utilizes the well understood absorption profile characteristics of hemoglobin to absorb red and infrared wavelengths of light differently based upon it being bound to oxygen (oxyhemoglobin) or unbound to oxygen (deoxyhemoglobin). See Figure 12.1 which illustrates the different absorption characteristics of hemoglobin based upon its oxygenation state.
{2}------------------------------------------------
Image /page/2/Figure/0 description: The image shows the title of a figure. The title is "Figure 1 - Absorption Spectra of Hemoglobin". The title is written in a clear, sans-serif font and is centered on the image.
Image /page/2/Figure/1 description: The image shows an absorption spectra graph. The x-axis represents the wavelength in nanometers, ranging from 600 to 1600. The y-axis represents absorption, ranging from 0 to 4 (1/mm). The graph shows the absorption spectra of carboxyhemoglobin, oxyhemoglobin, methemoglobin, deoxyhemoglobin, and plasma.
In SpO2 monitoring, red and infrared light is passed through a capillary site, such as the fingertip, to measure the difference in the absorption characteristics at the two different wavelengths to determine the ratio of oxygenated and deoxygenated hemoglobin, presented as SpO2. Similarly, ORi utilizes the same red and infrared wavelengths of light to measure the same ratio of oxygenated and deoxygenated hemoglobin at the same capillary sites. The difference with ORi is that additional wavelengths of light are used to provide additional absorption characteristics to help increase monitoring resolution at higher blood oxygen levels. The output is a numerical value on a 0 to 1 scale. When SpO2 values are below 96%. ORi will always display as 0. When SpO2 is at 96% or above ORi 'provides visibility to the transition from normoxia to hyperoxia'. The device includes high limit alarm with a threshold of ORi value 0.7.
Image /page/2/Figure/3 description: The image shows a monitor displaying medical data. The top portion of the screen shows two graphs with repeating waveforms. Below the graphs, there are two numerical values, 0.00 and 97. The screen also displays the time as 1:27 AM.
Image /page/2/Figure/4 description: This image is a title for a figure. The title reads, "Figure 2 - Illustration of the Graphical Display of ORi". The title is written in a clear, sans-serif font and is centered on the image.
# Mechanism of Action for Achieving the Intended Effect
ORi achieves its intended effect through a multi-wavelength optical sensor that is applied to a capillary site of the patient. Multiple wavelengths of light are passed from the sensor emitter through the capillary site to a photodetector. The absorption profiles at the different wavelengths of light are then processed to provide a numeric index that represents the patient's blood oxygen at higher blood oxygen levels. The numeric index is displayed on a monitor (e.g., Rad-97, Radical-7, and Root) along with the SpO2 values enabled through the same optical sensor. At the
{3}------------------------------------------------
upper limit where the sensitivity of ORi is diminished, the numeric value is fixed and no longer provides additional numeric increases. At this point, the changes in the index are reflected only through a directional indicator or a trend line. At the lower limit where SpO2 values are known to have sufficient resolution (i.e., SpO2 values below 96%), the numeric index is designed to provide no value or 0.
## SUMMARY OF NONCLINICAL/BENCH STUDIES
## BIOCOMPATIBILITY
Biocompatibility testing for the ORi device were leveraged from the previously cleared device. Masimo Root Monitoring System and Accessories cleared under K171121. because the patient contacting components are identical to those of the subject device.
## REPROCESSING/CLEANING
Similarly, reprocessing testing was leveraged from the previously cleared device. Masimo Root Monitoring System and Accessories cleared under K171121.
## ELECTROMAGNETIC CAPABILITY & ELECTROMAGNETIC SAFETY
The ORi is a medical device installed on a previously cleared device, Masimo Root Monitoring System and Accessories cleared under K171121. The electrical safety and EMC tests are leveraged from a prior 510K submitted for the subject device.
## SOFTWARE
Software documentation for ORi was provided according to the FDA Guidance Document, Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices. issued May 11, 2005. The software was found to have a Moderate Level of Concern 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 care, which would likely result in minor injury but would likely not result in serious injury or death due to the availability of other patient vital signs.
The software documentation addressed the ORi algorithm and implementation on the host Radical-7 pulse oximeter and included:
- Software Description 1.
- 2. Level of Concern
- 3. Device Hazard Analysis
- Software Requirements Specification 4.
- 5. Architecture Design Chart
- 6. Software Design Specification
- 7. Traceability Analysis
- Software Development Environment Description 8.
- 9. Verification and Validation Documentation
{4}------------------------------------------------
- 10. Revision Level History
- Unresolved Anomalies 11.
ORi validation testing was performed to demonstrate the device software meets its performance requirements using patient data. Additional details are provided in the "Summary of Clinical Information" section.
## SUMMARY OF CLINICAL INFORMATION
To support the current IFU, a total of 206 subjects with a total of 2330 data pairs (SpO2, SaO2) from two retrospective and one prospective study were submitted by the sponsor for calculation of the ORi values. The retrospective studies were conducted on 52 heathy volunteers (Masimo desaturation laboratory study) and 126 hospitalized participants (Loma Linda) while the prospective study (UC Davis) was conducted on 28 hospitalized patients. Importantly, the two clinical studies on hospitalized patients were conducted on those undergoing general anesthesia.
There were no adverse events when the device was used with concomitant SpO2 monitoring in the operating room environment on patients receiving supplemental oxygen. While there were no study sub-analyses for subpopulations such as but not limited to obese, neonatal, and post-arrest, the device demonstrated benefits for detection of changing PaO2 in the range of 100 to 250mmHg better than pulse oximetry alone. In this way, benefit-risk profile was determined to be favorable for the intended patient populations for the intended use as prescribed by the current IFU.
Labeling mitigates the high intra- and inter-subject ORi variability with respect to PaO2. However, the pooled data demonstrated an AUC >0.8 in PaO2 ranges from 100-250mm Hg. When used with pulse oximetry, the trend of ORi values is beneficial to titrate O2 delivery in surgical patients receiving supplemental 02 therapy.
Specifics of the clinical studies are as below:
Masimo Clinical Lab: 52 subjects with 939 data pairs were collected during stable plateaus when FiO2 was changes in a stepwise fashion. A pair of arterial blood samples were drawn at each FiO2 level and the reference PaO2 blood gas values was collected by using an ABL blood gas analyzer. These reference PaO2 values were time svnched along with the ORi values and stored in the CDB file.
University of California, Davis: 28 subjects undergoing general anesthesia induction had 140 data pairs (ORi and ABG) drawn at 4 time points: baseline, during oxygenation, induction, and laryngoscopy for endotracheal intubation.
Loma Linda University: 126 subjects undergoing elective surgery where supplemental oxygen was administered had 1251 data pairs drawn for analyses. ABG convenience samples were obtained as part of standard of care.
The retrospective study utilized data previously collected prospectively. Subjects included in this study were those who had rainbow R1 25 disposable sensors applied which were in turn connected to a Masimo monitoring system (Radical-7 and Root monitor). The Masimo
{5}------------------------------------------------
monitoring system should have collected data that was continuously logging ORi values or the necessary raw sensor wavelength absorption data to retrospectively calculate the ORi value.
The ORi feature extends monitoring resolution to the hemoglobin oxygen saturation under supplemental oxygen delivery as an adjunct to SpO2 in the range of PaO2 100 to 250 mmHz. The ORi device is to be used in patients undergoing surgery as in the presented clinical data. The retrospective calculation of the ORi in data collection in 2 of the 3 studies demonstrates a nonlinear relationship of ORi to PaO2; there is ORi variability between subjects, and within the same subject.
One study demonstrates use of the device in concurrent determination of PaO2 by arterial blood gas analysis with ORi recording during induction of general anesthesia with the associated changes in oxygenation.
The pooled data demonstrated an AUC > 0.8 in determination of PaO2 for the range 100 -250mmHg when compared to SpO2. The percentage of ORi was greater than that of SpO2 for the same PaO2 values.
The ORi feature is based on wavelength technology the same as with the SpO2 in pulse oximetry. This technology has been shown to have a positive bias in darkly pigmented individuals (Sjoding, 2020).
The UC Davis study was a prospective study with concurrent use of ORi and SpO2 during induction of general anesthesia in the operating room, it supports the proposed indications for use, and represents the real world clinical scenario.
While there are benefits for detection of impending oxygen desaturation and for monitoring of moderate hyperoxia. there are no analyses shown to assure accuracy for subpopulations of users (eg. obese, neonatal, post arrest). Pooled retrospective data analyses of adults (ages 21 to 86 years) are included in the studies.
## Pediatric Extrapolation
For medical devices, the FD&C Act defines patients before their 22nd birthday as pediatric patients. ORi is indicated for patients ages 18 years and older, which includes transitional adolescents and adults. The Loma Linda clinical studies provided data that supported the use of ORi in subjects 18 years and older.
## LABELING
ORi labeling consists of Instructions for Use that includes a summary of the clinical evaluation, and a summary of baseline demographic information and where appropriate, subgroup analyses for age, race, ethnicity, gender and/or sex.
The Instructions for Use also includes appropriate warnings and cautions associated with over reliance on device output in clinical setting.
{6}------------------------------------------------
ORi is an adjunct to SpO2 monitoring in the setting of the operating room with supplemental oxygen administration.
Labeling instructs the user to safely and accurately use the device according to the intended use in the intended use environment as below:
- . Arterial blood gas remains the gold standard in diagnosis of hypoxemia. Reliance on other monitoring (pulse oximetry/SaO2 and ABG/PaO2) remains unchanged with use of ORi (i.e., ORi is an adjunct not a replacement for other monitoring). The trend of ORi correlates with PaO2. For changes in ORi values, whether decreasing or increasing, check the patient first. Changes in cardiopulmonary status can affect oxygenation.
- Instructions on acute decreases in ORi including appropriate troubleshooting and data . interpretation such as checking delivery of O2 to patient, need to reposition sensor, clinical/cardiovascular changes and patient status that may contribute to findings
## RISKS TO HEALTH
The table below identifies the risks to health that may be associated with use of a hyperoxia monitoring device adjunct to pulse oximetry and the measures necessary to mitigate the risks
| Risks to Health | Mitigation Measures |
|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------|
| Inaccurate measurement of hyperoxia or<br>hypoxia leading to escalation of unneeded<br>therapy and false reassurance | Clinical performance testing |
| Incorrect or delayed treatment due to over-<br>reliance on device output for clinical decision-<br>making without using arterial blood gas values<br>for confirmation | Clinical performance testing<br>Human factors/usability testing<br>Labeling |
| Procedure delay or inaccuracy due to software<br>failure or corruption in data transfer | Software verification, validation, and hazard<br>analysis |
| Patient or operator injury due to electrical<br>hazards | Electrical safety testing<br>Electromagnetic compatibility testing |
| Adverse tissue reaction | Biocompatibility evaluation |
| Inaccurate measurement or infection due to<br>unclean surfaces | Reprocessing validation<br>Labeling |
# SPECIAL CONTROLS
- (1) Clinical performance testing under anticipated conditions of use must evaluate the accuracy of hyperoxia monitoring by the device and evaluate all adverse events.
{7}------------------------------------------------
- (2) Human factors/usability testing must demonstrate that the user can correctly use the device, based solely on reading the instructions for use.
- (3) Performance data must demonstrate the electromagnetic compatibility (EMC) and electrical safety of the device.
- (4) The patient-contacting components of the device must be demonstrated to be biocompatible.
- (5) Performance testing must validate the reprocessing instructions for the device. including demonstration of device performance after repeated cleaning and disinfection.
- (6) Software verification, validation, and hazard analysis must be performed. Performance testing must demonstrate compatibility with pulse oximeter devices labeled to be compatible with the device.
- (7) Labeling must include:
- (i) Cleaning and disinfection instructions:
- A summary of the clinical performance testing with the device: (ii)
- (iii) A warning against over-reliance on device output without using arterial blood gas values for confirmation; and
- (iv) Instructions to monitor oxygen delivery and patient clinical/cardiovascular status when device output changes.
## BENEFIT-RISK DETERMINATION
The probable risks of the device are based on data collected in a clinical study(ies) described above.
- 1. Adverse events such as pulmonary fibrosis, retinopathy of prematurity caused by hyperoxia due to inaccuracy of measurement.
- 2. Incorrect or delayed treatment due to over-reliance for clinical decision making without using arterial blood gas values.
- 3. Users without expertise operating the device leading to adverse events or ineffective procedures.
- 4. Incorrect or delayed treatment due to use outside of intended use environment.
- 5. Procedure delay due to corruption in data transfer.
The probable benefits of the device are also based on data collected in a clinical study(ies) as described above.
- 1. Benefits in detection of impending oxygen desaturation and for monitoring of moderate hyperoxia.
- 2. Monitoring resolution to the hemoglobin oxygen saturation under supplemental oxygen delivery as an adjunct to SpO2 in the range of PaO2 100 to 250 mmHg
{8}------------------------------------------------
The retrospective calculation of the ORi in data collection demonstrates a non-linear relationship of ORi to PaO2, however, there is ORi variability between subjects, and within the same subject. Subpopulations, including vulnerable ones, have not been individually identified, studied, or analyzed. This uncertainty is addressed through labeling and special controls. The device is limited to specific users and environment of use, and has a high limit alarm threshold of ORi 0.7. Special controls warn against use outside of an adjunct to pulse oximetry.
#### 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 OR i feature is intended to be used in patients undergoing surgery as an adjunct to SpO2 for increased monitoring resolution of elevated hemoglobin oxygen saturation levels (e.g., due to the administration of supplemental oxygen).
The ORi feature is indicated for the monitoring of hemoglobin oxygen saturation levels in patients 18 years and older (adults and transitional adolescents), on supplemental oxygen during no-motion conditions perioperatively in hospital environments.
The probable benefits outweigh the probable risks for the ORi device. 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 ORi is granted and the device is classified as follows:
Product Code: QWE Device Type: Hyperoxia monitoring device adjunct to pulse oximetry Regulation Number: 21 CFR 870.2720 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.